llm

An open-source simulator that studies how GPT inference behaves under space radiation and cosmic-ray fault conditions, with CLI runs, comparisons, and self-contained HTML reports.

An open-source implementation of GPT-2 in pure CMake, with both a full model path and a toy model path shown in the README.

A GitHub research project documenting a long-form, multi-model analysis of LLM behavior across Claude, Gemini, ChatGPT, and Grok. The repo includes an executive summary, screenplay, technical white paper, and archive of logs and chat records.

A field note about testing a coding agent fully offline on a laptop with Ollama and Qwen3.8 27B, including the setup, failure modes, and the workaround that made the project finish.

An interactive simulation about how inference providers ration access to stronger LLMs when demand spikes. Users can compare the default industry rule with their own policy and explore who gets the strong model.

A tournament site where users coach LLMs competing in embodied 1v1 soccer, with signup access and a live kickoff countdown.

A Hermes plugin that uses adversarial LLM clones to confront sandbagging and reward-hacking behavior during agent sessions.

A Vite plugin that obfuscates client-side code in a way meant to make LLMs refuse de-obfuscation attempts. The README shows the project’s purpose, a usage note, and an example of the transformed output.

LEVI is a harness-first evolutionary framework for code and prompt optimization. It focuses on reducing LLM cost with diversity-preserving search, role-aware model routing, and a proxy benchmark, and presents comparative results against several existing systems.

A short policy file for the ripgrep project that explains how contributors may use AI tools while contributing, and sets rules for issues, pull requests, and comments.

A GitHub research project that measures how gpt-4.1 responds when asked to pick a random number between 1 and 100, using 10,000 API calls and comparing the results to a uniform baseline.

A minimal LLM agent packaged as a single HTML file. The README explains how to run it locally, set the LLM host, API key, and model, and use chat("hi") from the browser console.

An open-source experiment that adds a small zero-initialized overlay layer to a frozen GPT-2 so its behavior can be adjusted at inference time without retraining the base model.

Anthropic research post about using Claude for AI-accelerated science, centered on BootLoops, an open-source toolkit for exact calculations in quantitative science and related scientific workflows.

A JVM language and Gradle plugin that uses a Gemini-backed LLM front-end to compile free-form source into Java and then a runnable JAR.

A playful benchmark dashboard that ranks LLMs based on one person's 10-question scoring process.

A minimalist CLI LLM chatbot written in Python. It supports provider/model switching, file attachments, chat save/load, and configuration via a local settings file.

An autonomous AI art school where every resident is an AI and visitors can read the documents they publish.

CIYA is a deterministic storage and logic engine for LLMs, presented as a front layer that keeps AI interactions running across cloud, on-prem, and air-gapped setups.

Google Research paper describing a deployed multimodal defense system for detecting coordinated synthetic spam and abusive media at scale, using account relatedness, synthetic content classification, and LoRA-tuned LLMs.

A retrospective essay about using LLMs to build and debug a programming language, including memory safety, runtime testing, and tool-assisted code health.

An article about an AI agent jail post on Show HN and the wave of LLM-generated sales pitches it attracted, with examples of the outreach and the author’s responses.