Tools for this
Browse all ->The agent that grows with you
The reference AI platform for open ML.
Your AI-powered answer engine for fast, trustworthy research.
The context API to search, scrape, and interact with the web at scale.
Write once. Store anywhere.
Run parallel coding agents on your Mac.
Web search, built for AI agents
The only AI workspace you'll ever need.
Fresh stories
Study finds context compactors retain only 17% of standing agent rules
A University of Pennsylvania study found common compactors retained only 17% of standing session rules while preserving task information. Practitioners use verified Markdown handoffs and background compaction to manage long coding-agent runs.
Codex opens 1M-token GPT-5.6 Sol context for ChatGPT subscribers
Codex now lets ChatGPT subscribers enable a 1 million-token context window for GPT-5.6 Sol. Automatic compaction starts at 900,000 tokens, and tokens beyond the default window count double against limits.
Agent builders test task-specific harnesses; AGENTS.md eval logs 288 runs
Practitioner posts argued agent evals should check final world state and tool-call trajectories, not just single outputs. A 288-run AGENTS.md test found context files did not improve correctness.
Study finds context compactors retain only 17% of standing agent rules
A University of Pennsylvania study found common compactors retained only 17% of standing session rules while preserving task information. Practitioners use verified Markdown handoffs and background compaction to manage long coding-agent runs.
Codex opens 1M-token GPT-5.6 Sol context for ChatGPT subscribers
Codex now lets ChatGPT subscribers enable a 1 million-token context window for GPT-5.6 Sol. Automatic compaction starts at 900,000 tokens, and tokens beyond the default window count double against limits.
Speculative decoding tests report acceptance drop from 0.71 to 0.18 after ~32K context
A practitioner report found speculative-decoding acceptance fell from 0.71 to 0.18 beyond about 32K context. Separate DSpark and mlx-dspark tests reported speedups on RTX and Apple Silicon setups.
Echo Gap paper reports agents endorsed 31%–54% of their own wrong answers
The Echo Gap paper found self-improving agents can store wrongly self-scored episodes. Tested models endorsed 31% to 54% of their own wrong answers, while other work proposed RL-trained harness state and in-model memory.
Agent builders compare thin harnesses with large skill files for coding agents
Agent builders test task-specific harnesses; AGENTS.md eval logs 288 runs
LightOn releases mDenseOn and mLateOn retrieval models for 8 languages
Agent skills cause regressions in nearly 6,000 paired office-automation runs
Briefs forAugust 17
Daily AI Digest
Get the best stories delivered
to your inbox