Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Paper • 2206.04615 • Published • 6
Gregor Betz PRO
ggbetz
AI & ML interests
Reasoning, AGI, AI Safety, AI Reliability
Recent Activity
upvoted an article 6 days ago
TRL v1.0: Post-Training Library Built to Move with the Field updated a Space about 1 month ago
ggbetz/trackio published a Space about 1 month ago
ggbetz/trackioOrganizations
authored 4
papers over 2 years ago
Critical Thinking for Language Models
Paper • 2009.07185 • Published
DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models
Paper • 2110.01509 • Published
Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2
Paper • 2103.13033 • Published