Dataset of hackable TerminalBench-style tasks and exploit trajectories
☆53Sep 30, 2026Updated last month
Alternatives and similar repositories for terminal-wrench
Users that are interested in terminal-wrench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Reproducing "Natural Emergent Misalignment from Reward Hacking" (MacDiarmid et al., Anthropic 2025) with open-source models. Includes rew…☆36Oct 5, 2026Updated last month
- ☆47Feb 18, 2026Updated 8 months ago
- Official Inspect Implementation for "ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases"☆79Oct 13, 2026Updated 3 weeks ago
- Benchmarking execution environments ability to prevent reward hacking in agent evals.☆18Oct 12, 2026Updated last month
- Generating, validating and running exploitable verifiable coding problems☆15Sep 30, 2026Updated last month
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆25Nov 11, 2024Updated 2 years ago
- Benchmark dataset for evaluating trusted monitors on AI agent transcripts☆20May 16, 2026Updated 5 months ago
- ☆18Oct 23, 2025Updated last year
- The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away fro…☆182Jan 20, 2026Updated 9 months ago
- ☆13Jan 14, 2026Updated 9 months ago
- A free, research-based vocab web app for beginners of Chinese with Django backend.☆10Feb 19, 2024Updated 2 years ago
- Code for "On the Learnability of Watermarks for Language Models" (ICLR 2024)☆29May 15, 2026Updated 5 months ago
- Harbor dataset for Senior SWE-Bench (v2026.06)☆57Jul 8, 2026Updated 4 months ago
- ☆14Jun 7, 2023Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆13Jul 16, 2026Updated 3 months ago
- This repository contains the code used for the experiments in the paper "Language Models use Lookbacks to Track Beliefs".☆17Mar 14, 2026Updated 7 months ago
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated last year
- 🏝️ Code for our paper: "Privasis: Synthesizing the Largest 'Public' Private Dataset from Scratch"☆16Jul 10, 2026Updated 4 months ago
- /goal port from codex to arbitrary agents and harnesses, opencode, claude code, etc☆12Oct 29, 2026Updated 2 weeks ago
- ☆10Aug 16, 2021Updated 5 years ago
- Zero-dependency local web app for browsing Claude Code session transcripts☆15Updated this week
- FGLA: Fast Generation-Based Gradient Leakage Attacks against Highly Compressed Gradients☆16Mar 17, 2026Updated 7 months ago
- TabLeak: Tabular Data Leakage in Federated Learning☆16Jul 4, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Codebase for paper: "Counterfactual Simulation Training for Chain-of-Thought Faithfulness"☆18Jun 18, 2026Updated 4 months ago
- 这是一个大学四年的cs基础课部分专业课的复习笔记的扫描版备份仓库☆12Jun 29, 2019Updated 7 years ago
- ☆13Aug 31, 2026Updated 2 months ago
- ☆19Nov 4, 2026Updated last week
- Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook☆18Feb 17, 2026Updated 8 months ago
- A fork of openai/miniF2F adapted to Lean 4, with corrections to formalizations and informal descriptions. for human readers.☆15Apr 23, 2026Updated 6 months ago
- An approach to utomatically generating browser environment with verifiable tasks☆76Mar 24, 2026Updated 7 months ago
- Advancing Small and Medium-sized Code Agents.☆17May 29, 2026Updated 5 months ago
- ☆13May 23, 2021Updated 5 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliabilit…☆35Feb 5, 2026Updated 9 months ago
- A compact high-signal benchmark for evaluating frontier agents☆45Aug 3, 2026Updated 3 months ago
- Conditional Mutual Informaation Neural Estimator☆15Oct 23, 2020Updated 6 years ago
- Chrome extension to draw vector icons in chrome source code repository.☆11Aug 10, 2020Updated 6 years ago
- ☆12Oct 2, 2026Updated last month
- 3cb: Catastrophic Cyber Capabilities Benchmarking of Large Language Models☆17Oct 30, 2024Updated 2 years ago
- Code and data for editing model beliefs with SDF and other methods, and for evaluating the depth of the implanted beliefs.☆20Oct 23, 2025Updated last year
Are these results useful?