Hacker News
- Why Are LLMs So Gullible? https://amistrongeryet.substack.com/p/why-are-llms-so-gullible 101 comments
Linked pages
- Man beats machine at Go in human victory over AI | Ars Technica https://arstechnica.com/information-technology/2023/02/man-beats-machine-at-go-in-human-victory-over-ai/ 355 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
- [2307.15043] Universal and Transferable Adversarial Attacks on Aligned Language Models https://arxiv.org/abs/2307.15043 3 comments
- Miguel Piedrafita on Twitter: "Bypass @OpenAI's ChatGPT alignment efforts with this one weird trick https://t.co/0CQxWUqveZ" / Twitter https://twitter.com/m1guelpf/status/1598203861294252033 0 comments
- ChatGPT-Dan-Jailbreak.md · GitHub https://gist.github.com/coolaj86/6f4f7b30129b0251f61fa7baaa881516 0 comments
Related searches:
Search whole site: site:amistrongeryet.substack.com
Search title: Why Are LLMs So Gullible? - by Steve - Am I Stronger Yet?
See how to search.