@nikhil07prakash.bsky.social
📤 37
📥 7
📝 21
pinned post!
How do language models track mental states of each character in a story, often referred to as Theory of Mind? We reverse-engineered how LLaMA-3-70B-Instruct handles a belief-tracking task and found something surprising: it uses mechanisms strikingly similar to pointer variables in C programming!
12 months ago
2
59
20
Excited to be attending
#ICLR
in person this year! I’ll be presenting 3 works across the main conference and workshops. If you’re around, please stop by, say hi, and feel free to reach out if you’d like to connect!
about 2 months ago
1
0
0
Another cool work indicating Transformers perform symbolic reasoning: filter heads represent and manipulate abstract predicates across tasks and languages.
add a skeleton here at some point
7 months ago
0
1
0
How do language models track mental states of each character in a story, often referred to as Theory of Mind? We reverse-engineered how LLaMA-3-70B-Instruct handles a belief-tracking task and found something surprising: it uses mechanisms strikingly similar to pointer variables in C programming!
12 months ago
2
59
20
you reached the end!!
feeds!
log in