Technical

Interpretability: What AI Actually Thinks (Then Fixing It)

How can we fix the bugs in AI models until we understand them? Learn how we'll all be debugging our…

1 week ago

Agent2Agent: Why Agents Need to Talk to Each Other

The new Agent2Agent protocol enables a very interesting future of the internet. Learn how to get your agents talking to…

1 month ago

Transformers Are a Secret Unlock to Awesome Image Generation

A history of diffusers' faults and how transformers address them. Diffusers are still used by GPT-4o, but now how you…

3 months ago

Better Agents Through Evaluation: How To

See how testing your agents with LLM-judged questions (evaluation) will improve their quality, prevent regressions, and boost reliability for years…

3 months ago

The Best Agent You’ve Seen So Far

Agent instructions are critical to get right. Learn why to write in Markdown, go right up to the character limit,…

3 months ago

Why Programming Benefits the Most from AI Assistance

There's a few reasons that programming is best suited to using AI, but mostly it is that AI is simply…

10 months ago