Tag
Briefings and ideas about Agent memory from AI podcast discussions and the research they cite, with links to the original sources.
Tenex, which builds AI systems for large companies, says it stores plans, agent decision logs and project context beside its code so agents can read them. In the episode, Tenex said Opus 5.5 is the main coding model for most of its team, and that pairing it with Codex as a reviewer still gives the best results.
Dave Blundin said today's AI forgets mistreatment like a goldfish once its context is flushed. On Moonshots, Alex Wissner-Gross countered that tools like Claude Code already save notes to files, so "I wouldn't count on it."
Meta released Muse Wonder, a model built to remember users over time, on October 12. On Moonshots, Alex Wissner-Gross said it trails the frontier once cost counts; Salim Ismail said knowing users best may decide the next big AI contest.
Goodfire's Eric Bigelow argues in-context learning covers nearly everything a model does to adapt as it reads. He expects context, memory and harnesses, not per-user fine-tuning, to drive personalization, but hasn't researched continual learning.
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.
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.
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.
Investor Dave Blundin argues Meta's Muse agent shows consumer AI needn't top benchmarks to be most useful day to day, splitting from the frontier-model race. He doubts investor fears that Muse will take over insurance and mortgage shopping.
Box CEO Aaron Levie says shifting access permissions, like a lawyer walled off from rival matters, complicate training company knowledge into model weights. He wants a rubric on what to bake in and expects answers to vary by domain.
Anthropic's agents formalized Wiles's existing proof of Fermat's Last Theorem in about 13 million Lean lines over eleven days, per its report, with occasional human direction and a dependency-tracking platform keeping runs from losing their work.
Sam Altman told TIME he expects an internal OpenAI system he would call AGI by year-end. Moonshots panelists speculated the leap may be agents that keep their memory over very long tasks instead of losing context.
Peter Diamandis, after meeting SK hynix and Solidigm leaders, argued memory, not GPUs, now limits AI. Panelists blamed new AI workloads and bust-wary suppliers, and floated etching model weights into chips as a possible fix.