Weaviate Podcast: MIT PhD's "Machine Studying" lets always-on agents prep without knowing the task
CShorten30 · x · 2026-10-29
Weaviate Podcast episode #148 hosts MIT CSAIL PhD student Jacob X. Li on his "Machine Studying" framing for what 24/7 always-on agents should do between requests.
Like a student prepping for an unseen exam, an agent studies a corpus (codebase, drug-discovery papers, system logs) without knowing the downstream task, building deep understanding ahead of time instead of leaning entirely on inference-time compute.
The paper defines expertise as efficient use of inference-time compute—measured as the area under the performance-vs-compute curve of a ReAct agent loop—and lays out three bets every studying method makes: synthetic data, weight updates (LoRA), and more.
More from coding & agent
- Linear's Slack bot slammed as "GPT-3.5-level" — pick your team's AI by daily reliability, not leaderboards — sujingshen · 2026-10-29
- Claude Code taps Oxylabs via MCP to scrape bot-protected sites into clean JSON — mhdfaran · 2026-10-29
- opencode ships /goal command for coding agents — lyraxana · 2026-10-29
- Make0 Brain: an open-source MCP server for shared, versioned agent memory with 80ms retrieval — heysrb · 2026-10-29
- Discover API lets AI agents search social platforms in one call, with spend caps and semantic filtering — dooddyman · 2026-10-29
- Dev's code merged by AI agent with zero human intervention — iamsahaj_xyz · 2026-10-29