This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
Language Models
•
Applied to
[Linkpost] Solving Quantitative Reasoning Problems with Language Models
by
Yitzi Litt
at
16h
•
Applied to
GPT-3 Catching Fish in Morse Code
by
Megan Kinniment
at
1d
•
Applied to
Assessing AlephAlphas Multimodal Model
by
Ruben Bloom
at
3d
•
Applied to
Announcing the Inverse Scaling Prize ($250k Prize Pool)
by
Ethan Perez
at
3d
•
Applied to
Yann LeCun, A Path Towards Autonomous Machine Intelligence [link]
by
Bill Benzon
at
4d
•
Applied to
Conditioning Generative Models
by
Ruben Bloom
at
5d
•
Applied to
Onto the neurolinguistic recursion
by
ナインペジャポ氏
at
6d
•
Applied to
Causal confusion as an argument against the scaling hypothesis
by
Robert Kirk
at
11d
•
Applied to
Lamda is not an LLM
by
Vanessa Kosoy
at
12d
•
Applied to
Contra Hofstadter on GPT-3 Nonsense
by
rictic
at
16d
•
Applied to
Investigating causal understanding in LLMs
by
Marius Hobbhahn
at
17d
•
Applied to
[linkpost] The final AI benchmark: BIG-bench
by
RomanS
at
21d
•
Applied to
Who models the models that model models? An exploration of GPT-3's in-context model fitting ability
by
Lovre
at
24d
•
Applied to
QNR prospects are important for AI alignment research
by
Evan R. Murphy
at
25d
•
Applied to
Bootstrapping Language Models
by
Raymond Arnold
at
1mo
•
Applied to
Paper: Teaching GPT3 to express uncertainty in words
by
Owain Evans
at
1mo
•
Applied to
RL with KL penalties is better seen as Bayesian inference
by
Tomek Korbak
at
1mo
•
Applied to
A possible check against motivated reasoning using elicit.org
by
david reinstein
at
1mo