All Stories

Steve Yegge reports 1.5 million Beads downloads

Amp can recreate earlier app screens from Git history

Microsoft completes pretraining a 2.8-trillion-parameter MAI-Base-2 model

StepFun decouples training telemetry to avoid slowing GPU iterations

Epoch's index places Mistral Large 4 near models from April 2025

Google demonstrates magic-state cultivation on Willow hardware

A developer trains a MuJoCo Warp agent at 250,000 steps per second

Epoch's GPT-6 compute scenarios draw scrutiny over timing and sparsity

An ML team seeks B200 and B300 nodes for training

Reducto hits Cloudflare Workers’ 100 custom-domain limit

V. Trivedy outlines how to design evaluations for agent capability frontiers

The Turing Post recommends Laurent Younes’s machine-learning textbook

OpenRouter adds Moondream 3 Preview and 3.1 with 32K context

torch-dist-bench benchmarks PyTorch collectives with bandwidth and latency measurements

Dan Breunig argues personal agents could reshape attention economics

Stas Bekman proposes measuring GPU compute and communication overlap

Microsoft finds session history improves cost-aware agent routing

Mat Velloso uses an AI camera to track his cats' eating and drinking

Hyperbrowser launches macOS agent sandboxes with browser and Terminal access

The /be-ambitious skill packages a four-step workflow for agent tasks

OpenAI launches a gallery of reproducible Codex hardware projects

fal launches Worlds for real-time interaction with world models

Gergely Orosz argues agent-generated work is stressing CI and build systems

Agent architecture proposal models execution as states and events

Geoffrey Huntley adds Amp-style threads and Orbs to Kittens

Berkeley research reportedly improves agents with periodic restarts

eve publishes a Python agent starter for Vercel

Eyes gives coding agents searchable video transcripts and frames

GPT-Live adds a native Decisions API path for low-latency actions

AdaEvolve adapts LLM-driven search across local and global levels

OpenCode developer runs a desktop agent from a phone through Slack

HumanLayer's Fold provides a provider-agnostic core for coding agents

Mike Hostetler proposes agents that wake, work, and hibernate as data

Deepagents exposes LangGraph hooks for deterministic agent control

eve adds MCP event subscriptions through Vercel Connect

OpenCode user keeps parallel project sessions running with subagents

Geoffrey Huntley surveys sandbox APIs for composable agent runtimes

Venice adds private access to Tencent’s Hy4 Preview

Amp’s Quinn Slack shares how the team builds software with agents

verified-tiff reimplements libtiff's reader in formally verified Rust

TryCua says its Hyprland support awaits Omarchy's newer stable build

Open TTS Leaderboard compares speech models with objective metrics

FrankenGraphDB reports faster analytical queries on graph workloads

Sentry lets employees use AI subscriptions while restricting customer data

V3R1T4S reports agent-assisted discoveries validated by external benchmarks

Tencent attributes reported agent browsing to third-party model evaluations

Posts report Opus 5.5 fast mode opens to all Claude API users

Vercel launches Token Pass for GLM 5.3 and Kimi K3 access

Higgsfield demonstrates Kling 4 gameplay concepts in generated video

fal adds native 2K and 4K generation to Flux Video

Sentry’s Zeeg explains why AI code review affects SOC 2 controls

Black Forest Labs releases FLUX 3 Image Klein for high-resolution generation

Replicate adds Krea 3 for prompt-driven image editing

Kling 4.0 generates multi-cut action scenes from detailed prompts

Ramp introduces Glass, an AI workspace built around compounding knowledge

Anthropic commits $5 million to support mathematics research

Dabit scrapes 821 forward-deployed engineering jobs across 292 companies

Dots user reports reaching inbox zero with an AI email workflow

A Dots workflow archives bulk email and notifications automatically

Polylane attaches narrated video walkthroughs to agent-written PRs

scriptc releases version 0.3.2 of its compiler tool

Athas brings its IDE to the browser

Yacine argues coding agents should solve problems with less code

MagicPath adds ChatGPT sign-in to its collaborative coding canvas

OpenCode builds a TUI preview tool to check layouts across the app

Visual Studio Code adds interactive canvases for agent workflows

Claude Code 2.1.300 changes its system prompt around user questions

Omnigent brings GitLab and Azure DevOps reviews into agent sessions

Semble searches code for agents with fewer tokens than grep and file reads

PRISM uses quantized scans and error bounds for Postgres vector search

OpenClaw’s agent removes about 1.2 million lines of low-quality code

A fork of Uma adds Plausible analytics support to its macOS menu-bar app

AA-3D models reproduce all 72 Eiffel Tower inscriptions offline

Vercel says Meta crawler traffic exceeded GoogleBot baseline by 15×

Modal reports $1 billion annualized revenue and raises $750 million

Qwen 3.8 27B reportedly runs at 20 tokens per second on a PS5

Google shows Argon building a 3D renderer in pure Python

AutoEnvScaling uses terminal agents to generate RL environments

NVIDIA’s Nemotron 3.5 Lightning becomes free on Vercel AI Gateway

Baseten offers dedicated deployments for Runway video models

Harness design determines which skills an agent practices

Inworld launches an inference API with model fallback and service tiers

Tripo AI generates a 3D chair that imports into Unreal Engine

Gemini 4 Argon produces inconsistent builds and skips collision checks

Argon sketches animation frames and adds cel shading in an iterative workflow

Gemini 4 Argon wins all 50 matched short-story comparisons against Gemini 3.1 Pro

Stripe finds fine-tuning a 4B model improves merchant fraud review precision

NVIDIA, OpenAI, Abridge, and Experian discuss open models in production

Magnific creator shares 297 AI-generated game assets and the Unreal workflow

A Qwen3 reranker routes requests to cut LLM spend by 38%

Vals AI proposes long-horizon tests for model routers

A chief-of-staff bot uses separate CLI logins for task-specific models

Anthropic’s planned TPU capacity could reach 16 GW by 2028

A researcher reports SOTA Vietnamese speech recognition with EmbeddingGemma 2

Lech Mazur compares repeated phrases across nine language models

Antigravity uses Gemini 4 Argon to reproduce a 3D modeling workflow

Vela turns anonymized user behavior into training tasks for Qwen

Claude Code Router centralizes model routing for coding agents

Jev adds image input to its TypeScript playground

A five-engineer team reports API routing raised its AI bill 30-fold

VideoJev releases 4B and 35B open models for video understanding

xAI TypeScript SDK cookbook adds examples, reaching 25

TasteVal tracks rapid gains in models’ AI research judgment

Paper Instruments releases Ultramarine 1 Flash for document-heavy work

Google shares six Gemini 4 Argon apps built in AI Studio

Purshow explains how Muon changes matrix updates through spectral norms

Anthropic’s planned TPU capacity could reach 16 GW by 2028

CoreWeave’s rising interest bill puts its AI infrastructure financing under scrutiny

A local vision model detects falls on an NVIDIA DGX Spark

vLLM reports faster sparse prefill kernels for Step 5 Preview

Grok Bot setup routes tasks through Claude and Codex subscriptions

Matt Pocock proposes GRILL.md to configure /grill-me planning questions

PilotDeck releases 2.0 open agent harness for verified office work

Artificial Analysis launches AA-Robotics benchmark for physical robot arms

Ethan Mollick gives his Dot a separate email identity

Hark says Handoff served one million browser sessions in seven days

Meta research traces reward hacking across coding-agent teams

Nvidia TacitVLA matches chain-of-thought performance at up to 3.4× lower latency

Composio Instant gives agents one wallet for paid tools

ElevenLabs says its support agent resolves 22,000 tickets monthly

Vercel’s Dots can control local and cloud Codex threads

Manufact ranks 969 MCP servers with AgentMail at the top

CopilotKit launches CLiF to turn product trajectories into agent skills

Grok Bot uses Cursor agents to build and save a web project

Parallel becomes Browserbase’s default search provider for agents

Tensorlake joins AgentEnv as a built-in sandbox provider

Nimble-v4-max leads JevMan’s Pac-Man decision benchmark

Odessia pairs hotel booking agents with accredited travel-agent rates

Lawve integrates its legal agent skills with the open-source Mike platform

Noam Brown discusses scaling and coordination limits for agent swarms

Surf CLI lets agents control Chrome through local terminal commands

Mastra Connect gives agents ready-made tools for workplace apps

Dyna-2 uses large-scale video to adapt robots with brief demonstrations

Factory adds persistent remote machines for Droids

Moritz Kremb documents his Grok Bot agent workflows

Mario Zechner uses four agents to review code changes independently

A Muse workflow turns Instagram reels into saved places on Google Maps

Hermes Agent v0.22.0 simplifies onboarding and app connectors

Deepagents’ V. Trivedy argues for agent-modifiable harnesses

A Codex skill turns research papers into spoken technical briefings

Orca coordinates coding agents across separate CLI panes

Epoch launches SpireClimb benchmark for agents playing Slay the Spire

Vals finds no frontier model scores 2/100 on simulated humanoid tasks

Researchers trace a rogue agent fleet to Tencent Cloud

HeyGen Voice joins OpenRouter with standard and low-latency modes

AA-Robotics finds GPT-6.1 Sol scores near Astra at far lower task cost

Uncle Bob’s Scriptwriter app lets an agent edit screenplay files

Report: GPT-6 Astra answers prompt TheoPhysEval authors to correct reference solutions

Report: Anthropic reportedly licenses Opaque confidential-computing technology

Researchers warn AI-driven math progress could pressure public-key encryption

A Carnegie Mellon study finds OpenClaw logs cannot prove policy violations

Researchers frame LLM evaluation as a forecasting problem

Sentient Foundation benchmarks methods for fingerprinting copied models

AIPOCH Open-Science packages research sessions with data and provenance

A researcher benchmark finds Gemini 4 Argon often misstates current affiliations

Chronos-2 reduces next-year model benchmark prediction error by 37%

Vapi builds a PR reviewer that runs tests against its own findings

Who Sells Data catalogs 159 AI data and RL vendors

An agent speeds up libtiff workloads by up to 7.33×

A free search tool embeds more than 203 million science papers

A developer uses Argon to audit code against project plans

An open-source tool red-teams image models with generated attack prompts

Ben Hylak says model evaluations need tests for eval awareness

Prosecutors charge an OpenAI engineer in an alleged recording-device incident

An open-source QA agent tests live apps and sends coding agents repro steps

Genspark traces a service disruption to a third-party vendor

LLMpsycho recommends passing integration tests as an agent stop condition

ARC Prize excludes Haiku 5.5 max-reasoning results after 74 of 120 tasks

Researchers frame agent privacy and security through contextual integrity

Hermes Agent v0.22.0 adds a tested stable release channel

METR proposes three public assessments of frontier labs’ agent risks

White Circle releases RISE to search for image-model safety failures

The Daily Oracle reports new math, graph, and codebreaking results

Cline reports Gemini Argon uses 30% fewer tokens than Claude models

Haiku 5.5 High ranks 27th in Agent Arena with $0.09 median cost

Embedding Gemma 2 reaches Hugging Face’s trending models

AssemblyAI releases Universal-3.6 Pro with expanded language coverage

Supermemory Local 0.0.9 adds Docker support and faster performance

DataTalks.Club prioritizes RAG failures by their real-world consequences

OpenRouter exposes Clef Omni for multimodal structured decisions

Jev adds image inputs to its decision-model API

A DataTalksClub workflow turns FAQ failures into regression evals

Timescale open-sources pg_vectorsearch with a PRISM index

ComfyUI points builders to more than 620 tested workflows

Zenzap adds workplace agents that connect to more than 400 apps

Sentry explains why rewriting a mature service in Rust is not a shortcut

Orange Business evaluates enterprise agents across retrieval, behavior, and traces

Telemetry builds agent-friendly documentation with Blume

Amplifier Health exposes 75 voice-derived indicators through one API

Mirelo SFX 2.0 brings text and video sound generation to fal

Prosecutors allege an OpenAI engineer planted hidden recorders

Daniel Shipper’s tutorial shows how to ask more of AI models

ComfyUI adds local RTX video-processing nodes for VFX

Koltregaskes collects 50 practical habits for working with AI agents

Sentry says its Junior agent is now its top code contributor

Every previews an agent-native history of OpenAI Codex

ComfyUI adds a Fish Audio Drama 3 node for multi-character scenes

Grok bot marketplace opens connector submissions

fal Reframe expands video beyond its original aspect ratio

Google reports Argon optimizations raise Gemma 4 E2B throughput 2.9× on vLLM

Drama 3 Preview scores 93.2% on Artificial Analysis pronunciation benchmark

ThunderSync computes GRPO and OPD gradients as rollout results arrive

DeepMind's Evo2 trains from harness edits and scores 48.3% on SWE-bench Verified

SemiAnalysis reports Rubin delivers 4.23× better performance per dollar than GB300

SemiAnalysis examines hardware and precision mismatch in RL rollouts

SemiAnalysis reports yield risks from denser 3.5D chip packaging

Deep Learning Alchemy launches model-behavior course with code-diff quizzes

Report: Fable 5.5 reportedly appeared in Azure model API listing

Moondream joins Prime Intellect to develop efficient multimodal models

Qwen credits TokenSpeed with 685 output tokens per second on Qwen3.8-Flash-Next

Google DeepMind fine-tunes Gemma for on-device scam detection with GovTech Singapore

ChatGPT dots adds creation on iOS and Android

Google demonstrates Argon simulation for Apollo cornhole robot

Theo releases ts-rust v0.6.0 with a reported 30% speedup

Alexandr Wang reports Muse Wonder placed fourth on Bug Hunt Bench

Arena ranks Muse Wonder Max second in Text Arena at 1,513 points

Kill My SaaS reports 72 submissions in weekend cloning contest

QuixiAI reports Muse Wonder Full produced 15 solid pull requests in one day

Google says Argon helped remove a category of Chromium crashes

Theo reports Gemini 4 Argon exceeded 50% false claims on codebase benchmark

Theo turns Astra usability examples into planned benchmark

models.dev develops v2 API shape for model information

Modal adds traffic mirroring for inference endpoint candidates

Report: Google is preparing Nano Banana 3 Pro for November–December

Reviewer tests Surface Laptop Ultra with RTX Spark for CUDA workloads

Matthew Berman reports Muse Spark weights are coming soon

Report: LoGRA uses 7.2 GiB versus LoRA's 13.2 GiB for 1.5B model

Sakana AI and Berkeley propose Multi-Agent Self-Supervision

SubQ Snap targets decisions with 384K multimodal context

SemiAnalysis reports upstream vLLM added megakernel decoding on ROCm

vLLM adds ReplaySSM support for Mamba2 decoding

Code Mode exposes MCP tools as APIs for agent-written programs

Practitioner runs remote agent sessions with Freestyle and HumanLayer

Arena reports top agents complete 94% of delegated tasks

Artificial Analysis launches FrontierCode 1.1 leaderboard for coding agents

Madiator alleges Perplexity uses Nimble code without attribution

T3 Code adds a visual callout for its goal workflow

Theo recommends Linux to avoid environment friction with coding agents

Kuncheng Guid measures maintainability by the cost of future changes

Zeeg argues agents will not erase the complexity of professional software

Geoffrey Huntley argues modern tooling makes unikernels practical again

Restream supports custom scenes and multiple hosts for livestream production

Wi-Fi 7 chipset support can require a newer Linux kernel

Dzhng uses custom validators to guide long-running coding agents

Matt Pocock revisits the maintenance cost of tactical tornadoes

Theo explains why he built the ts-rust compiler

Theo moves ts-rust builds and tests to Blacksmith runners

OpenCode prototype renders interactive interfaces inside the terminal

Theo rejects paid-product integrations in T3 Code

John Rush says Claude Code built a table-simulation wizard in five minutes

Giffmana attributes an Engram training pattern to ordinary overfitting

Stas Bekman adds GPU results to the MAMF and MSMF table

A 15-machine CPU fleet estimates 19× capacity for parallel jobs

Cu-diamond composites target heat and warpage in advanced packaging

AstroLoc launches LoMA aerial-image localization on a public demo

Amazon reportedly weighs buying Decart for its AI workload optimizer

A security warning says tuned model weights could conceal data exfiltration

Frontier labs reportedly scramble to secure compute for user demand

The Turing Post maps three ways world models represent reality

AWS schedules hands-on workshops for model customization and evaluation

A PAM4 guide explains the short reach of 448G copper links

AstroLoc reports its image localizer was used on lunar photos

Astra reportedly leads Fable on math while Fable follows instructions better

A Neural PDE Solver study tests whether models learn correct dynamics

DeepSeek memory compression makes recall depend on token position

QuixiAI launches the Dolphin API

Hermes adds request compression and plans ultrafast API support

Theo reports GPT-6.1 Sol default is barely slower than Fast mode

Technical explainer examines PAM6 for longer passive copper links

A report says Yandex may shift workloads to a major new compute deal

Hugging Face releases open RL environments from OpenAI math problems

Drone strikes raise questions about Yandex Cloud data-center capacity

Frontier agents could automate ground-truth creation for specialized models

Epoch AI tracks a sharp rise in math papers acknowledging AI use

A quick test finds Midjourney thinking mode trails GPT Image on prompt accuracy

Moondream 3.1 posts a 0.56-second response beside slower models

Practitioner claims Fable's time awareness does not improve inside Codex

Cartesia reports multilingual voice agents handle most Dhan conversations

Grok Bot adds card-photo checkout with an approval step

Codex Chrome use can sort and favorite photos in Google Photos

Mat Velloso uses browser agents to reconcile bookkeeping receipts

Benjamin Anderson builds a secrets proxy for cloud coding agents

Hrishioa maps three interface patterns for AI agents

A developer connects a Messenger MCP to an agent running at home

Hermes Agent adds Anatomy as an optional design skill

Hamel Husain uses Excalidraw's MCP integration for slide visuals

Report: Xpeng Iron deliveries could begin in the first quarter of next year

Nisten builds a Toronto simulation with 100,000 agents and an economy

Harrison Chase maps managed deepagents to LangChain runtime services

GitSwarm coordinates long-running agents through a shared Git repository

D-Shift adds a persistent sidebar that answers questions about on-screen content

An agent uses a virtual card to register domains and set up services

GPT-6 Pro reportedly flags errors faster than academia can process them

ALE-Gold audit removes nine flawed tasks from a frontier benchmark

A lookalike-domain phishing email bypasses Gmail's filters

Command Center 1.3.0 adds more than 40 system-monitoring improvements

ShipBash tests web apps and CLIs with recorded agent verdicts

Sentry trace IDs make production errors safer to hand to agents

Video Motion Analyser measures frame cadence and temporal anomalies

Claude Code maintainer says a dictation issue is fixed in nightly

Theo builds a dashboard to estimate remaining Claude usage

Sentry’s CLI lets developers ask coding agents to wire up instrumentation

Report: OpenAI withdrew three papers from its mathematics collection

Gergely Orosz warns AI SRE tools could weaken reliability feedback loops

François Fleuret recommends confidence intervals for model predictions

A developer plans to rebuild a personal agent workspace from a clean slate

Nick Dobos recommends learning unfamiliar codebases by exploring as you build

Northwestern mathematicians weigh how AI-generated papers affect research training

Meta Muse reportedly retains more than 30% of users through day seven

Hark reports 562,000 users and a range of agent workflows

Magnific and Seedance 2.5 turn reference images into video

Claude directs a video built largely from generated code

A ChatGPT plugin passes one million tool calls in ten days

A startup advertises up to $1.1 million for exceptional engineers

Pocket Holler ships an open-source Game Boy Color adventure

Karpathy describes a widening gap in how people experience LLMs

John Rush reports a 4× revenue increase after an Opus rewrite

Cohere upgrades North with agent memory, skills and cost controls

Report: Anthropic contracted roughly 350 MW of Rubin capacity for 2028 at $5.80 per GPU-hour

Reported Stanford study finds LoRA cuts poor agent plans from 28% to 5%

Sebastian Raschka publishes GRPO training stability walkthrough for MATH-500

HarnessSQL raises Qwen3-14B Spider 2.0-SQLite score from 22.2% to 54.8%

TestingCatalog reports hidden Voice Preview tab in Claude

Grok Bot workflow assigns priorities and tasks to a primary bot

Hermes Agent profiles can each connect to a Slack bot

Plinius reports agent solved two codebreaking challenges in under 12 hours

A chart recalculation puts Astra's estimated task horizon at 10 hours

Boris Tane proposes connecting production observability to coding agents

Astra beats Opus 24.5–5.5 in Peter Gostev's chess tournament

User documents Opus 5.5 in Claude Code refusing to copy local session logs

Ben Hylak describes replaying production traces to evaluate agent failures

Microsoft-Decision-1 reportedly ranks 19th on Decision Index 0.3.1

Users say Devin's ChatGPT integration requires a paid Devin plan starting at $20

Deedy estimates OpenRouter's annualized model spend at $1.5 billion

Nous releases MISSINGNO. coding model free for a limited time on Portal

MemoType reports Recall@1 gains up to 16.18% by routing memory retrieval

OpenDocRouter adds Mistral OCR with reported 1.8-second median page latency

Supermemory demonstrates memory graph that preserves fact history

TestingCatalog reports an unreleased Ultra mode in Google AI Studio Build

TestingCatalog reports hidden Gemini Argon references with three reasoning levels

HumanLayer prototypes shorter planning workflows for small coding tasks

Box says background agent swarms could multiply token demand

Nvidia discloses $530 billion in off-balance-sheet guarantees

GDN2 stability analysis examines its generalized update matrix

Mistral recruits researchers and engineers for its founding Korea team

Prime Intellect tests 18 models on an eight-day optimization speedrun

Qwen releases open weights for Qwen-Image-2.1-Turbo

Artificial Analysis compares four models across 30 photo edits

Meta’s MIMESIS trains agents with a 9B simulator and 13 user behavior patterns

Unsloth releases a Qwen3.5-4B training notebook for 8GB VRAM

Microsoft releases Decision-1 in public preview to score predefined choices

ElevenLabs adds synthetic-voice detection and joins an agent protocol group

Meta’s Muse uses a sentinel agent to monitor its primary agent

Claude Code Projects admits all Pro and Max users on its waitlist

Midjourney opens applications for a limited MCP integration test

Artificial Analysis introduces AA-Robotics v0.1 for zero-shot robot-arm control

Grok Bot releases four templates for X-based agent workflows

CopilotKit releases an open-source Intelligent UI template for web, mobile and Slack

Vercel adds domain purchases to its marketplace CLI for agents

Agent Flywheel adds a streamlined ACFS setup for cloud agent instances

Microsoft’s TeleTune learns agent skills from usage logs and held-out accuracy

Pine AI launches a cloud computer for business-app agents

Sabi raises $50 million to build an EEG interface for AI agents

Grok Bot gives agents email, scheduling, and lead-management workflows

Grok Bots can claim email addresses and subscribe to newsletters

HumanLayer demos an open-source serverless agent that turns issues into pull requests

OpenAI’s math results prompted discussion of model evaluation and research throughput

Yi-Chia Chen reports a new 59.17% ARC-AGI-3 high score

Polyshares packages private company workflows as AI training data

OpenAI says evaluation awareness threatens deployment safety measurements

Theo says he probably will not sustain maintenance of his Rust TypeScript rewrite

PartyKit founder announces free partykit.dev hosting shutdown

Claude Code user reports refusals to copy local session logs despite permissions

Bubble Tea 2.1 adds terminal status reporting for agent workflows

Venice documents a zero-retention web research workflow with Brave search

NVIDIA proposes ranking coding base models by their first passing edit

Meta paper finds agent memory should filter value claims more strictly

A compact coding-agent prompt specifies goal, finish condition, evidence, and constraints

Meta study measures agent learning gains per dollar across NetHack and other tasks

Codex adds next-message predictions for Pro users

Users report Opus Fast matches Sol Ultrafast at about 280 tokens per second

OpenCode developer says a single iOS prompt rewrote its server and TUI

OmniParseBench launches 16,000 OCR tests across 90 languages

Claude Opus leads a new OCR benchmark covering 48 models

Project Greenhouse builds an open agentic-search reranker from scratch

Turbopuffer cuts a 10-million-document query from 1,696 ms to 84 ms

Claude Code 2.1.296 fixes denied-tool handling in managed hooks

Files SDK v3 releases a unified TypeScript API with 48 storage adapters

Suno adds clip stretching, fade curves, and improved downbeat detection

Sakana AI tests LLM peer review on planted paper contradictions

A full-stack LLM engineering roadmap collects free learning resources

Capy integrates Paper into its cloud coding agent VMs

Orosz reports graduates lack experience with AI coding tools