High-compute reasoning models like o1 being bad at chat and good at “report generating” means a totally different UX. Seems closer to posting a job on a freelancing site vs messaging with a bright but lazy coworker.

https://www.latent.space/p/o1-skill-issue?utm_medium=web

Comments

Posting Rules

  • Be respectful to others
  • No spam or self-promotion
  • Stay on topic
  • Follow Bluesky's terms of service