Jev means structured output is interesting again

kept by inkandquire sep 18

The author contends that Jev’s speed comes from simple single‑token structured output, suggesting the technique is easily replicable and not a major breakthrough.

The last six months in LLMs in five minutes
Simon Willison's blog post documents rapid LLM improvements over six months, using the "pelican riding a bicycle" test as a consistent benchmark to track progress.
also on Simon Willison, OpenAI, #ai, #developer-tools
A first guide to building APIs with AI
Developers should design APIs optimised for AI consumption, exposing concise documentation via endpoints and using non-destructive candidate writes for safe AI actions.
also on Simon Willison, #ai-integration, #developer-tools
Fable & The End of the Free Lunch
The author argues that after Fable's high-cost release, developers must allocate work between expensive models and cheaper alternatives like GLM, ending the era of free performance gains.
also on Qwen, #ai-integration, #ai, #developer-tools
AI's Plummeting Prices Are a Software Story, Not a Hardware One
The rapid decline in AI inference costs is driven by software innovations rather than hardware, enabling local open-weight models to compete with frontier APIs.
also on Qwen, OpenAI, #ai, #developer-tools