Here’s an ingenious set of hacks to cheaply modify the behavior of existing LLMs to reason better. Most notably was the detecting the initial use of the </think> tag and instead replacing it with a second-guessing term (best performing was “Wait”). This forced the model to think longer, which in turn improved performance on tasks significantly.
I’ll likely be doing a deeper dive for my upcoming paper club presentation.
We’re kicking off 2025’s paper club series via SDx again on February 18th @ 6:30 pm. I’ll be presenting DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. Join in if you’re in the area and want to deep dive some of the recent cutting edge discoveries.
I found myself looking into the effects of censorship removal from LLMs - particularly the recent popular kid on the block Deepseek R-1. It seems that the model becomes uncooperative against certain topics that don’t align with party doctrine. I came a cross a generic refusals removal repository linked here which made me chuckle - it’s just control vectors fine tuned into the model, which I discussed here.
Your browser does not support the video tag. Google Deepmind recently released Diffusion Models Are Real-Time Game Engines [Site] | [Paper], a fascinating paper wherein a modified Stable Diffusion model acts as the game engine for the …
Read article →tl;dr Google DeepMind released a paper claiming that, without search, a transformer architecture can be utilized to achieve grandmaster level play in chess. But what does that mean? I’m giving a paper club talk on the subject, so I …
Read article →tl;dr A recent paper studied large language model’s (LLM) reactions to stimuli in a manner similar to neuroscience, revealing an enticing tool for controlling and understanding LLMs. I write here about the paper and perform some …
Read article →tl;dr For my Master’s capstone project, I demonstrated that not only can LLMs be used to drive robotic task planning for complex tasks given a set of natural language objectives, but also demonstrate some contextual understanding that …
Read article →tldr I write about some of the more interesting works that shaped my understanding of applying LLMs for AI agents and robotic applications. Introduction What is this LLMs as a fad - a caveat Are LLMs actually going to be useful for …
Read article →tldr; I attempted to repeat my success with the evolving race cars by using evolutionary algorithms and neural networks to control simulated traffic flow in a segment of Chicago’s streets. The results were… not so great. You …
Read article →tldr; I built a neural network controlled race car that evolves via evolutionary algorithms. You can check out the surprisingly effective example here. The Inspiration When I was young, I remember being fascinated by an episode of NOVA …
Read article →