Official Inspect Implementation for "ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases"
☆79Oct 13, 2026Updated 3 weeks ago
Alternatives and similar repositories for impossiblebench
Users that are interested in impossiblebench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- Reproducing "Natural Emergent Misalignment from Reward Hacking" (MacDiarmid et al., Anthropic 2025) with open-source models. Includes rew…☆36Oct 5, 2026Updated last month
- This repo is the official implementation of “Are Your Agents Upward Deceivers?”. The paper is accepted by ICML 2026.☆24Dec 15, 2025Updated 10 months ago
- [NeurIPS 2026 🏆 Oral] AgentAbstain: Systematic Evaluation Framework of Agentic Abstention☆23Sep 28, 2026Updated last month
- Dataset of hackable TerminalBench-style tasks and exploit trajectories☆53Sep 30, 2026Updated last month
- 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.
- ☆31Jan 7, 2026Updated 10 months ago
- Easily deploy my zsh and tmux configuration on new machines. Includes local and remote aliases to improve workflow.☆16Apr 23, 2026Updated 6 months ago
- Sandbox escape benchmark for LLM capability evaluation☆14Apr 29, 2026Updated 6 months ago
- ☆17May 21, 2026Updated 5 months ago
- Official Repo for the paper "SecPO: Principled Adversarial Training for Prompt Injection Security"☆14Nov 5, 2026Updated last week
- [ICML2026] Official JAX code for Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying☆17Oct 17, 2026Updated 3 weeks ago
- ☆67Jul 4, 2025Updated last year
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆24Jul 2, 2026Updated 4 months ago
- cheatbench.ai☆20Oct 28, 2026Updated 2 weeks 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.
- Async RLVR training that never gives up (with probability p) on hard prompts☆19Oct 7, 2026Updated last month
- ☆13Jan 31, 2025Updated last year
- Repo for the paper "Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks".☆75Jun 11, 2026Updated 5 months ago
- [NeurIPS 2026 Meta-Agents] PostTrainBench⁰ — Can LLM agents automate LLM post-training without gradients?☆17Sep 4, 2026Updated 2 months ago
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆20Oct 11, 2024Updated 2 years ago
- Benchmarking Dark Patterns in LLMs (ICLR 2025)☆20Mar 29, 2025Updated last year
- Monitoring the health of ARR☆33Oct 23, 2026Updated 2 weeks ago
- ☆15Dec 4, 2024Updated last year
- Replication of the MNIST experiments from paper **RL's Razor: Why Online Reinforcement Learning Forgets Less**☆14Mar 10, 2026Updated 8 months 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.
- ☆16Oct 13, 2025Updated last year
- ☆19Nov 4, 2026Updated last week
- [NeurIPS 2026 Pre-to-Post] From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space☆20Apr 16, 2026Updated 6 months ago
- A research workbench for developing and testing attacks against large language models, with a focus on prompt injection vulnerabilities a…☆63Jul 24, 2026Updated 3 months ago
- [ICML 2025 Poster] SAE-V: Interpreting Multimodal Models for Enhanced Alignment☆18Jun 5, 2025Updated last year
- [ICLR 2023] Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classifi…☆25Aug 18, 2026Updated 2 months ago
- [NeurIPS'25] Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders☆16May 28, 2025Updated last year
- [CCS 2026] The official implementation of our CCS 2026 paper "ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathological…☆19Aug 5, 2026Updated 3 months ago
- ☆34Nov 11, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Small Reward Models via Backward Inference, EMNLP 2026☆24May 25, 2026Updated 5 months ago
- Codebase for Temporal SAEs paper☆28Nov 14, 2025Updated 11 months ago
- Jailbreak Evo☆24Jun 2, 2025Updated last year
- ☆19Jun 3, 2026Updated 5 months ago
- Improving Alignment and Robustness with Circuit Breakers☆271Sep 24, 2024Updated 2 years ago
- ☆72Mar 18, 2026Updated 7 months ago
- ☆13Jun 4, 2025Updated last year
Are these results useful?