Frontier models are trained for official harnesses, leaving little room for custom agent tuning
menhguin · x · 2026-10-06
@pvncher argues that by fall 2026, the gains people found a year ago from tinkering with custom agent harnesses are much harder to achieve with the latest models — frontier labs' harnesses aren't perfect, but models are trained to use them well. @menhguin broadly agrees, though notes functionality gaps between harnesses remain significant.
More from coding & agent
- Indie dev's agents auto-produced 53 pregnancy reels at ~$0.03 GPU cost per clip, skill released free — victor_explore · 2026-10-06
- Jev playbook: use a $0.042/M-token judge model to route agents and clean context — blaizedsouza · 2026-10-06
- "I don't code anymore, I just yap and stuff happens" — jaivinwylde · 2026-10-06
- Prompt craft: using Opus 5.5 with JS Canvas to draw a Chinese seal-script seal — dotey · 2026-10-06
- "It's insane that coding is now just audibly speaking at your computer" — KevinNaughtonJr · 2026-10-06
- Reason Machines launches Reason 1.0, a frontier coding agent with free daily usage — kalyan_kpl · 2026-10-06