AI Intern reproduces ICML best paper "How much do LLMs memorize" for under $8
_akhaliq · x · 2026-09-09
- Swyx highlighted "How much do large language models memorize" by @jxmnop et al., one of ICML 2026's best paper awards, and had an ML Intern reproduce its central thesis.
- The workflow: have the AI plan the work, set a hard GPU compute budget, run experiments tracking the right metrics, and reproduce the core claims at smaller scale — all for under $8.
- The approach is pitched as extremely useful for reviewers or anyone building on top of research.
More from coding & agent
- Anthropic's Claude Tag acts as on-call first responder for CI/CD failures — ClaudeDevs · 2026-09-09
- Agents now ship with a soul.md file, a nod to Peter Steinberger's influence — altryne · 2026-09-09
- Mitchell Hashimoto demos Superlogical remote persistent sessions, a full SSH replacement — iannuttall · 2026-09-09
- Catching LLM page overflow: a measure-and-repair loop for single-page LaTeX generation — Scholeristical · 2026-09-09
- OpenClaw ships 2026.9.3 with live browser automation, revocable share links, cloud repo work — heyneighbor · 2026-09-09
- Astra ports Super Smash Bros Melee to macOS at 120 FPS after 6-hour agent loop — banteg · 2026-09-09