Articles and feed posts from Keith Chester on AI, robotics, and software development
I find myself unreasonably excited for the work that Taalas is doing. They’re turning open weight models directly into ASICs (application specific integrated circuits) so that the chip essentially acts as the model - and only as the model. You get raw transistor switching speed within the model. Not only does this result in incredibly fast computation (~15k tokens a second for llama 8b!) but…
I just gave a talk at DEVx giving a very early alpha preview of poprocks, a module providing simple golang primitives for building and working with Firecracker microvms. While it can be used serverside, I talk about utilizing it instead as a client side solution for isolated, malicious actor “safe” execution environments - especially for AI agents.
Coding agents are amazing - sure. I’m a fan and heavy user of them too, especially CLI agents. BUT - the existing coding subscriptions heavily discount token usage, to the point that most users are unaware of just how many tokens they are actually burning at any given moment to run their agents. This blissful ignorance is perfectly fine as long as the discounsts continue; the pain of running…
For the past few months I’ve been working for the ARC Prize - a non profit organization built around the idea of an Abstract and Reasoning Corpus - a set of reasoning games that are easy for humans to quickly and efficiently figure out, play, and solve - but near impossible for even the most cutting edge models. [Paper] …and today we officially launched the beta of our toolkit and…
Just released threadsafe_datastore, a simple, convenient thread-safe data store for Python. I kept rebuilding this feature to pass around context within AI agents working on the same data across multiple threads. I kept wanting a simple atomic datastore that was convenient to work with. I originally built it for arkaine | git |. So - here it is as a stand alone package for easier use. I also…
Right off the bat I had users asking for salary negotiation as a feature on HiredCoach. Apparently I’m not the only one that dreads the process of asking for more money and the tension the conversation can have. It’s live now. I went from idea to prototype in about a day, and only a few more days for the feature to be 99% there. I definitely can think of a few things I’d like to…
About five years ago (ok, that hurt to type. The days are long but the years are short…) I wrote SafeStop. I had made it to coordinate proper shutdown protocols across multiple services running in a large monolith application. I decided to renew it, modernize it, and added some dependency features (so service B can shutdown after service A is shutdown, etc). Another product of my recent…
I’ve long been a fan of task runners within projects - I find they’re practically required once you have a project or group operating beyond a certain level of complexity. There are just too many one liner terminal commands to memorize, too many differing syntaxes across dozens of tools operating across different stacks… it’s madness. Typically engineers (at least the ones…
Just released structured-parse, a multi-language parser for block labeled LLM output. It’s based on the parser I had built for arkaine. Here’s what I mean by “block labeleled” output: Thought: I need to search for information about robots Action: search Action Input: {"query": "robots and why they're so cool", "max_results": 5} This output is not only more human readable,…
Just pushed a pretty significant update to docker-harness. It was a tool I created originally to power some of my Docker containerized database tests. I pulled out the dependencies for each database to modularize it a bit. Each database module (MySQL, PostgreSQL, Redis, Memcached) now has its own go.mod and go.sum, which means you only pull in the dependencies for the databases you actually need.…
Recently I took on a contract job to fill the coffers a bit while HiredCoach handles its initial launch. Nothing that I can talk that much about publicly, but I can reveal that it’s your typical AI office assistant for a particular business process. As specific as it is exciting a description, I’m sure. Given that I recently wrote an entire article about the highs and lows of my custom…
tl;dr I talk about the ideas behind and efforts expended to build my AI framework, arkaine. What worked? What didn’t? Does it have a future? arkaine, briefly I decided a few months ago to create an AI framework for making agents. I use that term loosely because the actual definition changes based on what your focus is, what level of understanding of the inner workings of these models are,…
If I had the budget/compute power and time to research anything at the moment, this is what I would try researching. It’ll make sense in a bit, I swear. The Problem Training robotic policies to perform complex tasks is incredibly difficult. We have some success with generalist policies and existing reinforcement learning research, but they typically have limits on what they can accomplish.…
tldr; A paper caught my eye, proposing a way to treat individual agent calls in multi-turn agent training as individual steps. The key contribution - an easy, intuitive method of assigning credit to each step, for quicker training. [Paper] | [Slides] | [Video] Introduction A paper - Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Credit Assignment - caught my eye, prompting me to…
I recently gave a talk on DeepSeek V3 training improvements and the fascinating ideas behind GRM and SPCT. The talk took awhile to get posted, so here it is! Be sure to checkout the blogpost as well for a bit more on GRM and SPCT.
It’s certaintly a fascinating time for robotics. I am generally pessimistic of the current state, and likely fates, of much of the current landscape of the robotics industry, but it is undeniable we are rapidly unlocking new capabilities and research is flying forward. This talk acts as an excellent high level overview of the key innovations to our approach of utilizing reinforcement…
I’ve seen dozens and dozens of open source robotic arm projects; probably because of my own addiction to mechanical automatons paired with my unending desire (despite a lack of need) for a robotic arm of my own. This one caught my eye however as it has a particularly clever accessory method without the need to of a complex end effector tool changer. If they can route power/data control…
As I’ve mentioned before, I’ve been trying to learn to draw lately, initially inspired by a desire to be able to properly convey the headaches with pictures in my head to on-paper representations. Plus I’m eager to increase my practice in visualizatio nand intuition. But drawing references tend to be oriented towards the more popular subjects of nature, people, animals. Very few…
Recently, I gave a talk on several of DeepSeek’s innovations, which were as extensive as they were complicated. The particular clever discovery that best captured my imagination was their development of GRM and SPCT. Most AI models — be they “simply” instruction-based or reasoning — tend to focus on coding or mathematics domains. This makes sense; when training you need to…
Currently I’m going through the struggles of learning to draw from a very poor foundation of sub-stick figure talent and primarily spurred on by the desire to convert the vague ideas in my head to actual designed physical objects, this video spoke to me. The creator walks through the creaton of his clay making set, all to allow him to shape tiny, organic shapes that he can then photograph to…
Back when I was working on coppermind at the heyday of GPT3.5’s initial world shattering release, I had… difficulty finding good ways to deal with parsing the stochastic LLM outputs. I got better at this when I started work on arkaine, eventually developing a pretty useful and reliable parsing pattern. With an idea that would be best served as a golang app requiring interacting with…
Did some work on eli5equation, cleaning up and fully deploying prior one day project. We’ll see if people find it useful. I find it super useful when tackling new AI papers. I also gave it a bit of a glowup too. And yeah, still powered by arkaine.
I have been busy due to a flood of inspiration to work on projects. Pleasant, but also exhausting. The only updates to arkaine has been to fix an issue with default arguments in the ParallelList flow tool. The reason for the freeze in development is an accidental startup. How does one go “oops, I made a startup?” Basically, I decided to quickly develop a series of simple apps that…
Given my recent weekend foray into Replit, I wanted to try a simple solo project to “kick the wheels” and test drive Replit a bit more. It took about 2 hours from idea conception to deployed product with integrated DeepSeek AI - not too bad! reflecta is a simple journal prompting app (trying to avoid overly cheesey prompts at that) that allows you to specify categories to focus on, and…
This past weekend I participated in the Replit Hackathon held by SDx. It was a fun event. It may seem odd trying my hand at vibe coding, given its weird hype and counter culture built around it, and the fact that I am a skilled and experienced developer. I wanted to explore it, see what the tools and workflow was like, learn what is possible without my traditional approach to problems.
I am a reserved and ultimately shy individual, dealing with his own life is a way that best suits me. Recently, however, I have found a way, however small, to provide my own resistance with my skillset and resources. SciOp is a movement to backup government datasets and sights as they are targeted and removed for not toeing the party line. Since I have plenty of open space on my NAS, I’m…
I’ve long since embraced AI integrations into my AI, and I’ve experimented with several of the new app builders. I’m going to avoid commenting on the “vibe” coding meme that’s going on, I will say I’ve enjoyed some of the efficiencies gained. A few months ago per the suggestion of several peers I swapped from VS Code w/ Copilot to Cursor. It took some…
DeepSeek released another cool paper expanding on reinforcement learning for LLM alignment. Building off of their prior work (which I talk about here), they introduce two new methods. The first - Rejective Fine-Tuning (RFT) - They have a pre-trained model produce N responses. Then the collected responses are combined in a prompt wherein the model is instructed to produce principles for evaluating…
One of the great parts of building out tools like arkaine is that it allows me to sit down and just build for a bit to test the framework. After some quick experimentation I have a great agent that: Takes in a resume and a job description Considers additional topics to research to build out a knowledge base of what certain acroynms, skills, and technologies mean, and what are industry standards…
Version 0.0.21 of arkaine is out, including the finalized format for the text to speech tooling, equivalent speech to text tooling (though, admittingly, I currently lack a locally hosted option for this), and the think tool I mentioned earlier. There’s still a lot of features that I want to add, and some I’m in the middle of; adding a chat interface to Spellbook and expanding the…
I simply love when simple ideas get tested and proven to be quite effective. It’s a clear sign of slowly feeling out how to best understand the system at hand. Such a delight popped up when I saw that Anthropic had revealed that simply adding a no-op tool with a “thought” argument called “think”, allowing the agent to just output its thought in the chain of Action ->…
Inspired by OpenAI’s newest text to speech models, I decided to finally take a crack at text to speech on arkaine. To that end, I published 0.0.20 of arkaine with a beta build of text to speech tools, support OpenAI, Google, and Kokoro for local execution. Check them out in the toolbox!
My framework arkaine, which I quickly presented a bit ago, finally has some nice documentation for it. I had v0 do an initial pass on it, which I rather liked. After two quick rounds of prompting on their free tier I downloaded the project and tried my hand at expanding it from there. It’s my first tailwind/next.js project, but it was surprisingly easy. Granted it’s a simple page…
The paper club I host will be covering BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks! I’ve been looking forward to this one since I read the original paper on 1.58 bit nets. Join us and learn about the future of trinary and LLMs!
I picked up David Bessis' Mathematica on a whim. It focused on a discussion of what math truly was to one accomplished in it, and how the public’s understanding of what mathematicians do is wildly, grossly inaccurate. The book’s premise: language is a poor medium for transmission of intuition itself, whereas math and logical proofs are overkill but required to express it. Mathematics,…
tldr I recently gave a talk at the SDx paper club which I run on the paper DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. I wanted to take a moment to blog out some of the talk, specifically how their reinforcement learning approach worked. The recording the day of failed, so this is a rerecording the next morning. Above is the talk (and here’s the…
Last night Adam gave a great presentation at the SDx paper club. The idea of using ODE solvers as an activation function was 🤯. It’s heavily used in robotics, so I’ll likely be doing a deep dive at some point; specifically building a neuron that uses the paper’s techniques to better understand the inner workings.
A few weeks ago I gave a talk at an SDx paper club covering the DeepSeek R1 Paper. I talked in depth about the advancements made and the implications of their success with GRPO (group relative policy optimization) powered reinforcement learning. The recording at the event borked so I re-recorded it the next day. Enjoy!
I’ve been working on arkaine’s OCr service all weekend, and need a break. I’ve been toying with the idea of an equation explainer that copies the style I present complicated math in my paper club presentations. I’ve decided to step away from arkaine and try using it a bit in a prototype. Hence: eli5-equations. Want to get a walk through of a complicated equation? Pass it in…
Today I attended a mini-hackathon via SDx. I attended to solo work on some arkaine agents and to be present as a mentor/advisory role for other attendees. It was a short 6 hour affair, mainly focused on playing with the new OpenAI o3-mini. It also helps to be inspired by seeing other people creatively applying AI to a quick weekend project. I ended up building a great prototype of a research agent…
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…
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,…
I recently gave (an unfortunately rushed) talk about arkaine - a maker-focused agentic AI framework I’ve been spending most of my time building. Slides for the talk are 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 classic game of DOOM. Player actions are fed directly into the model (which they called GameNGen), which outputs a generated image of the next frame 20 times a…
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 decided to write up my own analysis of the paper. [Paper] | [Code] | [My Slides] Chess Without* Search This paper got a fair amount of press, but it seems that…
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 experiments to see if they work. Cool Experiments | Site | Paper | Code A Change of Perspective Representation Engineering Baselines Reading Vectors Control Vectors…
tl;dr I got nerd sniped by a problem and wrote a solver for it. You can find it here. The Problem Apparently it’s impossible to determine if someone is capable of coding without asking them arbitrary puzzles that are in no way related to a realistic job. Resumes and previous job experience are so passe - puzzles are where it’s at. I received one of these coding challenges - given a…
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 goes beyond information known about the world state. Just want to see the result? Jump to here. Just the code? Here. Introduction ROS2 the Robot ROS2 litterbug…
Melvin Conway has a law that I’ve heard thrown about throughout my career building applications and backend systems. Verbatim it states: Organizations which design systems are constrained to produce designs which are copies of the communication structures of these organizations. Or, put simpler - your system/product/service/software reflects the organization of teams interacting with and…