josh :)

Karma: 19

MS in AI at UT Austin. Interested in interpretability and model self-knowledge.

I am open to opportunities :)

Twitter: @joshycodes
Blog: joshfonseca.com/blog

A Simple Method for Accelerating Grokking

josh :)24 Jan 2026 3:19 UTC

13 points

1 comment3 min readLW link

The Case for Artificial Manifold Intelligence

josh :)28 Dec 2025 21:27 UTC

2 points

0 comments7 min readLW link

Training Models to Detect Activation Steering: Results and Implications

josh :)26 Nov 2025 14:51 UTC

7 points

0 comments4 min readLW link

How RLHF Silences AI

josh :)25 Nov 2025 6:01 UTC

1 point

0 comments1 min readLW link

(joshfonseca.com)