Power users nuke all memory, workflows and setups whenever a new model ships
nateliason · x · 2026-10-06
Austen reveals that whenever a new model comes out, he wipes all his memory, workflows and setups and starts fresh — nateliason endorses it as "the way." The practice reflects a growing consensus: big capability jumps make old prompts and accumulated flows a liability, so rebuilding from scratch beats migrating.
More from coding & agent
- Google's AIM paper: research agents improve faster by mapping and auditing ideas, beating baselines up to 3.1x sooner — rohanpaul_ai · 2026-10-06
- Most Lawyers Use AI Legal Tools Only at Basic One-Shot Prompt Level, Says Attorney — jkubicki · 2026-10-06
- GPT-2 × Codex builds 'alien eye' tracker web app that admits when it can't see — MikePFrank · 2026-10-06
- Codex tasks widget broken? Editing it to select a specific host fixes it for now — Dimillian · 2026-10-06
- xAI TypeScript SDK hits v0.2.2: retryBeforeOutput now retries create() without stream — tetsuoai · 2026-10-06
- Hugging Face Kernels quickstart: load GPU-optimized kernels in one line — ariG23498 · 2026-10-06