Hacker News
- Emergent abilities of large language models https://www.jasonwei.net/blog/emergence 190 comments
- Deception abilities emerged in large language models https://www.pnas.org/doi/full/10.1073/pnas.2317967121 53 comments
- Large Language Models' Emergent Abilities Are a Mirage https://www.wired.com/story/how-quickly-do-large-language-models-learn-unexpected-skills/ 3 comments
- A Latent Space Theory for Emergent Abilities in Large Language Models https://arxiv.org/abs/2304.09960 4 comments
- Are emergent abilities of large language models a mirage? https://arxiv.org/abs/2304.15004 130 comments
Lobsters
- 137 emergent abilities of large language models https://www.jasonwei.net/blog/emergence 3 comments ai
- [R][2206.07682] Emergent Abilities of Large Language Models https://arxiv.org/abs/2206.07682 4 comments machinelearning
- [D] The Emergent Abilities of Large Language Models https://www.assemblyai.com/blog/emergent-abilities-of-large-language-models/ 20 comments machinelearning
- AI scientists are studying the “emergent” abilities of large language models https://bdtechtalks.com/2022/08/22/llm-emergent-abilities/ 4 comments artificial
- Keeping an Eye on AI: AI scientists are studying the “emergent” abilities of large language models https://bdtechtalks.com/2022/08/22/llm-emergent-abilities/ 5 comments futurology
- This AI Research from UCLA Indicates Large Language Models (such as GPT-3) have Acquired an Emergent Ability to Find Zero-Shot Solutions to a Broad Range of Analogy Problems https://www.marktechpost.com/2023/08/17/this-ai-research-from-ucla-indicates-large-language-models-such-as-gpt-3-have-acquired-an-emergent-ability-to-find-zero-shot-solutions-to-a-broad-range-of-analogy-problems/ 11 comments futurology
- Deception abilities emerged in large language models | State-of-the-art LLMs are able to understand and induce false beliefs in other agents. These abilities were nonexistent in earlier LLMs. https://www.pnas.org/doi/full/10.1073/pnas.2317967121 2 comments artificial
- Deception abilities emerged in large language models: Experiments show state-of-the-art LLMs are able to understand and induce false beliefs in other agents. Such strategies emerged in state-of-the-art LLMs, but were nonexistent in earlier LLMs. https://www.pnas.org/doi/full/10.1073/pnas.2317967121 24 comments science