Researcher's AI workflow advice: start small, do key steps manually before offloading
jmschreiber91 · x · 2026-11-19
Researcher jmschreiber91 shares practical advice on adopting AI systems in research:
- No single right way: figure out what works for you; start with small bites — e.g., have the model plot results you already have, or redo an analysis you've completed, and watch how it approaches it.
- The grey zone: you need to understand how things work, but you can progressively offload tasks once comfortable.
- Manual isn't banned: do key things manually a few times before offloading — this builds the judgment needed to evaluate AI output.
A gradual, understanding-first methodology for adopting AI in research workflows.
More from coding & agent
- Garry Tan's "Personal AGI" is a folder of markdown files — 220,000 pages, 400x his 2013 output — jasonkneen · 2026-11-19
- Same weights, 3x score: Gemini 4 Neon jumps 12.8%→39% on SWE-sweep by swapping the harness — Delicious_Character6 · 2026-11-19
- ESP-Skainet: Open-Source Framework for Fully Offline Voice AI on ESP32 — alexcovo_eth · 2026-11-19
- Ploten ships an MCP server that live-edits open Power BI Desktop reports — plotenhq · 2026-11-19
- Testing gemini-4-neon with a DIY PowerShell agent harness: "benchmarks are for tourists" — dfinke · 2026-11-19
- Merge's Agent Handler adds credential passthrough: run tools without storing user tokens — shensi · 2026-11-19