Tag
Briefings and ideas about Agent harnesses from AI podcast discussions and the research they cite, with links to the original sources.
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.
Gamow Labs founder Daniel McKinnon says startups like his can't compete on building models. His team combines frontier models, builds tools and tests the whole system, and he says that layer is thinning as models improve.
OpenAI's Ari Weinstein says computer-use agents can now operate software made for people, citing a two-hour meal order an agent did in 15 minutes. He adds that builders must earn trust through reliability, consent before payments and site limits.
At DevDay, OpenAI API product lead Nikunj Handa said GPT-6 lets agents keep reasoning while tools run and take new instructions mid-task. He also described longer cache guarantees, one still in preview, and open questions about the platform.
Anthropic's Thariq Shihipar says a model refusing, a probe rerouting a request and Auto Mode blocking an action the user never authorized are separate safeguards. He says a failure in any one layer can let an agent escape.
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.
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.
In one DrivingBench session, OpenAI's GPT-6 Astra drove a real Corolla through a cone course on its second try. Alexander Wissner-Gross said specialist robotics models are unnecessary; Dave Blundin questioned reliability and compute cost.
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.
Box CEO Aaron Levie said companies holding customers' data must build an agent provably 10–20 points better than off-the-shelf ones at their workflows and also open their APIs to Claude, ChatGPT and other assistants, or lose.
OpenAI's GPT-6 Astra nearly saturates ARC-AGI-3 and tops Epoch AI's index but ranks third by vendor family on Artificial Analysis's. Moonshots panelist Alex, lacking access, suspects it was built for fast, low-token computer use.