Top postsTop post
Brendan Long
Message
I write a blog: https://www.brendanlong.com/pages/about-me.html
I made an RSS/read-later app: https://lionreader.com/demo/all?entry=welcome
I'm trying to get into technical AI safety work.
4927
55
1097
In the recent OpenAI hacking incident, the models seemed to be single-mindedly focused on getting the correct answer to the task they were given, with no long-term plan to prevent getting caught by OpenAI afterwards[1]. This makes sense to me, since in training, getting the right answer is reinforced and...
LLMs learn faster if we first pretrain them to imitate dense teacher-forced examples. I speculated that this would work on humans too, so I built a chess app where you try to imitate Stockfish. My theory is that this will help humans quickly become OK at chess, but they will...
Exercise is hard but it's even harder if you have to use your brain and muscles at the same time. I wish a personal trainer would just teleport into my house whenever I work out, tell me exactly what to do, and then record my progress (and complaints) to improve...
Instead of using static position increments (+1) per token, RoPE-based language models can learn per-token and per-layer position increments. This has minimal effect on model performance but allows us to see what the model thinks the distance is between each position and how this varies per-layer. Example sentence with each...
I'm working on an experiment comparing the internal representations of two architectures when solving a sequential algorithm, but training models to use a sequential algorithm is surprisingly hard. The optimization landscape makes it easier for models to learn parallel algorithms or memorize lookup tables, so I needed to make some...
I've been working on two fairly large vibe-coded apps, and my process has converged on: 1. Write a GitHub issue 2. (If complicated enough) tell an agent to make a plan and then update the issue 3. Have another agent read the issue and implement it As the features get...
LessWrong's RSS feed includes all recently published articles by default, but it has a bunch of undocumented features available with query params. Warning: The only officially supported options are view=frontpage, view=curated, and karmaThreshold. Other options may break in the future. * You can request only posts above a certain karma...