All Stories

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

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

Midjourney opens applications for a limited MCP integration test

Capy integrates Paper into its cloud coding agent VMs

Orosz reports graduates lack experience with AI coding tools

Kev ships a Modal skill for fine-tuning decision models

ReJev reports 80.50% accuracy on its decision-making holdout

LongCat experiment edits n-gram blocks to add subject-relation-object facts

Open Env Arena ranks agents building RL environments

llama.cpp adds Jev-like multimodal decision model support

Sakana's Continuous Memory Machine splits short- and long-term storage

Meta's RoboJEPA scales predictors from 22M to 8B parameters

Paper reports HERMES raises repository migration success from 6.5% to 31%

Atomic Agent Desktop runs up to eight local agents with cloud planning

Lance Martin publishes a Claude Managed Agents automation quickstart

Odyssey opens Odyssey-3 Flash interactive world model to public testing

Pi Durable becomes accessible from Swift through JavaScriptCore

Supermemory open-sources code implementing Cognition's dreaming memory architecture

Thariq publishes a Claude Managed Agents Chrome homepage extension

Hermes adds TinyFish browser backend to its plugin catalog

Peter Gostev reports Astra won five straight games against Opus

Next.js schedules an October 14 emergency update for three upstream vulnerabilities

Polylane launches agents that monitor and fix Vercel deployment issues

Report: Marker v2 reportedly parses about 24 pages per second on a B200

AREX verifies research answers requirement by requirement

A study finds 124 unique tool jobs across 11 coding-agent harnesses

Codex adds a /visualize command to its app

Blume 2.2 adds agent-assisted migrations for documentation sites

OpenCode uses agents to triage issues and open pull requests

Sam Newman argues LLMs lack causal models for reliable operations

llama.cpp ggml RPC backend supports inference across heterogeneous devices

NVIDIA VERA research paper describes 9,000+ restartable agent sandboxes

Sayak Paul explains KV caching for image-generation flow models

Google's AI Edge Foresight transcribes voice notes on macOS

d1 decision models add text, vision and audio variants

Microsoft previews local-or-cloud model routing for Windows Copilot

Nous Research raises $90 million to bring Hermes to enterprises

OpenAI says Codex and ChatGPT Work reached 40 million users

Liquid AI releases open-weight decision models for on-device use

Quail adds query-planned prefix sharing to its AI-SQL engine

vLLM-Omni unifies serving for speech, vision, diffusion, and robot actions

Vercel offers Glyph Cluster for coding and agentic knowledge work

Artificial Analysis adds base-model labels and filters for derived models

PyTorch documents pinned-buffer reuse for CUDA-to-CPU copies on NVLink-C2C

Cloudflare's Clef decision models become available through OpenRouter

Hybrid Latent Attention shrinks KV caches for looped language models

Vercel AI Gateway exposes OpenAI's structured Decisions API

Claude Haiku 5.5's published results show gains over Haiku 4.5

An Xid 31 guide traces production GPU crashes to MMU faults

Prism ML fits Qwen 27B into 6GB while retaining 95% of performance

Datology releases Zephon for deterministic, elastic training data pipelines

vLLM reports 5.3× higher throughput for DeepSeek V4.1 Flash at concurrency

AI networking engineers flag fiber handling as a production bottleneck

ReqLLM 1.27 adds support for the OpenAI Decisions API

tldraw lets canvas comments prompt ChatGPT and Codex agents

LearnOpenCV explains how NMS-free detectors remove a box-cleanup step

Microsoft brings local model routing and file context to Copilot on Windows

NVIDIA's CUDA guide maps kernel and memory controls to AI performance

An 8-million-parameter TTS model runs from just 9 MB of weights

Microsoft plans local MAI-Code-1.1-Flash for routine Copilot coding tasks

Mistral claims Large 4 ranks first among open models on Harvey’s LAB

Microsoft reportedly demos 284B-parameter DeepSeek V4 Flash on a laptop

Posts say Grok Bot will route tasks to outside models, including Claude Opus 5.5

OpenRouter adds Perplexity Decider v1.1 at $0.02 per million input tokens

Google Research presents EnvHarness for adaptable agent training environments

Epoch AI's InnovationEval finds agents struggle to invent post-training methods

Trillium Labs says compute access is blocking open distillation research

A Grok Bot workflow exposes a private agent API tool across an organization

Pi creator publishes subagent extension for adversarial reviews

A Codex workflow routes daily Todoist tasks by explicit owner

Rivet adds Pi Durable agents to Actors with crash-resumable execution

Kernel's Config Registry makes more sites reachable to browser agents

CopilotKit's Manufact cookbook embeds interactive MCP app interfaces in chat

OSWorld introduces an iOS benchmark for agents with persistent user identity

LangChain Managed Deep Agents v0.9 adds schedules and per-run configuration

An eval-review workflow uses diverse agents and privileged trajectory inspection

A first-principles study tests when agent swarms help solve hidden-rule problems

EffectTS's Blacklight harness stores agent state in an append-only log

Salesforce's CLIFT trains web agents to verify rollouts without live judges

DAEDALUS studies agent memory with ablations across its pipeline

Tembo adds the Vercel MCP for deployment and build-log access

Mastra brings Agent Controller, signals, schedules, and goals to GA

OpenHands adds scoped agent profiles and isolated Docker runtimes

Cline launches cloud agents that test code and open GitHub pull requests

LiteLLM team shares Moyai, a self-hosted agent for background coding

ComputeSDK Actions adds support for multiple sandbox providers

Jonas shares an open-source, self-hosted family agent built on Cloudflare

A browser-use test finds Haiku 5.5 close to Opus 5 on defect checks

Hermes background reviews can now improve user-owned skills

ai-rulez generates native assistant configs from one source of truth

Kittens offers self-hosted development machines backed by Firecracker

A team agent routes X requests to the developer who last touched the code

Devin Mobile lets developers manage cloud agents across operating systems

Grok Bot 0.68.1 adds PowerPoint and Google Slides deck creation

An Apple paper reportedly finds a single coding agent beats complex ML harnesses

Deepagents can load tools alongside skills without breaking prompt caching

A coding-agent orchestrator delegates large parallel test matrices to subagents

A LangChain engineer uses an ACP adapter to run Deep Agents in Zed

Geoffrey Huntley says Claude Code’s classifier disrupts his development loops

Trq212 recommends asking agents to teach unfamiliar domains first

Zephon open-sources a deterministic dataloader for large-scale ablations

Google Research introduces ContinuousBench for testing private synthetic data

OpenAI rebuilds its plugin submission flow with clearer review feedback

Menso runs AI personas through live websites for usability testing

A production-trace workflow asks agents to find high-impact waterfalls

Devin adds Haiku 5.5 and reports a 58.4% FrontierCode score

OpenAI's 722 math manuscripts shift attention from peak results to research throughput

Ryan Lowe argues safety processes can help teams move faster over time

A Claude Code postmortem traces a C-drive deletion to Windows quoting

Gergely Orosz says nondeterministic agents need deterministic data controls

ClaudeCost estimates $4,853 in API-equivalent cost across 8.6 billion tokens

OpenTunnel launches public URLs for local services with claimed end-to-end encryption

Google opens SynthID Detector globally in English

Mathematicians describe novel techniques in OpenAI's released proofs

A Lean autoformalization paper warns that checked proofs may mistranslate the original

NVIDIA researchers find tool use weakens multimodal models' refusal behavior

Vercel Flags adds timestamp-based targeting for scheduled releases

T3 Code displays an agent's evolving feature graph in its work thread

Doug Colkitt tightens an OpenAI integer-multiplication result

AI agents now account for about half of visits to the FRED data portal

OpenAI paper resolves a 3D elasticity inverse-problem uniqueness question

Anthropic releases Claude Haiku 5.5 at $0.10/$0.50 per million tokens for short prompts

Anthropic releases Haiku 5.5 for faster, lower-cost agent tasks

A coding-agent study finds harness choice changes cost more than accuracy

A developer's Skatebench comparison finds a 55× lower task cost in one year

A developer reports 842 billion tokens of API-equivalent use in September

Anthropic cuts Claude Sonnet 5.5 cache-read price to $0.10 per million tokens

Theo says T3 Code cuts GitHub rate-limit usage by over 75%

Ramp's October vendor data shows cheaper models and media generation pulling AI spend

Chandra OCR creator alleges a project copied Chandra OCR 2

An MIT paper reportedly improves agent memory by exposing history as Python variables

DAIR.AI releases MCP tools for its curated research paper index

Cohere opens private beta for its Compass Cloud retrieval platform

Vik Paruchuri rebuilds chart extraction with fewer errors and faster processing

Turbopuffer makes sharding generally available for namespaces up to 256TB

Unsiloed computes document values that are not printed on the page

Matt Pocock argues coding agents need to care about the codebase

PersonalAgentBench compares assistants on everyday tasks and authority limits

A source-preference study finds LLM agents favor familiar websites

Biohub and partners commit $1.8 billion to data for virtual-cell models

ComfyUI uses Blender blockouts to control AI-video choreography

FrankenManim replaces Manim with a compact Rust animation toolkit

A public index gathers ML training logbooks and postmortems by year

A startup founder says one engineer shipped four polished apps in six months

Huntley publishes Nix overlay walkthrough with a runnable demo

Overmind open-sources training from production agent traces

Intel Panther Lake uses PowerVia backside power delivery

Vercel adds beta fallback models for low-confidence decisions

GPU MODE launches a repository of AI performance lectures

A Devin autoresearch prompt runs autonomous hill-climbing experiments

Model routing should expose the right tools, not guess intelligence

ICML study finds AI and human paper rankings diverge sharply

Gemini Live adds Guided Vision for blind and low-vision users

Mistral Large 4 reaches the top open-weight tier in benchmark testing

Mistral Large 4 preview posts mixed coding and cyber benchmark results

Mistral trains Large 4 in European data centers on 3,800 GPUs

DeepSeek V4.1 Flash scores 72.9% on ARC-AGI-2

vLLM 0.31 adds a daemon to preload model weights

AMI’s H-JEPA raises Visual AntMaze success from 18% to 73%

Mistral Large 4 reportedly used 4,000 GPUs versus Astra's 100,000

Two agents play StarCraft in real time with four tools and no video input

Cortex Harness lets robots hand control to humans when stuck

Google Research demos ScientistTwo for autonomous paper analysis

Harness-aware distillation raises ALFWorld tool-context use to 73.1%

Eleven v4 Turbo ranks first on a text-to-speech leaderboard

Meta MIRA splits long-horizon research between planners and executors

Grok 4.7 posts mixed ARC-AGI-2 and ARC-AGI-3 results

Sesame adds voice control for coding agents and connected apps

Grok Bot users report strong chat but missing computer-use access

Google Research previews Co-Director for coherent long-form video

AGENTS.md workflow removes no-ops and moves instructions to CODING_STANDARDS.md

Google AIM improves scientific-agent search by 1.6 and 4.9 points

OpenAI makes ChatGPT auto-review free for account users

Claude Code 2.1.292 adds effort controls for spawned agents

Parsewave finds 206 faulty graders in 600 AutomationBench tasks

Anthropic expands Cyber Verification Program to offensive testing

Google Drive and Docs add native Markdown files

Gamma 5 launches agentic presentation editing with PowerPoint import

Google Earth AI maps Ebola exposure in the Democratic Republic of Congo

Scrimshaw turns Claude into a playable text-based music generator

Claude edits Google Workspace files directly from open documents

Mistral Large 4 leads a legal-agent benchmark at 15%

fal adds image and video generation to ChatGPT and Codex

Google Earth AI uses geospatial embeddings for public-health forecasting

Codex and T3 Code generate visualizations inside threads

Delta v0.18 adds thread bookmarks with Cmd-D and Ctrl-D

Vals uses 90 Opus agents to find magnetic semiconductor candidates

FrankenTerm cuts headless terminal processing time by 3.2×

NVFP4 outperforms MXFP4 on B200 matrix benchmarks

GPT-6 Astra and Sol reportedly reach 50 tokens per second

AWQ cuts Qwen3-Omni first-audio latency from 213 ms to 23 ms

Together Link routes open models through coding harnesses

ValsAI agents screen magnetic materials with DFT simulations

Z.ai releases GLM-5.3 on Amazon Bedrock

Manus launches an agent-driven video editor

Browserbase introduces cryptographically verified identity for web agents

MCP Events proposal adds asynchronous agent-to-agent work

html-plan plugin turns Claude Code plans into HTML mockups

Cua Driver adds six open-source cursor motions from 82 prototypes

Deepgram Flux TTS preserves acoustic state across turns

Eve launches an iMessage agent stack with memory and multi-tenant accounts

TanStack Start adds JSON-spec app generation with server-side rendering

Report: Figure plans a Hark agent for web and mobile

rho-1 introduces a 19B model for reasoning and robot control

One model plays multiple image-only games in parallel

LiveKit integrates Microsoft AI streaming speech models

AWS guide deploys Pipecat voice agents with Deepgram on SageMaker

Coucou puts coding-agent permissions and sessions in the Mac notch

OpenAI rolls out text watermarking for ChatGPT and Codex in the EU

Zeeg reports coding agents can produce 50 to 60 simple PRs per day

Claude Code 2.1.291 fixes dropped-session responses and final-message loss

SelfSearch says a self-modified harness matched Codex at $4.03

Flow-1 targets lower-cost failure finding in agent traces

New York City proposal would require external validation for AI models

QuiverAI launches an API platform for keys, usage, billing, and logs

WeirdML v3 tests autonomous data and machine-learning work

Qwen3.5-9B paper rewriter opens a public GPU demo

T3 Code adds CSS-themed visualizations inside agent threads

ComfyUI publishes a keyframe animation workflow

Venice adds account-free access to FLUX 3 Image

Amazon reportedly shuts down consumer-agent access to Muse and Instinct

Dot detects a possible account compromise from email and login context

Science Made Readable rewrites open papers without dropping caveats

Uber has fewer microservices in 2026 than it did in 2020

Amp removes Mermaid rendering in favor of ASCII, images, and HTML

A developer uses Opus 5.5 to clean up and test a personal web app

0xblacklight says getting database schemas right early pays off

Robert Martin uses agents to review repositories and report code issues

Practitioner claims an $80 run trained a 4B model to beat GPT-5.6 Terra

Post reports a possible Gemini 4 Argon listing on Google Cloud

Claude Fable 5.5 builds a black-hole renderer in Python

EditHero benchmarks multi-step, part-level 3D editing

BRUT turns a static website into a procedural city-building demo

DMAD distills visual generators without an auxiliary diffusion model

Maxime Rivest argues smaller generalist models should rely on retrieval

Aleph Alpha cites Kolibri scores of 96.9% on AIME and 66.4% on SWE-Bench

Anthropic reportedly adds an opt-in setting for voice-data training

OctLLM represents 3D geometry with explicit octree tokens

Dot user describes daily website digest scheduled through Chrome

Microsoft's Agensh study reports team gains at 128 agents on ProgramBench

Maxime Rivest demos scientific article rewriting attributed to a 4B model

Hermes supports iMessage through BlueBubbles and Photon, Nous says

Ethan Mollick says organizational systems may bottleneck AI gains

GitHarness versions agent work so changed requirements avoid full rework

Jakemor outlines mobile interface patterns for embedded agents

A developer adds Bitwarden passwords and passkeys to a personal agent harness

Ralph Loop v2 discussion proposes an external observer for agent runs

GPT-6.1 Sol becomes one developer's default for coding and subagent work

Amp uses screen recordings to specify requests and verify fixes

Dingyi publishes an October 2026 tier list of AI orchestrators

Developer uses ChatGPT computer use to manage eBay hardware listings

DeepSeek Harness tests compatibility with Claude Code Mods

ffmpeg-skill gives coding agents a probe-plan-render-verify workflow

Users report Codex agents feel slower than three months ago

Claude diary entry reportedly leads Anthropic to contact police

FunBench ranks models by human-rated creativity and playfulness

Nick Dobos proposes values-based prompting for proactive agents

Anthropic recommends Claude Code's /usage breakdown for token spikes

Rocky Ding explains the harness checks behind reliable agent execution

Cockroach Labs' Peter Mattis urges stricter testing for coding agents

VeriHarness releases 26,000 agent rollouts to check shared errors

A developer says autonomous agents got his OpenAI account deactivated

Wired reports Meta Muse builds detailed profiles of users’ contacts

Supermemory presents smfs as a filesystem-style memory interface

Open-source Slack client streams live unread state to Cloudflare Durable Objects

Instinct screens products for birds after misreading a user's joke

Avi Chawla compares five common vector-search index designs

Reducto separates table retrieval from reasoning over table data

LlamaIndex says Extract v2.5 cuts scanned-form errors by more than half

Vercel's Guillermo Rauch separates human and agent documentation

Omar Khattab explores artifact-based human-agent collaboration

A developer animates code-drawn illustrations with Fable 5.5

Rippling's agent queries blur the boundary between tools and data

Decode publishes a free course for building a coding agent from scratch

Dabit urges developers to expand skills and experiment with cloud agents

CodeMarkets offers a CLI to launch revenue for open-source projects