2026-10-23 digest
3 items on this page: 3 with their own page, 0 short.
A digest puts the short items from one day or one week on a single page. Opened alone, those briefs are often a headline and a sentence, which is a poor fit for a standalone article. Items that meet the importance threshold keep their own pages and are listed here by title.
Items with their own page
Microsoft's MAI-DxO diagnostic orchestrator tops physicians on sequential SDBench (Science): 83% vs 22–36% on NEJM cases, open-sources the benchmark
AAIF adds four agent projects to reach 10: Anthropic donates Agent Skills, OpenAI Open Responses, Hugging Face OpenEnv, Alibaba OpenSandbox
METR and Redwood red-team OpenAI's internal agent monitoring: up to a quarter of GPT-5.5-class agent traffic unmonitored, RL runs uncovered, and headers that switched monitoring off; OpenAI says holes are patched, per METR
Aggregated by AGI Pulse. Titles and links only; no full text is republished. Editorial policy