Hacker News
- GPT-4 performs significantly worse on coding problems not in its training data https://twitter.com/cHHillee/status/1635790330854526981 282 comments
- GPT-4 fails to solve coding problems it hasn't been trained on https://twitter.com/cHHillee/status/1635790330854526981 89 comments artificial
Linking pages
- GPT-4 and professional benchmarks: the wrong answer to the wrong question https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks 329 comments
- The Multi-modal, Multi-model, Multi-everything Future of AGI https://lspace.swyx.io/p/multimodal-gpt4 167 comments
- What GPT-4 Does Is Less Like “Figuring Out” and More Like “Already Knowing” https://amistrongeryet.substack.com/p/gpt-4-capabilities 85 comments
- GPT-4’s successes, and GPT-4’s failures - by Gary Marcus https://garymarcus.substack.com/p/gpt-4s-successes-and-gpt-4s-failures 1 comment
- Can Large Language Models Reason? - by Melanie Mitchell https://aiguide.substack.com/p/can-large-language-models-reason 1 comment
- Update #46: GPT-4 and Modular Reasoning for Visual Question Answering https://thegradientpub.substack.com/p/update-46-gpt-4-and-modular-reasoning 0 comments
- What Do LLMs Know About Linguistics? It Depends on How You Ask https://thegradient.pub/what-do-llms-know-about-linguistics-it-depends-on-how-you-ask/ 0 comments
- Responsible optimism for ML, which is still Programming's Asbestos https://morepablo.com/2023/07/ml-is-still-programming-s-asbestos.html 0 comments
Related searches:
Search whole site: site:twitter.com
Search title: Tweet / Twitter
See how to search.