early stage product: 🪵 collect tinder, start fire before freeze
later stage product: 🔥 keep fire alive, grow fire, defend fire
very different
h/t @christineluc
We re-tested GPT-5.6 Luna from @OpenAI on ARC-AGI (Verified) following its recent 80% price reduction:
- ARC-AGI-2: 59.6%, $0.18/task
- ARC-AGI-1: 90.7%, $0.07/task
The new results match Luna's original performance at a much lower cost.
huge smol update 🎈
smol is a mighty but smol (!) agent
in 9 lines of python
no 3rd party dependencies
smol is smol
smol is so smol you can understand it in an afternoon
smol supports any OpenAI Responses API compatible endpoint
smol now also sends session_id for better
huge smol update 🎈
smol is a mighty but smol (!) agent
in 9 lines of python
no 3rd party dependencies
smol is smol
smol is so smol you can understand it in an afternoon
smol supports any OpenAI Responses API compatible endpoint
smol now also sends session_id for better