invariantlabs-ai / invariant
A trace analysis tool for AI agents.
☆124Updated last month
Related projects ⓘ
Alternatives and complementary repositories for invariant
- Red-Teaming Language Models with DSPy☆142Updated 7 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆63Updated this week
- Sphynx Hallucination Induction☆48Updated 3 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆107Updated 8 months ago
- ☆63Updated this week
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆220Updated 2 months ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆86Updated 5 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆84Updated 8 months ago
- Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.☆103Updated this week
- Improving Alignment and Robustness with Circuit Breakers☆154Updated last month
- Synthetic Data for LLM Fine-Tuning☆97Updated 11 months ago
- ☆101Updated 3 months ago
- Thorn in a HaizeStack test for evaluating long-context adversarial robustness.☆26Updated 3 months ago
- ☆34Updated 3 months ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆107Updated 5 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆65Updated this week
- AWM: Agent Workflow Memory☆208Updated last month
- Fiddler Auditor is a tool to evaluate language models.☆171Updated 8 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆128Updated 3 weeks ago
- Attribute (or cite) statements generated by LLMs back to in-context information.☆147Updated last month
- Dataset for the Tensor Trust project☆33Updated 8 months ago
- Code for the paper 🌳 Tree Search for Language Model Agents☆140Updated 3 months ago
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents☆110Updated 5 months ago
- Automatic Evals for Instruction-Tuned Models☆45Updated this week
- Functional Benchmarks and the Reasoning Gap☆78Updated last month
- ☆128Updated this week
- ☆81Updated 4 months ago
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆115Updated 8 months ago
- Commit0: Library Generation from Scratch☆97Updated this week
- 🤖 Headless IDE for AI agents☆133Updated this week