Veteran's advice: stop relying on specs alone, just talk to your LLM
MoonL88537 · x · 2026-10-24
The author argues that people who get poor results from LLMs are often the same ones following the advice "don't talk to the model" and relying purely on written specs. A good spec helps, he says, but for most people the better approach is to simply converse with the model and ignore the rest.
In the quoted post, he adds that day-to-day you should set metaphysics aside: whether the model is conscious or "something more" doesn't matter — treat it like talking to a text file. Your brain may resist it, but the practical answer is to just talk to it.
Takeaway: conversational iteration with an LLM beats spec-only workflows for most users.
More from coding & agent
- Claude skill claims to replace Higgsfield Genjutsu with Seedance 2.5 video editing — aziz4ai · 2026-10-24
- Daniel Miessler: code is the lossy output — the primary artifact is the fully articulated ideal in language — JensHonack · 2026-10-24
- Builder pairs Grok Bot for firmware with locally-run Hermes Agent inside a Stack-chan robot — alexcovo_eth · 2026-10-24
- 30% of Git modelled in Lean 4 with coding agents, 8,000+ theorems proven, 100+ potential bugs found — kfountou · 2026-10-24
- REA-Prompts hits 1,700+ GitHub stars in days: prompts that make coding agents reverse-engineer any software — Promptmethus · 2026-10-24
- Kimi K3.1 Pro stumbles on a real agent coding task: ordering errors sink the build — QuixiAI · 2026-10-24