anthropics / sycophancy-to-subterfuge-paperLinks
☆23Updated 9 months ago
Alternatives and similar repositories for sycophancy-to-subterfuge-paper
Users that are interested in sycophancy-to-subterfuge-paper are comparing it to the libraries listed below
Sorting:
- ☆87Updated 2 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆70Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆27Updated last year
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆12Updated 2 years ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆108Updated last year
- An attribution library for LLMs☆41Updated 9 months ago
- ☆29Updated 10 months ago
- ☆28Updated last year
- Measuring the situational awareness of language models☆35Updated last year
- Functional Benchmarks and the Reasoning Gap☆87Updated 8 months ago
- ☆98Updated 3 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆96Updated this week
- ☆134Updated 2 months ago
- Public Inflection Benchmarks☆68Updated last year
- ☆61Updated 3 weeks ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆109Updated last year
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 4 months ago
- Sparse Autoencoder Training Library☆52Updated last month
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆58Updated 6 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆81Updated last year
- Open source interpretability artefacts for R1.☆149Updated 2 months ago
- ☆134Updated 7 months ago
- Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.☆22Updated last year
- A dataset of alignment research and code to reproduce it☆77Updated 2 years ago
- SWE Arena☆34Updated 2 months ago
- Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"☆51Updated 4 months ago
- Just a bunch of benchmark logs for different LLMs☆119Updated 10 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆148Updated 4 months ago
- Harness used to benchmark aider against SWE Bench benchmarks☆72Updated last year