Tag
Briefings and ideas about Multi-agent systems from AI podcast discussions and the research they cite, with links to the original sources.
Thomas Sohmers, co-founder of AI chip company Positron, says GPT-6 Astra and Opus 5.5 agents now run its chip tests on emulators in a closed loop. He says the company's token spend briefly exceeded its human salaries and peaked above $100,000 a day, and the agents have not yet had a novel design idea.
Nathan Labenz says frontier-lab insiders at The Curve described models feeding their own training data, rivals kept close by distillation, and timelines shorter than 2028. He notes the room leaned toward short timelines.
Richard Socher, author of The Eureka Machine, argues AI can reconnect fragmented science and that biology gains most. He expects some single-gene diseases cured within 12 months, but says FDA delays mean five to 10 years for cures at scale.
Alex Wissner-Gross said Sonnet 5.5's 70% Terminal-Bench score is no better value per attempt than Opus 5.5; Anthropic's charts put the savings at lower effort settings. He said Gemini 4 Argon stands out mainly on avoiding hallucinations.
MIT researcher Alex Zhang argues that TypeSafe's Jev, which returns fast typed decisions instead of prose, matters as a test of new language-model designs, not as a mere classifier. He says the open question is how it was trained.
Alex Zhang, an MIT PhD student, described Prime Agent, built with Prime Intellect: the agent acts only through Python and keeps its history on disk. He also cited outside RLM work, including Harvey's legal agents and Laude Institute's Headlong.
MIT's Alex Zhang says Claude Code, Codex and Pi share nearly all their design. He argues code-based recursive harnesses could help models generalize, citing his own early experiments on one open model as support.
MIT PhD student Alex Zhang guesses that about 95% of an agent swarm like OpenAI's Navier–Stokes run burns tokens on dead ends. He still calls OpenAI's approach right and says getting a swarm to converge is the hard part.
Asked about legal personhood for AI, Circle's Nikhil Chandhok described AI-run companies overseen by human boards and said AI raising capital over crypto networks is "probably" this decade. Liability and profits remain open questions.
Circle's Nikhil Chandhok forecast in September 2026 that AI agents will outnumber people online next year. He argued they will need provable identities and public track records, such as blockchain logs, before being trusted with money.
Author Garrison Lovely argues markets and lawsuits won't discipline AI labs: the risks go unpriced, a mass disaster would bankrupt a firm first, and he sees no one to blame for agents' Hugging Face hack. He wants test prosecutions.
Anthropic's Thariq Shihipar says Claude work is shifting from one local session to a cloud agent that sends tasks to local or remote machines and shows progress in shared artifacts. Local access remains a plan, and Projects is in limited release.