link
This seems like an important avenue of research. More people need to work on model reliability, consistency and traceability. www.technologyreview.com/2026/10/02/1...
Don’t be fooled—LLMs don’t reasonAbout Me
I’m a Senior Python Dev, AI Enthusiast, Builder. These are some of the things I’m working on:
- Teaching Python through bite-sizes lessons wrapped in a Koan.
Blog Posts
Nov 16, 2025
Skip the fork
May 1, 2025
Building your own tools
Latest Notes
text
I don't understand the hype with TypeSafe's new Jev model. Despite having a different post-training method, they still fail in exactly the same way as LLMs (this example is from their eval suite). And we solved typesafe outputs in 2023, not sure why it's being touted as revolutionary.
link
Substack partners with Pangram to add AI text detection to all notes and posts. Unfortunately, creators can opt out and disable this for their content. Still a step in the right direction, and rebalances the scales back to the side of the reader. post.substack.com/p/against-cl...
Against ClaudefishingProjects
These are some of my projects
Find Substack
Discover quality Substack posts. Beat the notes slop.
#Substack
#Discovery
#Newsletter
#Content
Python Koans
Python lessons wrapped in koans. A weekly newsletter.
#Python
#Education
#TDD
#Learning
