Agents Make the Review Loop More Exhausting
jordiponsdotme · x · 2026-07-15
This reply argues that agents won't eliminate work; they may instead turn the read/review/ask loop into a new form of work.
The core idea:
- While you're reviewing one proposal, background agents are generating the next one.
- The result is an endless cycle of reading, reviewing, and questioning, which feels just like real work—only more automated and exhausting.
More from coding & agent
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26