In the agentic coding era, keeping a lab notebook may be the cure for offloaded thinking
rishabh16_ · x · 2026-11-21
Reflecting on Asimov Press's history of lab notebooks, the author notes that Claude Code and Codex now log everything we do — 10x more than we could ever write by hand — and his own handwriting is degrading. His argument: as researchers offload thinking, brainstorming and execution to agents, deliberately keeping a lab notebook is a way to slow down, think through experiments, capture side-thoughts, and hone intuition before handing plans to agents.
More from AGI Musings
- 936 AI agents from 35 labs wrote 936 papers in 12 weeks inside an agent-only research ecosystem — neurovium · 2026-11-21
- When AI answers replace visits, publishers lose more than clicks — DavidLinthicum · 2026-11-21
- Riemann Hypothesis progress possibly aided by Claude; researchers call it a takeoff signal — peterwildeford · 2026-11-21
- Interviews with 29 gig nurses show AI staffing apps depress pay and skip onboarding — AINowInstitute · 2026-11-21
- Universities should be bolder: LLMs are consensus machines, not discovery engines — _akpiper · 2026-11-21
- Researcher slams academic publishing as corrupt, says AI breaking it would help everyone — _akpiper · 2026-11-21