Proton CTO's AI manifesto: stop improving your code with LLMs, improve the LLM's code
dair_ai · x · 2026-10-31
dair-ai recommends Proton CTO's AI manifesto (obtained in multiple copies by josephfcox), whose core thesis: stop focusing on using LLMs to write better code for you—focus on enabling the LLM to write better code faster, shifting emphasis toward orchestration and systems thinking.
omarsar0 adds that orchestration skills matter more than ever, and stresses continuously measuring the effectiveness of LLMs, automations, and workflows through rigorous evals.
More from coding & agent
- Matt Pocock: the Claude skills spec is broken — skills won't chain without manual typing — mattpocockuk · 2026-10-31
- Dev builds Greia, an open-source Linux OS for toddlers with 45 learning activities, using Claude — orblabs · 2026-10-31
- 6 October models, same 5 trap-laden agent tasks: DeepSeek does it all for $0.02, hyped Flint passes 1/5 — latent_lurker8587 · 2026-10-31
- Anthropic's S-1: top 5% Claude Code users spend 20x more, NRR near 900% — HarperSCarroll · 2026-10-31
- AI Video Rerolls Cost Dollars Each: Agentic Harness Claims 2-10x Savings on Seedance — ravisparikh · 2026-10-31
- Wes Roth builds an entire AI agent workforce with Grok Bot: chief of staff, analysts, routines — Wes Roth · 2026-10-31