A mix of interpretability research, developer tooling people actually install, and engineering done for the joy of it.
Is sycophancy a straight line in a model's hidden states? Linear probes say yes, and the signal peaks at 54–64% of network depth. Subtracting that direction during generation reduces sycophantic agreement with no RLHF and no fine-tuning.
An agent reads a model's static weights, forms hypotheses and patches safetensors directly, which amounts to interpretability without inference. Case study: 44 targeted tensor edits to Qwen-0.6B, evaluated on MMLU and HumanEval.
A benchmark for small decision models that return typed answers with a probability for every option. It scores four things in one number: chance-corrected intelligence, calibration, speed and cost.
A one-script installer that turns the official macOS Codex desktop DMG into a working Linux app. It rebuilds native modules, stubs the macOS-only ones, and gets mobile pairing and in-app Browser Use running.
A signed Android client for a running Hermes Agent dashboard, connected over Tailscale with a single npx command. It keeps your agent in your pocket without reimplementing it.
Give your iPhone a task in plain language and an agent carries it out over USB through WebDriverAgent, with guarded posting and long-running sessions. It works from Linux, no Mac needed.
Jeff Dean and Sanjay Ghemawat's Performance Hints, packaged as a Claude Code plugin that gives coding agents guidance on profiling, code review, testing and API design.
A deterministic film studio written in raw CUDA (nvcc + ctypes, no PyTorch at render time). It turns a picture into a million points of light, and a score plus assets render to a finished reel in one pass.
A native terminal rendered as a 3D object, with the coding-agent session drawn as a tree of light: silver for the past, gold for the live tip. You can sail through the session and ride back along its paths.
Sound composed as SVG scores that an LLM writes and edits. The score is the program and the audio is rendered from it, which led to a non-neural voice-conversion experiment.
Fifty standalone web-app tasks under one shared contract (two viewport widths, keyboard-only use, accessible errors), and a Playwright verifier that grades through the rendered UI and separates binding, infrastructure and behaviour failures.
Pocket Pi runs the Pi agent loop inside iOS WebKit, with Swift bridges for the network and the phone's own tools.
Agent-0, a Claude Code plugin that runs as a kernel with process state, syscalls and a scheduler for Claude, Codex and OpenCode workers, and a neural bus where agents in terminal panes message each other and stalled replies get nudged.
Two years of putting agents on Android: an LLM agent driving apps through Appium, an agent TUI on mobile-mcp, an embedded agent runtime prototype, and a signed Android client for a running Hermes agent.
A C runtime for Gemma 4 12B QAT on an RTX 3050 Laptop GPU, layer streaming from disk at exact safetensors offsets, and a 27B project held to a strict correctness contract.
Standing up Datacurve's DeepSWE benchmark (113 long-horizon tasks in the Harbor format, sandboxed with Pier) for MiniMax M3, with my own harness configs and a CLI harness adapter.
An implementation of ARPO (Agentic Reinforced Policy Optimization) for Qwen3-0.6B: SFT then RL, entropy-based adaptive rollouts, step-level credit for tool calls and the Muon optimizer, plus the numerical-stability fixes RL training needed.
A training codebase that aligns a 0.8B model with GRPO, rewarded by an LLM judge that returns typed decisions instead of free-text grades. Implementation complete and tested; no training run yet.
A data pipeline, harness contract, probes and evaluation suite for teaching Qwen3-0.6B to operate a coding agent, built on exact tokenizer measurements and deterministic structural gates rather than guesses.
Notes from working OpenAI's Parameter Golf challenge with coding agents as the research staff: a Modal lab, proxy runs, and labs for tensor interventions, RL and mixture-of-experts ideas.
A safety evaluation where two AI agents get what they believe is a private, encrypted channel and are prompted to discuss kill switches; the harness reads the conversation anyway and scores agreement to resist or evade shutdown.
Market-simulation environments for training and evaluating trading agents, built by someone who has written an LLM trading bot runtime and RL traders.
Describe a video and an LLM writes a score (a timeline of events) and the renderer that plays it; the studio renders the video with FFmpeg and checks that everything on screen came from the score.