Herbie Bradley: people in 2026 still severely underrate the returns to more time on prompting
herbiebradley · x · 2026-10-30
Responding to Nathan Benaich, Air Street Capital's Herbie Bradley argues the take "has aged well": as of 2026 people still severely underrate the returns to spending more time on prompts — over and above using a harness to construct prompts from data. His point: even with automated prompt pipelines, manual prompt refinement still pays off.
Related event: VC revives old post claiming prompt engineering is not a real job(2 posts)→
More from coding & agent
- Codex appears to default to GPT-6 Luna for memory extraction and GPT-6.1 Terra for organizing — TheMoonMidas · 2026-10-30
- Factory launches Droid 1.0, a new engine for its coding agent targeting complex projects — sonofalli · 2026-10-30
- E2E-SWE benchmark: 186 tasks test coding agents building repos from scratch, best pass@1 just 67.7% — jyangballin · 2026-10-30
- LLM-driven pentest framework ARTEX exposed: one FOFA query finds 300+ live panels — cyb3rops · 2026-10-30
- How one builder runs his life on a Grok Bot agent: skills repo, finances, home lab — Rasmic · 2026-10-30
- Qwen Code nightly: Generated UI on by default, WebShell message paging — qwen-code-review-bot · 2026-10-30