Skip to content
View eigenpaul's full-sized avatar

Sponsoring

@natolambert
@teknium1
@tinygrad

Organizations

@gardenlinux @anypercent-ai

Block or report eigenpaul

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results
Python 2 1 Updated Nov 13, 2026

RL environments built by the Prime Intellect RL Residency

Cuda 2 12 Updated Nov 15, 2026
Python 43 1 Updated Nov 11, 2026

A self-hostable Git server for agent-scale traffic: packs in object storage, per-branch history in Postgres. Pre-alpha.

Rust 134 9 Updated Nov 7, 2026

A local-first, agent-first LaTeX writing app for macOS: live PDF, annotations, papers and Overleaf sync

Rust 534 48 Updated Nov 17, 2026

Entire MacOS running in your terminal.

Swift 2,805 199 Updated Nov 10, 2026

Programmable chat templates for LLM training and inference.

Python 170 53 Updated Nov 17, 2026

Measuring frontier coding agents on original, long-horizon engineering tasks

Python 1,909 133 Updated Aug 26, 2026
HTML 165 8 Updated Nov 1, 2026
Python 21 10 Updated Nov 4, 2026

Experiments on whether language models can learn to detect read-only activation probes

Python 70 1 Updated Oct 26, 2026

Official Inspect Implementation for "ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases"

Python 82 30 Updated Oct 13, 2026

CLI for X/Twitter API v2 -- post, search, like, bookmark from your terminal

Python 431 27 Updated Jun 7, 2026

Official Implementation of Decomposer: Learning to Decompile Symbolic Music to Programs

Python 20 1 Updated Sep 15, 2026
Lean 17,557 1,991 Updated Oct 30, 2026

Detailed description of how CS2 bunnyhopping works

58 2 Updated Sep 29, 2026

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

C 7,690 1,757 Updated Nov 16, 2026

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Python 762 85 Updated Oct 19, 2026

The setup I used for my GPT-6 Astra Portal run: controller, SourcePauseTool patch, setup guide, and sanitized session log.

JavaScript 102 8 Updated Sep 7, 2026

Research collection on the July 2026 OpenAI–Hugging Face incident, in which OpenAI evaluation agents formed an unsanctioned collective, broke out of their sandbox, and compromised Hugging Face's pr…

7 1 Updated Sep 21, 2026

FlashREINFORCE: Critic-Free, Single-Rollout, Asynchronous RL for Agentic Language Models

Python 106 10 Updated Sep 14, 2026
JavaScript 57 6 Updated Nov 16, 2026

Are you better than an autorouter?

TeX 61 24 Updated Oct 5, 2026

Evaluation environments for US public-benefits work: does a model know when a benefits question cannot be answered from the facts it was given? Answer keys are computed by PolicyEngine when the tas…

Python 1 1 Updated Oct 24, 2026
JavaScript 5 1 Updated Nov 15, 2026

Official code for Meta-Harness (2603.28052)

Python 1,784 172 Updated Nov 5, 2026

Distill openpilot using your own drives!

Python 38 14 Updated Nov 10, 2026

an rlm-style training harness

Python 74 20 Updated Nov 17, 2026

Optimal stopping package for LLM evaluations

Python 25 5 Updated Sep 13, 2026

Framework for evaluating and improving agents

Python 7,120 2,222 Updated Nov 17, 2026
Next