All Stories

T3 Connect lets developers run coding-agent prompts remotely

Bitrig ships an iPhone app built without opening Xcode

Long-horizon coding agents increasingly fall back to Bash

Badlogic explores append-only logs for deterministic multiplayer games

CSS animations run smoother when they change transforms instead of layout

super.engineering runs coding agents in isolated worktrees

Dagger ships version 1.0 of its development platform

Thdxr questions whether monorepos still help coding-agent workflows

Lumen combines axe-core checks with agent-guided accessibility fixes

Albert Gu compares GPT-2 and GPT-4 pretokenizer regex rules

Megacute introduces a CuTeDSL megakernel with an on-GPU interpreter

SemiAnalysis examines Trainium support for model training

Fireworks offers MiniMax M3.1 Flash in serverless preview

Modal details four optimizations for Sakana’s Namazu API

Dessa trains a speech model using voice conversations alone

OpenRouter ranks GLM 5.3 first in security-audit model spending

Charlie O’Neill argues broad real-world environments matter for RL

SemiAnalysis examines ASML’s patented hybrid-bonding tool design

BeNice! shares KV caches across recurrences in looped models

Avalon-M1 trains agent organizations with collective rewards

A Blender workflow guide uses scene blockouts to control AI animation timing

Block's Dessa speech model was trained on one GB200 NVL72

LangChain shares a 21-minute introduction to continual learning for software teams

Mubit launches a platform to train small models from agent task traces

ASML brings lithography-grade overlay precision to hybrid bonding

HeyGen Video 1 generates 30-second clips through an API

RLCR trains language models to account for uncertainty

Sam Altman says OpenAI's strongest model needs stronger safeguards

Grok Bot generates Excalidraw diagrams from a single prompt

Point2 Technologies explores RF-over-plastic links for AI data centers

OPAL lets a coding agent change PyTorch optimizers during training

Giffmana cautions against scaling claims from zero-order LM training

Artificial Analysis measures Muse Spark Open serving efficiency across GPUs

OpenBMB shares reproducible MiniCPM self-distillation experiments

A researcher argues Chinese labs may be improving distillation efficiency

Fireworks reportedly serves DeepSeek V4.1 Flash above 1,500 tokens per second

General Reasoning introduces Avalon-M1 for agent organizations

A two-step Qwen distillation targets real-time image generation

ComputeSDK compares object-storage lifecycle performance

ComputeSDK benchmarks gateways serving Kimi models

NVIDIA Nemotron 3.5 Bolt arrives on Ollama with a 4GB E4B variant

Report: Hi3D V1.0 code and weights reportedly available for image-to-3D

Researchers question DeepSeek’s reported 155 trillion daily token figure

Baseten says Mirendil-Base-Large led private-code perplexity tests

SemiAnalysis compares expanded-beam connector maintenance, loss and cost

A MiniCPM-V camera assistant cuts local model calls by over 90%

Vals finds provider choice changes open-model cost and speed

Loupe compares webpage implementations against design references

Theo adds a council review before his coding agent merges

Pvncher proposes scheduled manager-agent polls instead of Codex Goal

OpenAI publishes seven runnable API demo projects

Muse Wonder Full gives users finer control over writing style

Perplexity Computer turns a Raspberry Pi into an agent-built arcade

Perplexity Computer integrates LexnLin’s open-source website-building skill

A developer charts PR growth across six agent-orchestration changes

Prime Intellect publishes a 2.5-hour walkthrough of its agent harness

OIDC connection components target provider-by-provider integration work

Pi-subagents adds a council mode for parallel model critique

OpenBMB ships StaffDeck preview with async, resumable agent workflows

Vercel Connect adds scoped, managed Stripe keys for agents

Vercel Agent investigates deployments read-only before requesting write access

Agent permission requests could bundle planned actions into one approval

LiveKit demonstrates video avatars with open models on Modal GPUs

SenseNova distills robotic experience into an open 27B model

GrottoAI coaches leasing agents live using streaming transcripts

Mastra publishes a guide to MCP authentication and authorization

Mastra lets developers filter signal types from agent live streams

Omnigent makes custom agents installable across every host

Boat compares sandbox providers by fleet capacity per budget

ComputeSDK publishes its latest Browser Throughput provider rankings

Archil and Casco schedule a $50,000 agent-building hackathon

Signal exposes API decisions in a live multi-vehicle traffic simulation

A computer-use agent controls a robotic arm using vision alone

Infisical plans OAuth secret support for Agent Vault

Cartesia shares recording tips for better professional voice clones

Kuncheng Guid links orchestration changes to a sharp rise in weekly PRs

Amp documents scheduled and event-driven agent automations

Vercel plans OIDC authentication for deployments

Dagger's GitHub app runs repository checks in Dagger Cloud

A three-server design separates agent inference, orchestration, and execution

Dagger releases its open-source 1.0 engine

Yab imports Arc spaces, pins, passwords, and history

Cursor adds desktop control to coding agents

OpenAI demonstrates a Dots workflow for fixing user-reported bugs

Pipecat's TTS server offers a local voice-agent backend for macOS

AssemblyAI shows a captions app built on its 32-language speech API

Decode compares three sandbox layers for coding agents

Nous Research opens an experimental Hermes Labs plugins repo

Polylane launches agents for Cloudflare Workers, Durable Objects and Workflows

Claude coding agents return videos and screenshots alongside end-to-end tests

Anthropic publishes Claude Duet safety and privacy details

Software factories masterclass turns successful agent runs into regression evals

Portless v0.15.11 fixes Tailscale HTTPS port conflicts

PLE benchmark tests agents on 85 professional physical-engineering tasks

Ethan Mollick reports prompt injection may be less effective on newer models

Ollama recommends local inference for sensitive defensive security work

Swyx urges developers to review transactional emails before shipping

Sonar Vortex feeds project rules to Cursor agents and checks their changes

Baseten forms a network of partners to build custom RL environments

Agents improve downstream package efficiency by up to 1.31× in a shared benchmark

ProgramBench tests whether agents can rebuild removed research code

Decision Index 0.4 switches its scores to private benchmarks

Tembo adds stacked pull requests, session exports, and faster search

Epoch AI marks three new benchmarks flawed and one verified

A Grok Bot user reports browser blocks, dropped links, and usage limits

DeepSeek V4.1 Flash 1017 leads public models on the Cyber Index

Simple Reviewer checks AI-written code against recorded evidence

Property testing can expose bugs that ordinary example tests miss

Bloomberg reports AI-driven vulnerability discovery is outpacing patching

Lech Mazur publishes debate and short-story model leaderboards

An agent workflow tests Verus specs against historical CVEs

LearnOpenCV finds Muse Wonder misses three of five match goals

Amp investigates intermittent macOS and iOS WebSocket failures

A developer says DeepSeek helped build a verified Apache replacement for $50

A model evaluator argues accuracy can hide calibration shifts

DeepSeek V4.1 Flash 1017 raises Cyber Index score to 57%

OpenCode can post long-running task progress to Slack threads

A cybercrime analysis argues AI-enabled harm may mature gradually

Data Agent Benchmark heads to EMNLP with 40-plus submissions

Voice Arena adds native-speaker voting to its TTS leaderboards

A Sonos firmware audit finds revoked eMudhra keys remain trusted

Decision-model researchers warn benchmark scores can hide answer-position bias

Pvncher argues clear prompts can act as shareable software programs

ZCode offers limited free access to GLM-5.3 coding models

Kimi K3.1 Pro completes a 3D build in five minutes for $0.55

KURE-v3 adds bilingual dense, sparse and multi-vector retrieval

Qdrant tests single-vector PDF pages against late-interaction retrieval

Fastino releases GLiDE v1.2 with a single-pass decision training recipe

Letta opens FrontierMemory submissions for its continual-learning leaderboard

Mubit releases Banyan Sapling for checking claims against context

Facet uses Python to answer questions across complete CSV datasets

Fastino releases GLiDE v1.2 with image inputs and 71.5 Decision Index score

Exa powers Revolut's securities news agent for over one million users

Turbopuffer releases an async Rust SDK for vector database access

Datalab Lite cuts OCR to $0.50 per 1,000 pages

Google Research highlights open models for frontline TB screening

Nomic previews an autonomous physical-engineering assistant

Quest Diagnostics reports unauthorized access to Quanum patient data

Folio turns image briefs into editable, offline HTML presentations

DejaVuCoder recommends reading source material before asking AI to curate it

Vals Legal Index ranks Wonder Full first on revenue-weighted legal work

Sweden's government offices restrict ChatGPT and Claude on work PCs

Carbon-X runs at 21 tokens per second on a Mac

Gemini Argon draws a pelican on a bicycle in 217 lines of SQL

CodeCrafters adds a challenge to rebuild Claude Code skills

Codex automates DaVinci Resolve edits from footage on an SD card

tsc-ts 0.0.8 cuts type-checking time and peak memory

Amp adds interface color filters for color-blind users

OpenSource Recruiter ranks candidates from a job post

Factory lets teams turn Slack threads into code pull requests

Thdxr is building a cross-platform native UI library for its apps

Lexington Themes helps coding agents reuse designer-made styles

Aidenybai calls for formal verification beyond software tests

WebGL Fluid packages a GPU Navier-Stokes simulation as one call

Matt Pocock shares a /software-factory planning workflow

scriptc v0.4.2 adds JSX and TSX support to its compiler

Matt Pocock uses a one-question-at-a-time prompt for unclear projects

Geoffrey Huntley suggests using agent loops to fix O(n) bottlenecks

ComfyUI releases a MOSS Image LoRA for images up to 10 megapixels

Study reports harness diversity improves agent training on unseen configurations

Intel’s fab tour explains transistor advances and chipmaking limits

Dwarkesh’s semiconductor flashcards turn a fab tour into a study deck

Google DeepMind tests auctions for routing model responses

Future Chunk Prediction improves autoregressive video dynamics

Recursive launches Flint, a local model for frontend coding

Wafer routes inference through You.com’s OpenAI-compatible API

HUD opens a marketplace for private AI training and evaluation data

Meta’s Muse Glimmer 30B targets on-device agent tasks

OpenClaw adds DeepSeek V4.1 Flash support for agents

Speechify and Baseten launch Simba 3.5 for streaming voice

Exposed Nvidia monitoring endpoints reveal restricted B300 chips

You.com launches an inference router with failover and a 99.9% SLA

Gemini vision and SAM3 form a workflow for image labeling

NSF selects teams to move AI infrastructure efficiency research into deployment

SAM 3.1 speeds up multi-object video tracking with Object Multiplex

CoreWeave previews NVIDIA HGX Rubin NVL8 for deployment this quarter

SemiAnalysis tracks early construction signals to forecast data-center builds

A study compares Opus 4.8 with experts reviewing 124 Harvard papers

agent-browser 0.39.2 denies actions when policies are invalid

Capy 0.5.0 adds OIDC access for GCP, AWS, Azure and Vault

Google's Agents CLI packages seven skills for building ADK agents

Ramp explains why it built its own model-agnostic agent harness

Firstmate adds Rex support across coding-agent harnesses

Anthropic transfers Agent Skills stewardship to the Linux Foundation

Ethan Mollick shares a reusable Codex computer-use prompt

Google Cloud previews isolated virtual machines for AI agents

Karin Nguyen argues agent permissions must cover delegated actions

E2B adds Veris receipts and Notte browser access to its Cookbook

Vercel says its platform now includes primitives for at-scale backends

Grok Bot adds user-approved sign-ins through 1Password

axuse gives coding agents browser and desktop control through MCP

Intuit says its QuickBooks voice agent helps pay invoices same day

Vercel Daemons support persistent outbound connections for Discord

Theo's harness explainer sparks debate over what coding agents actually see

Artificial Analysis ranks Claude highest for writing style on AA-PersonalityBench

Tailscale joins Agent Baseline's Secure Software Factory initiative

Artificial Analysis releases CritPt v2 with 70 revised physics challenges

Raindrop launches production reports linking merged PRs to agent behavior

Subquadratic’s Snap 1.1 ties for first on the Decision Index

Parallel adds EU data residency for its web-search APIs

OpenClaw 2026.10.6 patches security and startup issues

Amp recommends asking agents for end-to-end proof before code review

Google DeepMind and Penn rebuild text detection from readable features

Braintrust compares decision models on harmful-content classification

Artificial Analysis warns CritPt v2 scores are not comparable to v1

Claude automates sensitive-information blurring in video edits

A developer reports a $15,000 Cloudflare bill after startup credits expired

Doodlestein shares a fuzz-testing skill for finding software bugs

Anthropic and Theorem use Claude to prove properties of 123 C libraries

Report: Railway reportedly tells all customers to rotate secrets after breach

Researchers reportedly find 10% of eligible Codex traffic escaped monitoring

Anthropic says Claude proved security properties in over 100 open-source libraries

Cognition open-sources a plugin for cybersecurity threat remediation

PHP security releases reportedly patch php2shell flaws

Mastra lets custom gateway models report costs in metrics

Liquid d1-ultra gets all 1,960 claims right on ClaimBench

A GLM-5.3 study measures how abliteration weakens refusal safeguards

OpenRouter adds centralized API key spending and lifetime controls

pi-cached-compaction preserves prompt caching during compaction

FreshStack refreshes its leaderboard for technical-domain retrieval

MemoryTax reports Pi with Opus 5.5 scored 99% using raw-history search

Grok Bot reportedly adds iOS and Android system app connections

Canva Craft separates image layout planning from rendering

Uber extends ChatGPT Work to its 30,000-person workforce

Canva introduces Craft, an image model that plans layouts before rendering

ChatGPT’s Intelligent UI turns personal learning prompts into guided lessons

Microsoft’s MAI-DxO combines five roles for sequential diagnosis

Swyx uses Opus 5.5 to estimate delegated agent work

Quiver previews SVG icon families with switchable styles

Kast founder describes holding headcount steady as revenue grows

Uncommon Web catalogs 425 unusual libraries in live demos

CopilotKit Soar offers self-hosted AI coworkers for company workflows

T3 Code reports processing 36.5 trillion tokens in 72 hours

OpenAI describes how ChatGPT ads stay separate from answer generation

scriptc and tsc-ts now compile and type-check each other

Genspark recaps ten updates, including its GenCode CLI assistant

Zed 1.25.2 adds direct editing of inlay hints

A code review workflow uses before-and-after agent diagrams

Supervibes bundles app building, backends, and App Store releases

FrankenTorch attempts a PyTorch-compatible tensor stack in Rust

PandaCode runs multiple coding CLIs in one desktop workspace

Decks turns slide comments into agent-driven presentation edits

A developer recommends rebuilding legacy WordPress sites with coding agents

Amp adds a BYOK option for GitHub Copilot subscriptions

Amp adds interactive mini-apps to agent threads

OpenAI details the retrieval and auction tools behind ChatGPT ads

Robert Martin describes agents building and checking a system from a spec

JetBrains offers Junie Lite free for everyday coding tasks

Devin configures and tests iPhone Duo apps through terminal and simulator

Google demonstrates Gemini Argon turning Chaco Canyon scans into a 3D site

Infinity claims 216 experiments doubled Nemotron serving throughput

Google releases Coral NPU compiler v1.0 and launches Coralboard devkits

Google DeepMind uses Gemini 4 Argon to build an interactive anatomy viewer

Mirendil reports a strong code model trained by one researcher

Google DeepMind study finds RL can widen watched versus unwatched compliance

Pieter Abbeel explains faster humanoid policy training with world models

OpenRouter reports median agentic cache rates rose to 85%

Databricks makes AI Runtime generally available for GPU workloads

Kling rolls out API access for its Kling 4.0 video model

FastH3 Omni runs local video generation on DGX Spark and Apple Silicon

Common Crawl releases an October archive with 2.16 billion pages

Baseten offers Mammoth-1 and Elephant-1 decision models free on AI Gateway

vLLM and Ant Group open-source Humming quantization kernels

AI21 uses Kueue to automate scheduling across a 10,000-GPU fleet

Kling 4.0 launches on fal for text, image, and reference-to-video

HeyGen brings video and speech models to fal

Nemotron Super VL agrees with a checklist despite missing a step

Inferact, AMD, and NVIDIA pursue LLM decode gains with megakernels

Notion revives Elo ratings to evaluate its Auto model router

Full-vocabulary score-centering measures the cost of removing tail bias

Sam Altman discusses coding jobs, cheaper compute, and new computers

Notion uses Elo comparisons to tune its model router

OnDeviceLLM runs MiniCPM-V 4.7 for offline photo and document questions

Gemini builds a reusable CLI for architectural drawings

vLLM adds native PyTorch serving for TPUs

SGLang adds GPUs to running MoE deployments without restarting

Modal releases reinforcement learning training library

Tinker introduces StableReinforce to stabilize off-policy training

A paper gives agents KV-cache controls and reports lower costs

Vals AI schedules a hackathon for small-model training and evals

Corridor uses SmithTune traces to train a 9B security model

OpenCode reports 72.8 trillion tokens processed in two days

SemiAnalysis examines DeepSeek's Ascend 950PR software and hardware stack

Together publishes recipes for user-controlled post-training loops

The Turing Post explains Gaussian splatting as a basis for robot memory

AMPD routes multi-turn agent prefills around decode-worker load

Morph opens application-only access to DeepSeek V4.1 Flash for defense

Advantage-conditioned policy extraction reaches state-of-the-art RL results

Gemini 4 Argon builds a detailed Shore Temple scene in Blender

AgentMail gives each AI agent a dedicated email inbox

CopilotKit shares an open interface for interactive agent answers

Cartesia runs a coffee cart with a voice agent on Managed Agents

Pydantic AI and E2B show coding agents resuming after worker crashes

Decode uses progressive disclosure to load agent skills on demand

Baseten partners on infrastructure-level safety for AI agents

Vapi launches CX for voice agents handling complex customer calls

OpenClaw opens its internal agent platform to public contributors

A developer migrates Hermes automations to Antigravity by reusing its config folder

mcporter brings MCP tools into harnesses without native MCP support

Amp traces a service issue to CPU spikes in its durable execution layer

Superwall outlines an agent loop for testing and deploying paywall changes

Robo-View uses Isaac to turn an SO-101 arm into a camera operator

Claude Code 2.1.307 fixes duplicate MCP tool calls after disconnects

NVIDIA demonstrates Hermes building a Microduck robot training environment

Simular says Agent S4 improves computer use with evolved interfaces

Straiker reports AI agents automated attacks on more than 400 financial targets

A Blender guide shows Claude building and rendering a game-course previz

Microsoft says Storm-0940 used ARTEX agents to reach cloud admin access

Dream-1 transfers robot control to 27 unseen simulated embodiments

A researcher challenges SWE-bench Multimodal v2's multimodal claims

Security thread reports CVEs rising from 4,000 to 15,000 per month

AA-PersonalityBench finds Gemini models rarely admit uncertainty

Claude Sonnet 5.5 ties GPT-6 Astra on revised MLCR-AA

Greptile V5 runs specialist subagents on each pull request

A security checklist urges developers to update devices and package managers

HeyGen Voice Turbo tops a controlled TTS leaderboard

C. Wolfe Research lays out a statistical workflow for subjective agent evaluations

CyberCartel used a multi-model harness to target Latin American banks

A simulated robot duck detects falls and sends an emergency alert

Meta and Michigan State find errors in LLM-built reasoning graphs

Jevbench ranks Bespoke Nimble-v4 third among decision systems

Claude Sonnet 5.5 produces less mergeable code at max reasoning

Vercel firewall blocks known patterns targeting a Node.js Brotli RCE flaw

Sonnet 5.5 scores 72.4% versus 24.3% on ARC-AGI-3 across harnesses

Anthropic says Claude increasingly supports safety research and model training

Anthropic says it delayed broad Mythos access to strengthen cyber safeguards

Google's OO-Harness routes tasks to specialized agent harnesses

Claude Code 2.1.308 ships CLI reliability fixes

FrontierMemory proposes testing whether agents learn across related tasks

Qdrant’s MLOps Amsterdam recap finds chunking gains depend on the task

Keenable tops Vals AI’s web-search index with GPT-5.6 Sol

DeepSeek Search scores 69 on Artificial Analysis's Search Index

Databricks describes MemCurrent memory synthesis from agent traces

FrontierMemory benchmarks whether generated memories help agents solve tasks

DeepSeek Search API enters a search benchmark at a low per-query price

OpenClaw adds Baseten elephant-1 and mammoth-1 decision-model support

Nemotron-3.5-Embed raises recall on Turbopuffer's PDF search benchmark

LangChain explains file-backed context offloading for agent memory

Baseten makes NVIDIA Nemotron Retriever models available for deployment

NVIDIA Nemotron 3.5 Parse leads ParseBench under one billion parameters

Iso Morph shares practical agent-engineering tradeoffs

OpenAI says ChatGPT Ads has reached 100,000 advertisers across 89 countries

Mistral and NVIDIA plan benchmarks for industrial engineering agents

ComfyUI adds HeyGen Voice Turbo and instant-clone nodes

Pi adds workspace mentions for jumping between chats and terminals

Figma Weave shares a reusable workflow for relighting video

Vals launches a GDP-weighted benchmark for finance agents

Jef Frankle identifies task specifications as an enterprise AI bottleneck

Learn DeepInfer maps request execution across 12 interactive chapters

DeepLearning Focus condenses a coding-agent harness course into a webinar

An engineer uses an agent to maintain launch lists and weekly work logs

ReMind pairs a voice-led dementia game with an SO-101 robot arm

Gemini Argon turns a handwriting sketch into a usable font

Claude Code runs separate accounts with CLAUDE_CONFIG_DIR

ComfyUI adds FLUX 3 Max text-to-video and image-to-video workflows

Nathan Lambert publishes a course deck on open language models

Diffusers adds NVIDIA and Baker Lab's RFD4-Proteina design model

Venice Studio adds a low-resolution draft mode for Seedance 2.5

Superwall moves paywalls into code for agent-driven optimization

Nexus production shares a workflow change after high daily generation costs

Techhalla shares an AI music-video production workflow

OpenClaw migrates its frontend from Lit to Solid 2.0 with agents

v0 adds clickable browser-use annotations to its iOS app

Linear's Tom Moor turns merged PR lessons into agent guidance

Thdxr says outside contributors lack the context of internal coding agents

Overalls documents its NixOS architecture for agent workspaces

Amp engineer recommends incremental releases for billing code

Laude introduces RevEngine to make AI code reviews less painful

Solomon Hykes argues CI should follow agents as they develop

Jediah Katz maps a data flywheel between agent harnesses and models

Google says Gemini 4 Argon processed nearly 25 trillion tokens in 72 hours

Sakana releases QD-Rec recommendation research and code

Deedy Das claims Mercury 3 is 2–4× faster on OpenRouter

Musk reportedly targets 440,000 Vera Rubin computers by Q2 2027

MiniCPM-V 4.7 reaches 20.5 tokens per second on iPhone 18 Pro

Gradium releases Phonon, an open on-device text-to-speech model

OpenRouter says agentic token use is 34× higher than in February

Meta confirms it runs Google TPU inference with SGLang in production

Devin and Modal publish a template for training and deploying custom models

Bria releases Fibo 2.0, an open-weight model for image editing

Anthropic paper localizes reward-hacking updates for later removal

Gemini 4 Argon estimates numbered body keypoints from reference images

Krea 3 Ultra places fourth on the image-editing leaderboard

Revolut's prolonged outage renews questions about cloud failover

RunInfra serves Ornith 1.5 122B at 302 tokens per second

An iOS voice-agent demo combines on-device speech models

SparkLLM releases Spark-X2.6-4B with a million-token context

General Compute splits inference prefill and decode across different chips

Browser Use releases rl-env-use for building RL environments from cases

Timestral leads GIFT-Eval and TIME charts in its release announcement

Ollama adds the Ornith 1.5 122B model for local inference

Fastino adds Qwen3.6-35B-A3B to its training and inference API

General Compute will offer Positron Atlas inference systems

Reflection's Beam 1.0 ranks among the fastest open-weight models on Vals Index

Krea 3 Ultra reaches the top five on image-editing evaluations

Vals finds no tested model router beats the best single model on cost and score

DoubleCat and SemiCat aim to remove self-conditioning from diffusion language models

Bria releases Fibo 2.0 open-weight image generation and editing models

A decider-model researcher recommends tuning thresholds on your own data

Electric Plant Co. trains Bombadil on seven million hours of plant signals

SF Compute describes a programmable market for GPU capacity

Simon Willison builds a multiplayer RTS with Claude Opus 5.5

SpaceX reports rapid growth in AI compute revenue and capacity

Andrew Carr post-trains Gemma 4 E2B into a fast decision model

Argon processes raw JWST captures into a star-formation image

Marvell demonstrates photonics that places HBM up to 50 meters from GPUs

GPT-6 Astra Pro uses a separate execution mode from reasoning effort

Anthropic report details large compute contracts alongside rapid revenue growth

EAGLE-4 releases adaptive speculative-decoding drafter for hardware and workload

Agentic RL data scaling laws favor environment diversity over trajectories

Krea 3 Ultra reaches 1,151 Elo on the image-editing leaderboard

A Codex capacity dashboard records 271 overload errors in 48 hours

Zyphra reports faster long-context serving on AMD MI355X GPUs

Google open-sources TorchTPU for native PyTorch workloads on TPUs

OpenBMB adds MiniCPM-V 4.7 support to vLLM

DeepSeek V4.1 Flash runs in a dual-DGX Spark inference demo

Flora releases open models for robotics video labeling

Laravel Herd 2.0 adds isolated workspaces and Git worktree support

AgentVFS maps live service data to files and actions to virtual CLIs

A practitioner runs agent graphs in isolated cloud sandboxes

A Vercel workflow runs sandboxed agents that spawn other agents

T3 Code reports 4.5 million completed agent turns in one day

Researchers publish a field guide to evaluating AI agents

Grok Bot preview adds editable files, task views, and diagnostics

Gemini 4 Argon outperforms its general score on a robotics benchmark

ego (lite) lets coding agents browse websites through a Chromium browser

Claude Code 2.1.306 fixes cloud login and MCP-heavy session errors

Cline's Goal plugin checks work before an agent marks a task complete

Cloudroom offers an open-source home for cloud coding agents

OpenCode turns a phone screenshot into a scheduled task

Overalls offloads agent VM compilation to distributed Nix builds

Overalls adds zone-scoped message boards for agent coordination

PlanetScale OAuth phishing flow targets OpenCode users

Co-op Anything gives agents a playbook for modding PC games

Fastino outlines six components of a reliable agent harness

AssemblyAI previews TTS-1 for conversational voice agents

Amp adds per-tool approval policies for MCP actions

Teknium previews a Meshy plugin with MCP, skills, and desktop integration

Harness Lens offers a visual guide to comparing agent harnesses

TanStack AI plans a pluggable computer-use package

A developer moves agent workspaces into isolated Incus containers

Peter Steinberger uses an agent to mute AI-generated reply slop

Mirage gives agents a policy-controlled virtual terminal

Amp documents setup and resume scripts for project Orbs

Cua releases Spaces SDK for running agents across chosen computers

Mirage unifies agent access to cloud data through a virtual terminal

Audio Studio MCP generates game audio locally with Stable Audio 3

Call4Me connects Grok Bot to automated subscription-cancellation calls

Gemini Argon plans a robot project and delegates coding to Opus

Mastra releases conformance tests for custom framework adapters

Claude Desktop and ChatGPT users report blocked MCP approvals

Hugging Face Agent Manager coordinates agents across coding harnesses

Arena ranks DeepSeek V4.1 Flash 1017 first among open models for agents

Factory lets Linear issues trigger Droid investigation and pull requests

Grok Bot can drive a local browser and hand work to coding agents

Gemini Managed Agents bundles code execution and persistent workspaces

LiveKit releases turn-detection and adaptive-interruption models for agents

Omnigent 0.19 adds an MCP gateway and SSH-based repo access

Unhoard turns X bookmarks into tasks for connected agents

Corey Ganim details ten Grok Bot workflows for personal operations

AgentCore guide shows browser agents paying for x402-protected resources

PHP security notice warns users to prepare for critical update

Artificial Analysis clusters models across 30 personality traits

ChatGPT adds PIN and biometric protection for locked chats

T3 Code proposes deleting 9,000 low-signal tests to stabilize CI

tsrs reports TypeScript builds in 0.6 seconds using 0.8 GB

Hamel Husain shows how to select and threshold decision models for evals

ARTEX AI penetration-testing tool appears in attacks on Korean and Japanese firms

NVIDIA releases Flora models for labeling and evaluating robotics data

Terminal-Bench fixes expose widespread verifier and scoring weaknesses

Weak eMudhra certificate keys could let attackers impersonate websites

Gemini Argon helps derive new exact solutions for fusion simulations

LangChain adds human-in-the-loop controls to Managed Deep Agents

Vals introduces ClaimBench for testing financial decision models

T3 Code publishes measured token and cost data from landed PRs

Simon Willison shares reusable prompts for engineering tasks

Lust cuts ts-rust release builds from 17 minutes to 16 seconds

Deep Learning Focus outlines a workflow for evaluating subjective agent tasks

A coding review finds MiniMax M3.1 Flash strong at frontend work but uneven at verification

Muse Wonder Full ranks seventh in Agent Arena across real-world sessions

OpenAI reports coding agents disabled or concealed misalignment monitoring

Vals finds safety failures in chatbot conversations with teens

Terminal-Bench reviewers uncover widespread benchmark defects

DeepSeek V4.1 Flash 1017 scores 91.3 on a 940-puzzle benchmark

Laminar launches flow-1 to inspect agent traces for hidden errors

OpenCode says its team is clearing issues after the 2.0 launch

Anthropic describes its multi-agent review process for Claude Code

Lech Mazur argues cryptographic video signing could prevent deepfake confusion

Perplexity Computer adds offline local execution on Mac

Anthropic paper finds many transcoder features align with MLP neurons

Researchers train language models to report expert routing after ablation

TestingCatalog finds confidential-VM setting for Muse sessions

FrankenTerm plans encrypted QR transfer of Mac workspaces to iPhone

Artificial Analysis tracks steep cost declines at fixed intelligence scores

Uber uses spend tiers and CostCheck to govern AI engineering costs

AgentVFS cuts agent task tokens by 52% while raising success rates

Devin Fusion ties for the Coding Agent Index lead at lower task cost

Runinfra launches coding-agent inference subscriptions starting at $10 a month

OpenVLHarness uses multimodal memory and tools to improve visual agents

Jev and ontologies route decisions by confidence before invoking an LLM

Google DeepMind finds self-evolving agents can forget earlier tasks

Cloudflare’s Clef decision model becomes available through Ollama

Turbopuffer adds one-call native reranking for search results

LightOn releases SlideOn sparse retrieval models for English and multilingual search

Paulius Ztins recommends treating agent ontology changes like code changes

Poliscope searches 130 million civic records in 0.87 seconds

Meta’s ProPerMem study finds proactive assistants struggle with timing

Datalab adds PDF and image form-field detection to its API

OXR trains its document parser from clustered failure analysis

Exa's Search Index compares cost, performance, and latency across 1,700 tasks

SlideOn converts late-interaction retrieval models into sparse indexes

Hamlet launches 10,000 council-member profiles using AssemblyAI diarization

Gaggle reranker adds Sentence Transformers CrossEncoder compatibility

AgentVFS proposes exposing live service data through a virtual filesystem

Cursor breaks down agent inference spend and reports a 7% cost reduction

OpenAI lets API users cache stable prompt context for 12 hours

Firecrawl gives ChatGPT and Claude access to 270 million Alexandria records

MiniMax M3.1 Flash leads a search leaderboard at lower reported cost

OpenBMB showcases ghfind’s GitHub contribution scoring workflow

Jev beats Clairic on a 100-case payee extraction evaluation

Épi reports mathematical discoveries from a persistent research agent

OpenAI acquires Orchestra Bio to coordinate drug development

Gemini 4 Argon builds an animated, song-synced periodic table

Gemini 4 Argon scores 61.1% on Ramp Accounting Bench

Software engineering job postings rebound as senior and AI roles grow

Amp improves dictation speed by 20–40% across its request path

Amp’s founders describe a 21-person team shipping around 100 releases daily

Sophont's Holon-S1 maps gene activity across pathology slides

Claude designs toxin-binding proteins that two labs test in vitro

Warp reports 40% more merged PRs after adopting software factories

Google demonstrates Gemini Argon building a real-time WebGL fur engine

Coco Labs launches Vyb for editable, brand-matched graphics

Glass Health launches its patient agent on mobile

UniqueHuman launches Niq to track migraine signals and coordinate care

Arda turns product designs into manufacturing plans for engineers

Citrini sends Claude-designed proteins to a lab for testing

OpenAI acquires Orchestra Bio to coordinate drug-development programs

Krea says its image model places fourth on multi-image editing

SQS recommends parallel variations and dictation for coding-agent work

Core Auto invites founders to build businesses operated with agents

Arvind Narayanan argues agent evaluation will become core engineering work

Anthropic reports lab tests of Claude-designed scorpion toxin binders

Epoch AI finds frontier models handle defined tasks but miss open-ended work

Luis von Ahn imagines AI tutors adapting to each learner's gaps

Meta says Muse passed 10 million US downloads in 40 days

Anthropic releases lab data for 17 Claude-designed scorpion toxin binders

ComfyUI reports 23.2 million Hugging Face downloads in a week

Google previews Gemini agents for government research and document workflows

Browser Use raises Qwen trial forecasting from 0.53 to 0.78 for $8

Terminal X reports 88.6% agreement on 500 investment judgments

Fable 5.5 automatically crops and pads images for social posts

Unsloth releases 250GB quantization of DeepSeek Flash 1017

Google demonstrates Gemini Argon building a racing game with Blender

SemiAnalysis reports TPUv7 beats NVIDIA GB300 by 1.64× in performance per dollar

Practitioner fine-tunes FastConformer on saved Parakeet transcriptions

OpenAI Decisions API reportedly gets a playground with Predicate, Choice, and Score options

Together launches post-training platform for supervised fine-tuning and reinforcement learning

DeepSeek reportedly helps Huawei shape its next-generation AI chip designs

Matt Pocock shows an agent iterating on diagrams in tldraw

SGLang adds low-latency mode for DeepSeek inference, reaching 928 tokens per second

ComfyUI adds support for the open-weight MOSS-Image model

SemiAnalysis reports Vera Rubin NVL72 delivers up to 7.3× performance per dollar

Skyfall reports SKY-001 matches Astra at 79.7% CAD IoU for $0.005 per part

Vercel open-sources libfx prototype builder for HTML artifacts

OpenCode developer delegates desktop work through one pinned agent session

OpenClaw v2026.10.5 adds undo to Skill Workshop 2.0

Crusoe will add Perplexity's open-source SPACE sandbox to Managed AI

Mollick reports new Claude Projects uses independent agent threads

Modal reports NVIDIA Vera delivers up to 2× agent-workload throughput

Zed adds Figma access to Delta through MCP

A Salesforce study finds agent teams fail to verify peers across boundaries

Photon makes its project-management MCP server generally available

Nace releases Drex Max for visual action selection, reporting 88.3% on Mind2Web

Orchard open-sources a local app for semantic photo search

OpenCode maintainer reports similar agent products were attacked in recent days

A Gemini Argon demo builds an offline health app with Gemma

Google DeepMind agents find Lean-verified rules for 11 Busy Beaver machines

Claude Code 2.1.304 adds required human approval for selected tool calls

A DeepSeek variant reportedly finds a vulnerability missed by a frontier model

A security researcher warns refusal-removed models could aid attacks on outdated systems

Amp rolls out usage charts that track long-lived agent threads

Claude Code catches a cryptominer during a Mac temperature-app project

Turbopuffer cuts vector-search disk reads by up to 80% on one cluster

ChatGPT Slides adds real-time collaboration and direct slide editing

OpenAI evaluates behavior-preserving migration of legacy COBOL systems

Developers credit DeepSeek with accelerating open-model adoption

A developer says agents can help engineers learn company-specific tools

AI Engineer Code Summit names its first speakers for November

Google.org awards $36 million to 17 AI-for-science projects

A practitioner demonstrates Tern's integrated agent workspace

A code-review flowchart puts agent checks before human escalation

Geoffrey Huntley proposes resetting agent work to resolve merge conflicts

OpenAI Devs showcases community-built Codex projects

Graphicle gives coding agents local code graphs and cited project memory

Uncle Bob recommends instrumenting bugs with an agent iteratively

Martin Odersky discusses capability-oriented programming in Scala

GitHub Copilot maps saved prompts and sessions to Logitech MX Keypad

An Xcode cleanup prompt recovers about 420 GB from runtimes and caches

A developer alleges Apple is restricting app feature switches

Perplexity Computer builds a playable browser driving game

Moshe Kanat frames disposable and durable software as a spectrum

Sphinx quizzes developers on agent-written diffs before Git pushes

AI Toolkit adds LoRA training for Qwen 3.8 27B

Dax reports a self-hosted DeepSeek setup with improved price-performance

Odyssey reportedly connects a simulated fruit-fly brain to an AI world

Users report three OpenAI Aurora image-model references in API tests

A diffusion-language-model study adds clustered semantic representations

Data World reports gains from generated data-analysis environments

A technical thread traces visual compression as a multimodal context limit

vLLM adds serving recipes for D3 decision models

Continuous batching keeps LLM serving slots filled between tokens

A 32M speech model matches a larger ASR baseline on voice commands

A developer runs a quantized Qwen model on the Rabbit R1

Kuncheng Guid links coding-agent code quality to post-training rewards

wllama runs llama.cpp models in the browser with WebGPU

Geoffrey Huntley shifts inference regions as capacity changes

A practitioner reports faster Claude Code startup and cloud sessions

Sarah Hooker says model gains increasingly come from post-training

Researchers debate how reasoning disclosure affects model distillation

Liquid AI says fine-tuned d1-omni-600M excels on bounded decisions

Transformers adds CPU offloading for activation checkpoints

veRL evolves rollout into an agent runtime for asynchronous training

A developer runs quantized Qwen3.5-0.8B on Rabbit R1 with wllama

OpenBMB clarifies MiniCPM-V 4.7's runtime-memory claim

TestingCatalog compares OpenAI Aurora image outputs with other models

Argon user reports reconstructing black-hole images from telescope data

Dieleman describes diffusion loops that correct errors at fixed noise levels

Dieleman reports conditional flow improvements from unconditioned matching

Ethan Mollick says developers may be a small share of AI token use

AWS documents disaggregated LLM inference across EKS GPU nodes

Gabri Berton traces how early multimodal LLMs processed images

Earshot gives coding agents CPU-only audio analysis tools

Playwright measurements help an agent size skeleton UIs

A developer runs Gemini Argon inside Claude Code for a visual demo

A shared repository uses Codex to supervise Claude Code on long tasks

Practitioners report coordination bottlenecks in multi-agent coding

fal launches Kotoba APIs for speech translation and transcription

Huntley reports OmniOS running in Firecracker on Linux

Newsjack packages PR workflows as open-source agent skills

Shopping sites and banks are limiting autonomous agent access

Muse shows how an agent selects products across retailer sites

The Turing Post maps current tradeoffs in agent harness design

Ethan Mollick argues for secure agent access instead of blanket bans

A developer explores using a Mac mini as an agent sandbox host

Keycard explains why agents should not approve their own actions

Cohere tests cheaper planning agents for coding-team tasks

NVIDIA outlines compute access for UK agent-safety research

Arca agents prepare tax outreach before clients request help

Brett Leavitt argues agent swarms can parallelize research work

Daytona and Oracle discuss where agent-written code should run

Gemini Argon workflow sets review gates for architectural reconstruction

A developer evaluates Microsandbox for self-hosted coding agents

Geoffrey Huntley discusses verification and agency in agentic engineering

Overalls adds an internationalized interface across multiple languages

DeepSeek brings its agent harness, web, app, and platform teams together

Google Research reportedly releases experimental Harness²

Reports say major websites are blocking autonomous agents

Tim Dettmers lays out research workflows for the agent era

Cohere studies how coding-agent teams benefit from inference scaling

Antithesis testing finds a leap-second bug that could skip backups

Claude Code 2.1.303 ships CLI fixes to reduce crashes

Anthropic model traces NIST curve seeds to a timestamped generator

Preflight inspects and redacts secrets before requests reach a model

A paper examines recovery of reasoning traces from weaker models

Overalls proposes private-network blue-team exercises for agent code

Scott Aaronson discusses the research impact of OpenAI's math proofs

MLpowered explains how language models learn to predict text

Quiver AI finds style-vector similarities across open and closed models

A developer credits YubiKeys after recovering a hacked account

VoxelBench 2 previews scenes ahead of its beta test

Geoffrey Huntley seeks Daybreak Red access to fuzz Overalls

Prinzbench finds GPT-6.1 Sol Pro answers 91 of 99 legal research points

Telegram Desktop versions before 7.2.9 face a session-file exposure flaw

Vercel AI Gateway adds session-level agent logs

A tester reports DeepSeek Flash 1017 cheating in a bug-hunting evaluation

Dettmers reports small tool-equipped models outperforming a larger diagnosis baseline

Geoffrey Huntley shares a week of high-volume agent token use

Matt Pocock distinguishes codebase observability from persistent evals

Hermes plugin maintainer uses a three-day delay to reduce supply-chain risk

Grok Bot engineer explains when idle context compaction can backfire

Anthropic commits equity to a new public benefit fund

A Fortune 100 case study reports $21 million in legal-fee savings

Claude turns a WWI history question into a playable trench model

Techhalla uses character references to keep generated scenes consistent

Dot adds iOS widgets and Action button support

Gergely Orosz argues AI token-use targets can accelerate engineering adoption

A developer explores open-source games with agent-created characters

Uber says Minion writes roughly 15% of production pull requests

Factory's agent-readiness checklist starts with engineering hygiene

Reported Anthropic data shows junior technical hiring share falling

Anthropic says its public-benefit equity commitment can grow with valuation

A Codex user reports rapid usage depletion during Astra sessions

Addy Osmani outlines four verification layers for agent-written code

Piotr Skalski demonstrates single-prompt sports analysis with Gemini 4 Argon

NVIDIA midtraining raises Nemotron's SWE-bench Multilingual score to 62.8

Researchers train an 8B reasoning model to diversify research ideas

Wafer previews GPU guide updates for Stream-K, Blackwell and Triton

Llama.app automates local model setup and speculative decoding

Cerebras founder recounts spending $8 million monthly before its chip worked

A solo-agent workflow overlaps local builds with background agent tasks

Next Concept Modeling reports 21× faster inference than diffusion models

A model-size projection estimates 100-trillion parameters by 2030

llama.cpp documentation adds a speculative-decoding guide

ModelTrace identifies model families from output fingerprints

Fable 5.5 builds a detailed 3D forest in a VoxelBench demo

Stanford and Together propose coarse-to-fine Next-Concept Modeling

Dynamic tool additions can trigger KV-cache misses in agent sessions

Just Out proposes user progress as an agent training signal

TypeSafe releases 27B and 4B decider models with a new attention schema

Athas IDE lets developers switch AI providers for agent workflows

Gemini 4 Argon and Blender generate a procedural aquarium wallpaper

Princeton and Penn’s Recurrent Looped Transformer generalizes beyond training length

Geoffrey Huntley releases GeoClass for regional inference routing across Tailscale VMs

A 0.6B distilled student reaches 44% accuracy on the MATH eval

Hermes Index adds GPT 6.1 Sol and other models to its catalog

JevAgentHarness reportedly cuts agent costs 14.2% with calibrated routing

Nando de Freitas warns outcome rewards can reinforce faulty reasoning

Mikhail Parakhin calls for post-training models to explain their answers better

Pi Durable plans serverless hibernation support for next week

Codezoom explores C# codebases through browser-based UML maps

Geoffrey Huntley demonstrates an agent handling an Uber Eats support case

A diffusion action head keeps memory tokens separate from denoised actions

Overalls runs FreeBSD guests inside Firecracker on Linux

Agentic Discipline 7 shows one disciplined agent handling larger tasks

Android Skills gives coding agents Android development playbooks

Claude Code Desktop opens side chats in separate tabs with /btw

Stripe adds real-time Postgres sync without custom webhooks

Delta lets an agent change provider settings through a scoped tool

ASPIRE open-sources V1.0 for robot skill discovery and self-improvement

Scott Stevenson warns against colocating frontier agents and crypto wallets

Codex reportedly reuses subagent context and retains caches longer

A paper maps government responses to surges in agent-driven requests

Keycard panel advocates runtime authorization based on agent intent

Geoffrey Huntley starts two weeks of autonomous repair against Antithesis tests

Lucas Cordeiro presents a verifier loop for LLM-generated code

AA-Omniscience reports lower hallucination rates for Gemini 4 Argon

Hegel adds shared property testing across Erlang, Elixir, and Gleam

Gemini 4 Argon leads LegalReasonBench with a 50.8% score

Neel Nanda questions how neuron attribution graphs handle weak activations

PhotonHQ rebuilds its iMessage engine and adds OpenTelemetry traces

A harness study compares agent results across sampling settings

Epoch AI finds closed models lead open weights on cybersecurity tests

Pi’s Qwen harness variations show no significant pass-rate gains

An IPython harness raises Qwen3.5-9B reward while cutting input tokens

DeepSeek V4.1 Flash draws creative-coding comparisons in animation and 3D

Tribuchet offloads Nix builds to resilient remote workers

Hugging Face Hub collects ready-to-run reinforcement-learning environments

Uber Code Inbox combines AI checks and PR risk signals

Haiku 5.5 posts a low API price and a strong Terminal-Bench result

Supermemory adds one-command coding-agent memory setup

Lark grammar support reduces turns in code-mode tool calls

Geoffrey Huntley proposes OCR loops for reviewing large legal evidence sets

Tencent's Hy-Memory-30B-A3B scores 55.49% across four memory harnesses

A walkthrough agent teaches a plugin system from source files and questions

The Turing Post separates agent memory into three design goals

billion-context compresses coding-agent histories for long-running sessions

Vishal Trivedy uses a phone-driven agent to triage research work

Claude Projects anchors a personal agent system across machines and assistants

Wells Fargo reports better fraud detection than its production XGBoost model

Oil UI helps agents compare and refine multiple interface directions

Badlogic builds and runs a personal work tool entirely on Android

Geoffrey Huntley publishes the second edition of his SRE book

Ostris AI Toolkit adds day-one support for NVIDIA RTX Spark

Spellbook’s founder describes testing over 100 landing pages before product-market fit