Pinned
@kiki_morozova's Black Hat Europe talk on our image scaling research is on YouTube now! If you liked Anamorpher, check it out for more cool image preprocessing exploits-- plus some fun audio ones too!
Suha
@suhackerr
Disclaimer: The views expressed here are solely my own and do not reflect the views of my employer or any organization I am or was affiliated with
Joined August 2017
- this works well. i also really like asking it to write in the style of martin kleppmann or hillel wayne for more conceptual docsYou can get LLMs to write good non-AI-slop-sounding technical documentation by requiring them to adhere to ADS-STE100 Simplified Technical English
- thanks opus 4.8 lol! this is a cute way to theorize about what is and is not in the data for different models.I made it into the weights of Opus 4.8! just barely. and maybe Grok. I am at best the 9th most famous Jack Morris on the public internet. such a cool website: intheweights.com
- New post! Embedding reversal is one of the most practical yet underexplored attacks against modern AI systems. Check out our blog post where we break down what the research shows, why it matters, and how we approach defense at scale here.Embeddings power how Harvey retrieves and reasons, but emerging research shows they can be reversed to expose underlying text. We’ve engineered controls to stay ahead of that risk. Read how: harvey.ai/blog/how-harve… @suhackerr
- !!!!!! i wish cursor/cc for auditing was more of a thing !!!!!!"AI code review" should be about teaching people how the code works, not just verifying that it's correct We can now generate essays, diagrams, and explorable explanations on demand!! Why are we still reading raw code diffs as the primary UI?
