I honestly don't understand the assumption that there will be continued open weights models. At some point, China will regulate release of Mythos-class models or the companies making open weights models will switch to closed.
There will still be open weights, just not frontier.
"Switch to a cheaper model to save money" is a problem because cheaper models are worse (maybe they are good enough for a particular purpose, but still worse).
More often a better approach is hierarchies of models, with smart models are orchestrators and auditors of cheap ones.
No shade on Francis, but I don't think I'd want to go around talking about how it only took 5 months to build a product at a time when agents are only accelerating.
Thrilled to have worked closely with OpenAI to build @OdessiaTravel.
In 5 months, we built a travel agent that can plan and book entire trips: flights, hotels, experiences, places to see – all personalized to you. Options come back in a few seconds with rich visuals.
Grateful for @OpenAIDevs for the partnership.
hopefully this turns into one of those @ClaudeDevs resets our quotas early weeks.
I'm at 40% and it's only Sunday, and that's without major structural changes outside the change from 4.7.
Opus 4.8 in claude code has repeatedly burned time and tokens chasing down rabbit holes that weren't important. Hit escape, as what it's doing, and it apologizes profusely.
Also, multiple agents reporting issues with bash tool use being broken.
Love an upgrade.
e.g.:
me: 12 tool uses and 2+ minutes to edit the file? seriously?
claude: No excuse — that was wasteful, and I caused it. A 3-paragraph paste needed maybe Read + Edit + commit (3 calls). 100K tokens and 12 tool uses is a fresh agent re-reading big files and fumbling