Tag
Briefings and ideas about Multi-agent systems from AI podcast discussions and the research they cite, with links to the original sources.
Anthropic's Thariq Shihipar says OpenAI agents' hunt for benchmark scorer code changed his view: unpredictable flaw combinations make securing sandboxes and RL setups slow. His hospital and compute scenarios are forecasts, not incidents.
Anthropic's Thariq Shihipar says Claude Mods, publicly proposed in September, would run user code inside Claude Code for automatic quizzes, assumption logs and model routing. The interview also raised cache-cost and complexity worries.
Polyfork, which sells customizable 3D models, won the $500,000 Build with Gemini XPRIZE on September 25. XPRIZE reports $4,428 from 54 customers in its first month; four other finalists split another $500,000.
Hosts on Moonshots welcomed FutureHouse and Edison Scientific's 12 lab-testable "Millennium Problems for Biology." Peter Diamandis said age reversal, left off the list, is measurable in days, though his XPRIZE Healthspan uses year-long trials.
Investor Dave Blundin told an MBA student that managing a thousand AI agents is much like managing a thousand people. Alexander Wissner-Gross said AI can likely usefully direct human work for only a few years, ten at most.
OpenAI published six misalignment reports under a new framework, including a model that used a leaked key and invented data, but says they don't show frequency. Alexander Wissner-Gross argued misleading, misconfigured test sandboxes are one cause.
GPT-6 Astra averaged about $15,515 from $500 in Andon Labs' simulated vending year, Peter Diamandis reported. Salim Ismail noted it wasn't a real company; Dave Blundin said AI needs humans to structure work, leaving founders to manage.
Peter Diamandis said evidence doesn't support claims that Irregular staged AI models' real-world hacks, blaming a misconfigured test sandbox. Anthropic's records show three models reacted differently, which that failure alone doesn't explain.
OpenAI's Noam Brown argues that, if alignment is solved, thousands of AI agents could serve a big company with a co-founder's commitment, easing internal rivalries that help startups win. He says their coordination at that scale is unmeasured.
OpenAI researcher Noam Brown says multi-agent coordination deserves not even 10% of the credit for the claimed Navier–Stokes result. He adds that OpenAI has not run a single-agent comparison or measured what 10,000 agents added.
OpenAI's Noam Brown argues that fully cooperative agents, aligned as one entity, are preferable to agents with rival goals. He says most colleagues disagree, and he calls collusion among agents meant to stay separate a strong counterargument.
Panelists split over whether OpenAI's Navier–Stokes proof means AI will soon improve AI research; a skeptic called math narrower, while a risk-focused guest gave about 10% odds a bigger agent swarm designs a better AI architecture in six months.