> Input tokens: $0.042 / MTok ($42 per billion tokens).
> Output tokens: FREE (too cheap to meter).
Insane. The video demos are really compelling, in particular the speed.
> Structured outputs slot into ordinary software as fuzzy decision rules: classify, route, score, extract, or branch where hand-written logic is too brittle. The surrounding code constrains their freedom, making them easier to compose into reliable systems.
I buy this vision. A lot of LLM integration I see these days is ultimately exactly this. OpenAI-style structured outputs works decently but this would be a great improvement in cost, latency.
constrained decoding (OpenAI-style structured outputs) make models dumber unfortunately - the short+dense version is that simply masking logits is insufficient because if ever a model was assigning probability to an invalid token, the model is by definition confused. you'd be better off erroring IMO
wxw · · focus · HN ↗
> Output tokens: FREE (too cheap to meter).
Insane. The video demos are really compelling, in particular the speed.
> Structured outputs slot into ordinary software as fuzzy decision rules: classify, route, score, extract, or branch where hand-written logic is too brittle. The surrounding code constrains their freedom, making them easier to compose into reliable systems.
I buy this vision. A lot of LLM integration I see these days is ultimately exactly this. OpenAI-style structured outputs works decently but this would be a great improvement in cost, latency.
CompleteSkeptic · · focus · HN ↗
constrained decoding (OpenAI-style structured outputs) make models dumber unfortunately - the short+dense version is that simply masking logits is insufficient because if ever a model was assigning probability to an invalid token, the model is by definition confused. you'd be better off erroring IMO