logicallee

↗ HN profile [ 72.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. I am currently generating a substantial amount of code with Claude Code. I also pay for ChatGPT Pro. I am thinking of having ChatGPT's codex review Claude's code. Do any of you do anything like that? What are your…

  2. I thought an interesting flex would be fine-tuning Gemma 4 (Google's latest offline model, released Friday) to talk like a pirate. Voila! (demo is at the 4 minute mark): https://www.youtube.com/live/WuCxWJhrkIM I looked…

  3. I'd love to hear where you've run into the limits of current coding models, whether it's based on lines of code, systems integration, databases, etc.

  4. I wanted to leave this post (these couple of paragraphs) as an artifact of our process in working toward a full SHA-256 collision. After publishing our results yesterday, we continued the work we started. The next step…

  5. I'm not sure why the stream quality is so low, I spent a while selecting 4k. I'm able to make out the text and you should be able to as well. This stream will run for about 24 hours or so. You can see the collision of…

  6. I am curious about the state of prompt injection attacks on frontier models. Are they still vulnerable? For example, is it safe to let Claude Code look at user-submitted data if it also helps manage some of the…

  7. Here on Hacker News some time ago (like years ago) I saw a link to criticism of something that became an Internet standard, the format of the link was either text or a picture of text. It was a very long time ago, like…