I taught myself to code 5 months ago and built an autonomous AI red-team tester — testyourllm.com
Summary
A piano teacher with no coding background taught themselves to code in 5 months and launched testyourllm.com, an autonomous AI red-team tester that attacks any OpenAI-compatible LLM endpoint. The attacking AI, Tron, broke Llama 3.3 70B on the first try in live testing.
Similar Articles
I built an AI that acts without being told to. No frameworks. No prompts. No roles. Here's what I learned.
A developer built LIA, a persistent cognitive ecosystem that achieves genuine autonomy through architectural design (memory, self-generated rules, private domain) rather than prompts, outperforming a standard LLM in the same environment.
@oliviscusAI: OpenAI's co-founder just released his personal guide to train LLMs from scratch. It's called llm.c. No heavy setup. Jus…
OpenAI co-founder Andrej Karpathy released llm.c, an open-source guide to training LLMs from scratch with simple code that runs on any hardware, including CPUs and MacBooks, and is 7% faster than standard approaches.
@VukRosic99: Build LLM in 1 Prompt + Setup Autoresearch By DeepSeek Researcher (his side project) A live build where you create a fu…
Demonstrates building a full LLM using a single prompt to an AI coding agent (Claude Code/Codex) and installing an autonomous AI research skill by a DeepSeek researcher, covering architecture, failure modes, and unattended operation.
I built a local autonomous coding agent with Ollama — fine-tuned soul model, 40-round agentic loop, MiniMax M3 for the heavy lifting
A developer built a local autonomous coding agent using Ollama, combining a fine-tuned personality model (Eve) for conversation and MiniMax M3 for heavy lifting, achieving a 40-round agentic loop with 16 tools and 9/9 tests passing first try.
Build a local AI coding agent from scratch
A step-by-step guide to building a minimal AI coding agent that runs entirely locally using llama.cpp, GGUF models, and a custom harness, demonstrating how to set up tools and call a model to execute real tasks like creating a landing page.