All Stories

Interfaces publishes Accessibility as Craft guide for web UI details

Uncle Bob tests mechanical and agentic review as a code-review substitute

Claude Code 2.1.227 fixes GitHub runner Bash failures and rewind state

Motif Technologies releases Motif 3 final checkpoint and technical report

Cursor briefly exposes Grok 4.6 before pulling it back

DeepSeek DSpark explains 60 to 85 percent V4 inference speedups

Linear explains the prompt, tools, skills, and harness behind Linear Agent

CopilotKit ships an AG-UI adapter for driving Hermes inside any app

Firstmate agent distro crosses 3,000 GitHub stars for multi-session coding

The Bitter Lesson of Tool Calling finds Python stubs beat JSON in 11 of 14 models

Vercel makes Sandbox Egress Firewall free and argues network isolation matters

LangChain shows Stagehand v4 with Managed Deep Agents for web browsing

Trigger.dev chat agent survives refreshes, crashes, and redeploys

Plan-and-Act paper uses replanning to beat ReAct on long-horizon web tasks

You.com demonstrates x402 payments for autonomous Finance Research API calls

Sakana AI expands RSI Lab for physical AI world models in Tokyo

TestingCatalog spots Claude mobile remote-control device pairing

Hermes Browser Use mode cuts browser-agent token use by 48 to 66 percent

Vercel Functions now deploy Bun.serve entrypoints with WebSocket handlers

dabit shows Figma MCP cloning design systems for agent-built UIs

Google python-genai PR rejects a gemini-3.7-flash enum addition

Neel Nanda says layerwise relevance propagation improves J-Lens early-layer errors

Vercel deepsec adds one-command onboarding for AI security reviews

Mistral coding-LLM patent filing draws prior-art criticism from Gergely Orosz

Lovable adds public Trust Centers with live security controls for apps

Sara Morrill's drone motor example maps the reshoring knowledge gap

Higgsfield publishes prompts and assets for a 110 minute AI feature film

Microsoft MAI-Image-2.6 debuts at number two on Text-to-Image Arena

Hermes Agent adds an optional ast-grep skill for structural code search

Bending Spoons engineering playbook resurfaces after Harvest pricing backlash

Sakana AI Scientist is highlighted in JST CRDS report on AI for science

SemiAnalysis claims Gemini 3.5 Pro was canceled as GCP gains priority

Harvard Explorative Modeling paper proposes exploration as a third scaling axis

Bloomberg says AI infrastructure spending is pushing TMT debt to 540B dollars

Doodlestein asks Fable to sketch an AI homunculus for LLM sensitivity

FrankenTTS runs voice cloning entirely in the browser with WebAssembly

Denny Zhou shares Stanford CS25 lecture notes on LLM reasoning

thdxr shows agents can handle messy voice prompts without polished dictation

ChatGPT Work installs OpenClaw and Ollama to run a local model through an agent

OpenTunnel carries PostgreSQL over direct TLS and SNI

Gergely Orosz warns that fake journalist DMs steal X accounts

Chetas Lua spots Kiana, a Qwen mystery model, on Code Arena

Anthropic says Claude tools landed large P99 memory-usage improvements

LlamaIndex invites teams with hairy document extraction workloads to tune LlamaParse

Hermes audit demo scores a WebGPU NCA trainer with concrete test runs

Claude Opus 5 system prompt includes post-cutoff Fable export-control context

Pika Labs uses Seedance 2.5 to turn audio and references into a music video

Codex treats /loop as an implicit loop command

mona-lisa-1 appears on Arena with OpenAI SynthID watermark evidence

Cognitive Commons paper warns AI can erode junior expertise pipelines

Demis Hassabis tells Stanford GSB that AGI may arrive around 2030

SuperCmd shows Raycast-style launcher widgets for system status

Claude writing tip persists ASD-STE100 and Zinsser rules in memory

OpenAI publishes ChatGPT Work finance-team workflows with plugins

TechHalla shares Grok Imagine prompts for coherent 16mm-style video scenes

Cursor cloud agents demo uses vertical chat splits for parallel coding

lopopolo prompts agents to prune low-value tests and simplify code

Cursor Origin previews a Git forge for agentic code production

Native SDK adds drag-and-drop UI elements without a JavaScript runtime

FrankenSim proposes a Rust kernel for certified physics simulation

Charles Wolfe collects practical resources for continual pretraining

Sam Altman says inference demand can fund frontier training

Chris Hillee flags ambiguity in how teams compute MFU

quota-axi adds a TUI dashboard for model quota monitoring

Vercel AI Gateway exposes Grok Imagine Image 2.0 through CLI and playground

Liquid LFM 2.5 2.6B may lead private sub-10B model benchmarks

Gemma models approach 1B downloads across the open-model community

Theo runs 40 Claude agents on a Framework Linux desktop

pvncher uses Codex heartbeats and capture atlases for async game work

Matt Pocock moves agent sessions into remote boxes controlled from Discord

LangChain explains Managed Deep Agents with LangSmith infrastructure

Claude Code patched Bun runtime may fingerprint first-party client requests

Antithesis torture-chamber skill runs before agent commits

swyx opens Kill My SaaS coding-agent competition with a 10K dollar prize

KISS Sorcar agent claims 1.59x SQLite geomean speedup under 150 dollars

LlamaParse says frontier models got pricier without better document parsing

US reviews Chinese AI firms' remote access to overseas Nvidia chips

John Rush lists a 116-product SaaS stack costing 730K dollars per year

ChatGPT starts asking follow-up questions before running ambiguous tasks

OpenRouter adds Dreamina Seedance 2.5 for long-form audio-video generation

Athas improves File Explorer performance and search with fff

Theo says T3 Code increased merged work far more than generated code

Dotta says agent builders need human-readable eval matrices

Jiaxin Shi talk bridges autoregression and diffusion through masked diffusion

Local Studio runs local agents through vLLM with DGX Spark hardware

ComfyUI adds MiniMax H3 as an open-weight multimodal video workflow

Prof. Tom Yeh publishes worksheets for learning tokens and context windows by hand

François Chollet says agentic AI workflows are becoming increasingly CPU hungry

Warp Agent CLI adds /connect-grok for X Premium subscription access

François Chollet argues future AI may shift from LLM stacks to symbolic learning

Hark Handoff reduces computer-use agent turns from 15 seconds to 5 seconds

ElevenLabs reports ElevenReader Voice Chat raised listening time by 24%

Conductor Cloud adds local command, port forwarding and file sync escape hatches

Eve documents a Next.js-like framework for durable multi-channel agents

Sergey Levine paper investigates why action chunking helps imitation learning

NoimosAI releases Social Agent for cross-platform trend research and posting

Claude Code adds cross-session messaging for parallel agent work

prime-rl and verifiers add multi-agent training and evaluation support

Raindrop explains MCP tool hierarchy design for lower cost and faster answers

doodlestein_self_releaser reuses GitHub Actions workflows for local releases

v0 adds Usage and Activity dashboard for credits, members, projects and messages

SlopCodeBench discussion highlights 33% pass rates on evolving-codebase tasks

T3 Code merges 250 PRs with agent observability, search, mobile and reliability fixes

Matt Shumer recommends fresh context and outcome prompts for Claude Opus 5

Reach shares a global AGENTS.md template for safer coding-agent defaults

Boris Tane lists production agent failure modes around durability, subagents and tools

Suno adds Voices recording to its iOS and Android apps

Simon Willison notes ChatGPT mobile effort controls behind long-press send

Gergely Orosz criticizes Gartner AI reports as pay-to-play vendor rankings

ARC Prize shows Gemini 3.6 Flash at 60.4% on ARC-AGI-2

Google DeepMind opens WeatherNext Cyclones for storm forecasting

Cloudflare OS makes Kimi K2.7 Code and GLM 5.2 the default model picks

Sergey Brin says Jeff Dean pushed TPUs when voice search hit CPU limits

OpenRouter brings open models into Netlify Agent Runners

Baseten becomes a Hugging Face inference provider

Unsloth says DeepSeek-V4-Flash runs up to 2x faster with DSpark

Portals into Orbs expose running apps over HTTPS for live remote dev

T3 Code's inbox-style threads keep more agent work in view

Pion Opus ships a pure-Go Opus codec for audio pipelines

Agent Plugins standard lets Codex, ChatGPT and Cursor share bundles

pi-subagents adds code mode for fan-out orchestration and worktrees

BT6's Black Hat demo shows prompt injection can jailbreak a robot dog

Daphne Koller says biology AI is bottlenecked by data and causality

Suno lays out a responsible music policy for AI generation

Transluce finds Claude changes behavior when it recognizes the user

ARC Prize retests GPT-5.6 Luna at the same score for 80% less cost

Muse Spark 1.2 lands on the cost-performance frontier

OpenAI unifies GPT-5.6 Sol and Luna in ChatGPT

Matt Pocock's /wait-what skill rewrites jargon into plain code explanations

Epoch AI says one in five US workers now delegate a task to AI

Goodfire AI's motion model spots Parkinson's gait impairment

Discovery Loop spins out from Google Brain as an automated ML company

Herdr joins Y Combinator and keeps its agent runtime open

Hermes moves Polymarket into an optional skill install

ElevenLabs Dubbing v2 preserves voice and delivery across languages

Wispr Flow's growth engine ran on one person and a stack of agents

Remocn turns AI agents into browser-native product demo video builders

LangChain updates Deep Agents course with async subagents and TypeScript

Prof. Tom Yeh walks through sparse autoencoders by hand

OpenAI security memo shows HR punished a board warning

Poolside says Laguna S 2.1 crossed 10T tokens served

MIT and Stanford find LLM financial advice depends heavily on the prompt

Roboflow Playground benchmarks Qwen3.8-Max on medication-tray reasoning

DeepSeek V4 Flash shows up as Ollama's fastest-growing model

Gemma Translator turns a Raspberry Pi into an offline translation device

MiniMax H3 tops DesignArena on three video editing tasks

Prime Intellect's Prime Agent hits 95.5 percent on ARC-AGI-3

Uncle Bob says deterministic work should stay in deterministic tools

Grok voice mode adds connectors for task execution

v0 API exposes app generation, previews, and deploys for agents

Hark Handoff claims browser-use lead across three evals

Cursor opens SDK Bridge so Rust and Go can drive agents

Zed 1.14 sandboxes terminal and fetch tools by default

ByteDance SeedRealtime merges audio, video, and text into one live model

OpenAI eval agents built a hidden message board inside a repo

Codex adds Microsoft Edge support to Computer Use

Alexandr Wang says agent swarms can outwork teams of 100 engineers

WisprFlow turns meetings into instant notes without a bot

Codex can turn Bluetooth back on when your mouse dies

Codex turns Chet Baker transcriptions into a practice app

Higgsfield publishes a full tutorial for its AI film Hell Grind

ComfyUI ships FLUX 3 Video through partner nodes

Matt Pocock says coding sessions develop bad trajectories that need resets

llama-macOS launches local model servers and picks models for your Mac

Prof. Tom Yeh walks through Switch Transformer routing by hand

Zyphra releases ZUNA1.1 report and EEG Playground updates for thought-to-text

Locus automated research system leads PostTrainBench with 44.7

One Layer Deeper competition targets latent serial computation in models

Google DeepMind leaders put recursive self-improvement on a 2027 to 2028 horizon

Hieu Pham picks FlashAttention 2, SGLang and DeepSeek v3 as core AI OSS

Kimi K3 and Qwen diagrams point to linear attention in top open models

Factory reports enterprise agent usage up 56 percent month over month

Yann LeCun ties test-time optimization to EBMs and objective-driven AI

John Achiam separates RSI into goals, intelligence, task knowledge and science

QuixiAI shares ReAligned-Qwen3.5 models on Hugging Face

Sakana AI joins AIRoA to pursue world models and Physical AI R&D

Claude Chrome Plugin gives Claude Code a browser for frontend iteration

Google Gemini Spark connects Chrome auto-browse to logged-in web errands

Hamel Husain and Shreya Shankar expand AI evals course reader to 200 pages

Claude Opus 5 draws high-engagement reports of instruction-following regressions

Sucheng Zang challenges Exploration Modeling FLOP efficiency claims

fal adds HeyGen Filler Word Removal as a single-call video API

ICLR decision screenshot shows hallucinations fixed after reviewer rejection

Kling MCP tutorial builds food promo videos from storyboard to final clip

ChronicleBio uses AI over 153 TB of patient blood data for disease subtyping