Linking pages
- We Have Made No Progress Toward AGI - Mind Prison https://www.mindprison.cc/p/no-progress-toward-agi-llm-braindead-unreliable 60 comments
- OpenAI's o3: Over-optimization is back and weirder than ever https://www.interconnects.ai/p/openais-o3-over-optimization-is-back 0 comments
- Weekend Links #12: o3 is smart but tells lies https://peterwildeford.substack.com/p/weekend-links-12-o3-is-smart-but 0 comments
Linked pages
- [2310.13548] Towards Understanding Sycophancy in Language Models https://arxiv.org/abs/2310.13548 72 comments
- [2109.07958] TruthfulQA: Measuring How Models Mimic Human Falsehoods https://arxiv.org/abs/2109.07958 7 comments
- [2409.12822] Language Models Learn to Mislead Humans via RLHF https://arxiv.org/abs/2409.12822 7 comments
- https://cdn.openai.com/o1-system-card.pdf 6 comments
- Model Spec (2025/02/12) https://model-spec.openai.com/2025-02-12.html 4 comments
- [2210.03629] ReAct: Synergizing Reasoning and Acting in Language Models https://arxiv.org/abs/2210.03629#google 3 comments
- https://platform.openai.com/docs/guides/reasoning 0 comments
Related searches:
Search whole site: site:transluce.org
Search title: Investigating truthfulness in a pre-release o3 model | Transluce AI
See how to search.