Jeremy Howard, fast.ai co-founder, says Opus 4.8 improves coding workflows by pausing for user input at critical steps
Developer Ross Wightman corroborated the improved usability.
(This is using our in-house harness, Solveit.)
Worked on some code this morning using Opus 4.8 and so far I'm really liking it. Much more cooperative than 4.7 and less "over agentic". Stops and asks for my input when needed in places 4.7 (and GPT 5.5) would just foolishly blast ahead. (Still WAY too expensive.)
@jeremyphoward 4.7 was rather difficult to work with on anything extensive, mostly used it for review and switched to GPT 5.5 for the building / round tripping. 4.8 seems more useful so far...
Worked on some code this morning using Opus 4.8 and so far I'm really liking it. Much more cooperative than 4.7 and less "over agentic". Stops and asks for my input when needed in places 4.7 (and GPT 5.5) would just foolishly blast ahead. (Still WAY too expensive.)