| #4 |
How I got into research (and why I'm still here)
Self-reflection
|
| #3 |
Language model from scratch
So what does a language model do, exactly?
|
| #2 |
Programming refusal with conditional activation steering
Can we make language models follow behavioral rules without altering weights?
|
| #1 |
Do language models truly learn language?
What is it like to be a ChatGPT?
|