jprivera44 / EscalAItionLinks
Repo for the paper on Escalation Risks of AI systems
☆40Updated last year
Alternatives and similar repositories for EscalAItion
Users that are interested in EscalAItion are comparing it to the libraries listed below
Sorting:
- An OpenAI gym environment to evaluate the ability of LLMs (eg. GPT-4, Claude) in long-horizon reasoning and task planning in dynamic mult…☆68Updated 2 years ago
- Hypothetical Minds is an autonomous LLM-based agent for diverse multi-agent settings, integrating a Theory of Mind module Theory of Mind …☆30Updated 10 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆90Updated 4 months ago
- Demo of using ChatGPT API for language learning☆12Updated 2 years ago
- ☆133Updated 7 months ago
- General-Sum variant of the game Diplomacy for evaluating AIs.☆29Updated last year
- Text-based game of lies and deceit, made for language models.☆31Updated last year
- A benchmark for evaluating learning agents based on just language feedback☆79Updated 2 months ago
- Learning to route instances for Human vs AI Feedback (ACL 2025 Main)☆23Updated 3 weeks ago
- Navigating a maze using LLM agent☆39Updated 2 years ago
- Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"☆50Updated 3 months ago
- Interpreting how transformers simulate agents performing RL tasks☆83Updated last year
- A tutorial for building autonomous agents: with LangChain and from scratch☆26Updated 2 years ago
- ☆19Updated last week
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆58Updated 3 months ago
- ☆54Updated 8 months ago
- Benchmark for LLMs playing full press diplomacy☆46Updated 3 months ago
- ☆17Updated 3 months ago
- An attribution library for LLMs☆41Updated 8 months ago
- Track the progress of LLM context utilisation☆54Updated last month
- Automated Capability Discovery via Foundation Model Self-Exploration☆50Updated 3 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆147Updated 4 months ago
- ☆78Updated last month
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆32Updated last month
- Source code for our paper: "SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals".☆67Updated 11 months ago
- The AgentForge project focuses on building general tooling to construct multicapability AI systems by composing skills and models togethe…☆17Updated last year
- Evaluating LLMs with CommonGen-Lite☆90Updated last year
- ☆22Updated this week
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents☆124Updated 11 months ago
- A preprint version of our recent research on the capability of frontier AI systems to do self-replication☆60Updated 5 months ago