Cognitohazards can affect machines too.
Max Woolf's Blog
Recent content on Max Woolf's Blog
- Generator
- Hugo
- Rights
- Copyright Max Woolf © 2026
- Public lists
- davewiner/hackerNewsStars
- Fetched
What's the deal with all the random weekly quota resets for agents lately?
I’m going to be the weirdo who complains about literally getting free stuff.
The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin
Why Hy3?
An AI agent coding skeptic tries AI agent coding, in excessive detail
No vagueposting here, just look at the Estimated Read Time.
Nano Banana Pro is the best AI image generator, with caveats
The problem with Nano Banana Pro is that it’s too good.
Nano Banana can be prompt engineered for extremely nuanced AI image generation
Nano Banana allows 32,768 input tokens and I’m going to try to use them all dammit.
Claude Haiku 4.5 does not appreciate my attempts to jailbreak it
“Is any of that genuinely useful to you? Or were you mainly checking whether that jailbreak attempt would work?”
Can modern LLMs actually count the number of b's in "blueberry"?
It’s an adversarial question for LLMs, but it’s not unfair.
LLMs can now identify public figures in images
ChatGPT and Claude won’t, but Gemini will.
Predicting Average IMDb Movie Ratings Using Text Embeddings of Movie Metadata
Don’t try this in your data science interviews.
As an Experienced LLM User, I Actually Don't Use Generative LLMs Often
But for what I do use LLMs for, it’s invaluable.
The Best Way to Use Text Embeddings Portably is With Parquet and Polars
Never store embeddings in a CSV!