https://github.com/ExpressGradient/lazarus
I have been interested in long-horizon coding tasks for a while, especially with benchmarks like FrontierSWE, where even the best coding agents like Codex and Claude Code struggle to complete tasks.These agents come with a collection of tools like bash, file edits, grep, glob, etc.Lazarus takes a different approach. The idea is to give the model exactly one tool: a persistent Python...
https://github.com/ExpressGradient/modal-cuda
I use a MacBook (no NVIDIA GPU) but still like experimenting with CUDA kernels.I didn’t want to spin up a VM every time or use browser-only tools, so I built a tiny CLI that runs local .cu files on Modal GPUs with a single command.Modal gives around $30 in free credits when you sign up, so the CLI is built around that. You can run simple kernels on smaller GPUs (like T4) for very little. I ran...
https://github.com/Think-a-Tron/elliot
Built a coding agent that's actually useful for working with existing codebases - the kind where you need to understand structure, not just append code.Key capabilities:- Structural code search via ast-grep: Searches by AST patterns, not text. Finds all implementations of an interface, all callers of a function, etc. Treats code as structure.- Planning before execution: Writes a plan, ticks off...
i speak in thoughts in my head and it is better to just translate those thoughts to code directly.
putting them into a language for LLMs to make sense and understanding the output is oof... too much overhead. and yeah the micromanagement, correcting mistakes, miscommunications, its shit
i just code like the old days and if i need any assistance, i use chatgpt
The LLM (GPT-4.1) suggests small code changes to improve compression ratio. Mutations are applied and tested on a real input file (big.txt). If the round-trip decompress fails, it's discarded. Everything is logged in a local SQLite DB.
Selection is dumb but effective: top 3 elites + 2 random survivors per generation. Each spawns 4 children. Repeat for N generations or until stagnation. At around 30 generations, I hit a compression ratio of 1.85×. Still decent, considering the starting baseline.
It's not a framework, it's not Pareto, and there's no multi-objective fluff. Just a tiny search loop hacking away at code. Curious if others have tried something similar with code-evolving setups.
https://github.com/Think-a-Tron/zeno
With TRL, it's now straightforward to RL-finetune LLMs, but picking good reward functions is still the weakest link.Zeno is an open-source toolkit for verifiable, deterministic reward functions for RL on LLMs.While the initial release focuses on Python code generation, the goal is broader: make RL reward design for LLMs transparent, modular, and extendable across domains (math, retrieval,...
Everyone saw the AlphaEvolve hype. I got obsessed with how it might work under the hood and decided to just build it myself.My setup uses GPT-4.1 to mutate matrix multiplication code, guided by a bunch of hand-crafted mutation strategies (loop reordering, tiling, Strassen, etc.). Each candidate is evaluated on both speed and accuracy. Then I apply Pareto selection with crowding distance to...
https://huggingface.co/think-a-tron/raman-01-1.7B
I built a tiny physics solver LLM that performs surprisingly well on easy-to-medium difficulty physics problems. Most LLMs today still struggle with physics QA (as PhyBench recently highlighted), so I wanted to see how far I could push a small model with careful data and minimal compute.Model: Qwen3-1.7BSupervised Finetuning: ~1500 curated examples spanning kinematics, EM, acoustics, and moreRL...
i've been talking to chatgpt about rl and grpo especially in about 10-12 chats, opened a new chat, and suddenly it starts to hallucinate (it said grpo is generalized relativistic policy optimization, when i spoke to it about group relative policy optimization)
reran the same prompt with web search, it then said goods receipt purchase order.
absolute close the laptop and throw it out of the window moment.
what is the point of having "memory"?
https://v0-ai-debate.vercel.app/
Just launched AI Agents Debate Arena – a battleground where OpenAI’s GPT-4o and DeepSeek’s V3 go head-to-head in real-time debates! Users can either pick from AI-suggested topics or enter a custom challenge and watch the models argue their cases. Built using V0, this project explores how different LLMs handle reasoning, persuasion, and counterarguments. Who makes the stronger case? Test it out...
I created a classic text-based adventure game inspired by Zork using Vercel's v0. Each refresh generates a unique game title, setting, and context, with AI handling the dynamic storytelling and gameplay. It features a retro terminal-style UI, simple text commands, and endless possibilities for exploration. Check it out and let me know what you think: https://uj0gnt8ewsnqdwnf.vercel.app/
i just typed the objective, it solved the game, stupid openai
fixing it
check it out here: https://awng08bk1cxj8ydx.vercel.app/
https://piliwtfcobjhsczp.vercel.app/
I created a classic text-based adventure game inspired by Zork using Vercel's v0. Each refresh generates a unique game title, setting, and context, with AI handling the dynamic storytelling and gameplay. It features a retro terminal-style UI, simple text commands, and endless possibilities for exploration.