Post
Conversation
![David Watson π₯](data:image/svg+xml,<svg xmlns="http://www.w3.org/2000/svg" width="96" height="96"><rect fill-opacity="0"/></svg>)
Post your reply
Ironically it's in the GPT 4.5 model system card, p45 cdn.openai.com/gpt-4-5-system
Self reported metrics are as good as this meme. Not very professional or useful.
Looking to invest in the Enablers and Adopters of AI?
Consider an actively managed fund investing in companies actively involved in developing and implementing AI technologies.
sonnet 3.7 gets ~70% on SWEBench, but have we seen a measurable drop in open github issues?
Very interesting, though Iβd note that 42% of PRs will be << than 42% of the work, bc many PRs will be trivial/busywork and few will be massive projects
Yeah. I donβt understand why that deep research data point hasnβt gotten more attention/discussion β seems pretty significant!!
