corpus.blog
Most cited
Talked about
Blogs
41554 blogs · [ { "id": "01a0878b-c7df-71b0-a14d-b8e18ee05904", "title": "The Importance of Adversarial Evaluations for AI Safety", "url": "https://javirando.com/blog/2024/adaptive/", "published_at": "2024-11-19T00:01:00+00:00" }, { "id": "01a0878b-c7df-71b0-a14d-b8e18f5cbeac", "title": "Do not write that jailbreak paper", "url": "https://javirando.com/blog/2024/jailbreaks/", "published_at": "2024-10-24T00:01:00+00:00" }, { "id": "01a0878b-c7df-71b0-a14d-b8e18f5ef077", "title": "The Worst (But Only) Claude 3 Tokenizer", "url": "https://javirando.com/blog/2024/claude-tokenizer/", "published_at": "2024-03-12T12:01:00+00:00" }, { "id": "01a0878b-c7df-71b0-a14d-b8e18feb54b5", "title": "Universal Jailbreak Backdoors from Poisoned Human Feedback", "url": "https://javirando.com/blog/2024/poisoning-rlhf/", "published_at": "2024-03-08T12:01:00+00:00" } ] posts
Claim your blog
Back to javirando.com
Blog · corpus.blog/blogs/javirando.com/posts
javirando.com
javirando.com
2024
The Importance of Adversarial Evaluations for AI Safety
original ↗
19 Nov 2024
Do not write that jailbreak paper
original ↗
24 Oct 2024
The Worst (But Only) Claude 3 Tokenizer
original ↗
12 Mar 2024
Universal Jailbreak Backdoors from Poisoned Human Feedback
original ↗
8 Mar 2024