← Home

Topic: Agents

209 stories · page 2 of 5

• Operator Memory author: agents need documentation, not RAG memory2026-10-04
• Muse, Claude Cowork and GPT 6.1 tested in English and Farsi: Iran results far weaker2026-10-04
• Earendil ships Pi 1.0 agent harness and Pi Durable package2026-10-02
• DeepSeek releases open-source Harness agent framework in public preview2026-10-02
• Omni-IO Skills harness lifts GPT-5.6 Sol and Claude Sonnet 5 to 100% input support2026-09-30
• 2026 in LLMs so far: coding agents, OpenClaw and tokenmaxxing2026-09-30
• OpenAI launches dots, always-on agents powered by GPT-6 Astra2026-09-29
• Meta's Muse agent shared a seller's home address and posed as him2026-09-29
• PUBG Ally: a voice-enabled AI agent joins matches as a teammate2026-09-27
• John Gruber warns Meta's Muse is riskier than it looks2026-09-27
• How to keep enjoying programming in a world of LLMs2026-09-27
• Coding agents make software engineering harder, not easier, argues blog note2026-09-27
• Google's Gemini can now call businesses for you on Pixel 112026-09-26
• Instinct's AI agent saved a WIRED writer $550, and it's chasing a $10bn valuation2026-09-25
• Meta piles new features onto its Muse AI agent at Connect2026-09-24
• Unreal Labs ships Unreal Agent, an async harness up to 40% cheaper than Codex2026-09-23
• Rabbit launches OS3, an agentic OS for devices you own2026-09-23
• Carson Gross proposes checking Markdown into /src as source code2026-09-23
• Google's RRSI curbs overfitting in self-improving AI agent harnesses2026-09-22
• MintAct unifies UI agents across mobile, desktop and web2026-09-21
• Meta's Muse AI agent collects more data than it gets things done2026-09-21
• A blog post argues MCP has already outlived its usefulness2026-09-21
• Codex Astra tops Brood War Bench, beating Grok and Claude Fable at StarCraft2026-09-20
• Claude Code: a 'Chief of Staff' pattern for orchestrating agents2026-09-20
• OpenAI: GPT-6 Astra powers Hex's data-visualization agents2026-09-19
• Cua releases CUA-S1, small models for computer-use decisions2026-09-19
• Claude Code adopts OpenAI's AGENTS.md format2026-09-19
• Google announces CC, an experimental AI agent for families2026-09-18
• Devin's Code Scans turns broad goals into pull requests2026-09-18
• Anthropic rebuilds Claude Code Projects for parallel agent threads2026-09-18
• HarnessTax study: coding agent harness swings cost, not accuracy2026-09-17
• Gusto, Insight Partners and Leland to debate AI agents as co-founders at Disrupt2026-09-17
• Fable 5 designs a working PCB from a plain English prompt2026-09-17
• Amazon open-sources Pizza Bot, an inbox for long-running AI agents2026-09-16
• ALTK-Evolve cuts a GPT-4.1 agent's consistency gap roughly in half2026-09-16
• Fyxer's AI assistant hits 90% retention using OpenAI models2026-09-15
• Andon Labs opens Pion for AI agents to run real businesses2026-09-15
• OpenAI introduces Data agent in ChatGPT Work2026-09-14
• Occamy-1.0 ships as a cost-efficient 35B model for co-work agents2026-09-14
• Fable 5.1 solves a cipher unsolved for 370 years2026-09-14
• Ensemble pitches EIQ as healthcare AI's missing integration layer2026-09-14
• GPT-6 Astra tops Claude Fable 5.1 on vending, drone tests2026-09-13
• Cognition's Devin uses GPT-6 Astra to test its own code2026-09-13
• AllSpark's Iris-mini and Iris-pro top open-weight search agent benchmarks2026-09-13
• AI agents run on priors nobody can fully vet, essay argues2026-09-13
• T1 lifts Terminal-Bench 2.1 score from 43.8% to 64.0% with RL2026-09-11
• Shopify ditches React Native for native apps, crediting AI coding agents2026-09-11
• PARSER splits reading from reasoning in long-context LLM agents, cuts latency by up to 11x2026-09-11
• OpenAI ships Agents API with a managed Codex harness2026-09-11
• Thoughtworks engineers rediscover the blackboard pattern coordinating AI agents2026-09-09

All topics · Archive by month