nverse-scaling/prize: A prize for finding tasks that cause large language models to show inverse scaling
github.com · 6,422 words · saved by 1 readers
A prize for finding tasks that cause large language models to show inverse scaling
TL;DR: Win up to $100,000 for finding an important task where larger language models do worse. Submissions due August 27, 2022 (Round 1) and October 27, 2022 (Round 2). The contest has ended! Results: Round 1, Round 2. Recent changes 11 October, 2023 Added Modus Tollens caveat to data-release README 21 March, 2023 Updated prize pool info 1 March, 2023 Released data for all winning tasks 17 December, 2022 Updated prize eligibility for FAR employees 12 December, 2022 Added prize terms update to the ‘Prize information’ section Updated ‘About us’ 9 October, 2022 Added Huggingface…
saved by
related reading
- irmckenzie.co.uk/round2irmckenzie.co.uk
- Announcing the Inverse Scaling Prize ($250k Prize Pool) — AI Alignment Forumalignmentforum.org
- Scaling Laws, Carefully | Lil'Loglilianweng.github.io
- machine learning imindslice.substack.com
- Pathways Language Model (PaLM): Scaling to 540 Billion Parameters for Breakthrouai.googleblog.com
- Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
- 2308.03958arxiv.org
- larger language models may disappoint you [or, an eternally unfinished draft] — LessWronglesswrong.com
- Scaling: The State of Play in AIoneusefulthing.org
- IsoCompute Playbook: Optimally Scaling Sampling Compute for RL Training of LLMscompute-optimal-rl-llm-scaling.github.io
- Alex L. Zhangalexzhang13.github.io
- Scaling Laws Do Not Scalearxiv.org