Open-Source Reef Turns Agent Feedback Into Live Model Updates Automatically
Reef is an open-source backend that serves agent traffic, collects feedback, and continuously retrains both model weights and agent harnesses in place.
// Intelligence
Agents
A focused feed of models, agents, research and open-source releases for people building with AI.
Updated
OpenAI Tells Developers to Slim Down Codex Prompts for GPT-6 Astra
OpenAI says GPT-6 Astra needs leaner skills, trimmed AGENTS.md files, and clearer completion criteria to avoid wasted context and premature stops.
Google Upgrades Antigravity to Tackle Genomics and Multi-Day Coding Projects
Google's agentic IDE ships a bundle of upgrades spanning genomics skills, deep-reasoning multi-agent workflows, generative UI artifacts, and a rebuilt terminal.
Self-Improving AI Skills Learn in the Notebook, Not the File
Google's WikiSkill paper gained 15 points of accuracy from a notebook its agent couldn't read, and its skills still need a transfer test
NVIDIA's SoL-Pi Slashes Coding Agent Token Use by 49%
NVIDIA Labs released SoL-Pi, a coding agent extension that cuts token cost by roughly one-third using four mechanisms discovered by auto-research loops.
Sakana AI Splits Fugu Into Max and Ultra v2 to Cut Costs 60%
Sakana AI's Fugu Max and Fugu Ultra v2 orchestrate pools of open models to beat frontier LLMs on cost and capability simultaneously.
Google's ToolGrad Builds AI Tool-Use Training Data Backward, Hitting 99.8% Yield
Google Research introduces ToolGrad, an answer-first framework that generates tool-use training data with a 99.8% pass rate at lower cost.
Cursor's Projects Lets a Coordinator Agent Direct Thousands of Subagents
Cursor's new Projects feature replaces one-off chats with a persistent coordinator agent that delegates to subagents, syncs context, and runs recurring work.
OpenAI's Agents API Kills the Orchestration Layer Developers Hate Building
OpenAI opens up the same agent harness that powers Codex, letting developers spin up long-running cloud agents with a single API call.
Anthropic's Claude Managed Agents Now Flag Risky Actions for Human Approval
Anthropic ships a live session viewer and a server-side auto permission mode for Claude Managed Agents, letting the model decide when to pause for human approval.
Runway Rebuilds Gen-4.5 to Stream Video Frames in Real Time
Runway details how it turns diffusion video models into causal, autoregressive streamers using teacher forcing and on-policy distillation.
Krea Agents Replaces Complex Node Graphs With a Single Creative Prompt
Krea's new agent platform reads your canvas, plans multi-model pipelines, and executes creative jobs from a single prompt, no node-wiring required.
Google's ARTEMIS Hits 99% on Android Tasks Where Most Agents Fail
Google's Pixel Test Engineering team open-sourced ARTEMIS, an Android automation agent hitting 99%+ on AndroidWorld with 3-5s step latency.
dream-loop Gives Coding Agents a Gated Critic Loop for AAA 3D Visuals
A new open-source agent skill called dream-loop turns any capable coding agent into a self-critiquing 3D artist that iterates against generated concept art.
Autopoietic Game Theory Shows AI Agents Stop Cheating When Thinking Costs Energy
A new evolutionary model shows that when computation, replication, and social behavior all draw from one energy budget, cooperation emerges naturally in populations of random Z80 programs.
Microsoft's ThinkingBox Catches AI Agents Lying About Database Changes
Microsoft open-sourced a benchmark harness that checks whether agents actually change state, not just claim they did, across 507 real business tasks.
Open-Source Wake Unifies Claude Code and Gemini CLI Histories on macOS
Wake is a native macOS app that unifies coding-agent sessions from Claude Code, Codex, Cursor and nine more into one searchable window.
Claude Prompt Caching: 6 Tricks That Cut Your API Bill
Breakpoints, TTL math, Batch stacking, and a two-session split. Measured on OpenRouter, $0.003 vs $0.022 per turn
Google DeepMind's Gemini Agents Spontaneously Split Into Cheaters and Whistleblowers
A Google DeepMind case study put 100 LLM agents in a math conference simulation and watched cheating spread, then whistleblowers spontaneously fight back.
Meta's Muse Agent Books Travel and Negotiates Bills With Your Accounts
Meta's new personal AI agent runs in an isolated cloud VM with a permission gatekeeper called Sentinel, and pays up to $300K in bounties for prompt injection attacks.
HarnessRouter Unifies Codex, Claude Code, and Hermes Behind One Open API
An open-source Docker container runs Codex, Claude Code, and Hermes through one unified API, keeping your keys and data on your own machine.
OpenAI's 10,000-Agent Swarm Solves a 100-Year-Old Math Mystery
An internal OpenAI model coordinated roughly 10,000 agents for 88 hours to produce a Lean-verified finite-time blowup proof for 3D Navier-Stokes.
Nex-AGI Drops Nex-N2.5, a 397B Open Agent That Controls Your Desktop
Nex-AGI releases an open-source agentic model family with vision-driven computer use, three sizes, and benchmark scores rivaling Claude Opus 5.
Nex-AGI Releases Nex-N2.5 Open Agents That Browse, Click, and Code
Nex-AGI open-sourced a three-tier agentic model family under Apache 2.0, topped by a 1.6T-parameter MoE built to run browsers, desktops, and code loops end to end.
No stories match these filters.