Full Width [alt+shift+f] Shortcuts [alt+shift+k]
Sign Up [alt+shift+s] Log In [alt+shift+l]
1

Can modern LLMs actually count the number of b's in "blueberry"?

from Max Woolf's Blog [alt+shift+b] in AI

It’s an adversarial question for LLMs, but it’s not unfair.
12th Aug 2025

Stay updated

Get a weekly newsletter with the top 5 articles worth reading every week.

More from Max Woolf's Blog

An AI agent coding skeptic tries AI agent coding, in excessive detail

No vagueposting here, just look at the Estimated Read Time.

27th Feb 2026 • 1 votes
Nano Banana Pro is the best AI image generator, with caveats

The problem with Nano Banana Pro is that it’s too good.

22nd Dec 2025 • 1 votes
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.

13th Nov 2025 • 1 votes
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?”

17th Oct 2025 • 1 votes

More in AI

The Good Thing About Hard Things

A new research paper titled “​AI Assistance Reduces Persistence and Hurts Independent Performance,”​ which was recently presented at the ​Conference on Language Modeling​, has been ... Read more The post The Good Thing About Hard Things appeared first on Cal Newport.

7 hours ago • 1 votes
Stumblebug - simulation - beta
5 days ago • 1 votes
Run AI agents safely with Ollama and Fly.io

AI agents can now use Ollama's cloud models safely inside Fly.io's cloud computers.

6 days ago • 1 votes
Agentic Primitives 101

Inside the harnesses that let AI carry a job across hours, days, and conversations.

a week ago • 2 votes
Agent governance looks less like moral education and more like institutional economics

how agents turn ruthless on paper first

a week ago • 1 votes
📚 BoredReading

You seem to be enjoying this.

Join free to unlock everything.

Create free account

Already have an account? Sign in