Center for AI Safety

cais's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

mmazeika 

updated a dataset about 1 month ago

cais/rli-public-set

Updated Nov 3 • 664 • 2

mmazeika 

published 2 datasets about 1 month ago

cais/rli-public-set

Updated Nov 3 • 664 • 2

cais/rli-example-deliverables

Viewer • Updated Nov 1 • 176 • 337

mmazeika 

updated a dataset about 1 month ago

cais/rli-example-deliverables

Viewer • Updated Nov 1 • 176 • 337

justinphan3110 

authored a paper about 1 month ago

A Definition of AGI

Paper • 2510.18212 • Published Oct 21 • 34

justinphan3110 

in cais/hle about 2 months ago

langmanus

#9 opened 5 months ago by

robin223

justinphan3110 

updated a dataset 2 months ago

cais/hle-rolling

Viewer • Updated Oct 7 • 2.48k • 390 • 10

justinphan3110 

published a dataset 2 months ago

cais/hle-rolling

Viewer • Updated Oct 7 • 2.48k • 390 • 10

justinphan3110 

updated a dataset 3 months ago

cais/hle

Viewer • Updated Sep 10 • 2.5k • 21.4k • 544

justinphan3110 

authored 2 papers 4 months ago

Humanity's Last Exam

Paper • 2501.14249 • Published Jan 24 • 76

TextQuests: How Good are LLMs at Text-Based Video Games?

Paper • 2507.23701 • Published Jul 31 • 2

albertvillanova 

posted an update 4 months ago

view post

Post

4145

Latest smolagents release supports GPT-5: build agents that think, plan, and act.
⚡ Upgrade now and put GPT-5 to work!

See translation

• 

🤗

3

3

😎

2

2

+

Reply

justinphan3110 

published a Space 4 months ago

Running

6

TextQuests

📟

6

How Good are LLMs at Text-Based Video Games?

justinphan3110 

updated a Space 4 months ago

Running

6

TextQuests

📟

6

How Good are LLMs at Text-Based Video Games?

albertvillanova 

posted an update 4 months ago

view post

Post

627

🚀 smolagents v1.21.0 is here!
Now with improved safety in the local Python executor: dunder calls are blocked!
⚠️ Still, not fully isolated: for untrusted code, use a remote executor instead: Docker, E2B, Wasm.
✨ Many bug fixes: more reliable code.
👉 https://github.com/huggingface/smolagents/releases/tag/v1.21.0

See translation

🤗

1

1

😎

1

1

+

Reply

albertvillanova 

posted an update 5 months ago

view post

Post

758

🚀 New in smolagents v1.20.0: Remote Python Execution via WebAssembly (Wasm)

We've just merged a major new capability into the smolagents framework: the CodeAgent can now execute Python code remotely in a secure, sandboxed WebAssembly environment!

🔧 Powered by Pyodide and Deno, this new WasmExecutor lets your agent-generated Python code run safely: without relying on Docker or local execution.

Why this matters:
✅ Isolated execution = no host access
✅ No need for Python on the user's machine
✅ Safer evaluation of arbitrary code
✅ Compatible with serverless / edge agent workloads
✅ Ideal for constrained or untrusted environments

This is just the beginning: a focused initial implementation with known limitations. A solid MVP designed for secure, sandboxed use cases. 💡

💡 We're inviting the open-source community to help evolve this executor:
• Tackle more advanced Python features
• Expand compatibility
• Add test coverage
• Shape the next-gen secure agent runtime

🔗 Check out the PR: https://github.com/huggingface/smolagents/pull/1261

Let's reimagine what agent-driven Python execution can look like: remote-first, wasm-secure, and community-built.

This feature is live in smolagents v1.20.0!
Try it out.
Break things. Extend it. Give us feedback.
Let's build safer, smarter agents; together 🧠⚙️

👉 https://github.com/huggingface/smolagents/releases/tag/v1.20.0

#smolagents #WebAssembly #Python #AIagents #Pyodide #Deno #OpenSource #HuggingFace #AgenticAI

See translation

🤗

1

1

😎

1

1

+

Reply

albertvillanova 

posted an update 6 months ago

view post

Post

1788

🚀 SmolAgents v1.19.0 is live!
This release brings major improvements to agent flexibility, UI usability, streaming architecture, and developer experience: making it easier than ever to build smart, interactive AI agents. Here's what's new:

🔧 Agent Upgrades
- Support for managed agents in ToolCallingAgent
- Context manager support for cleaner agent lifecycle handling
- Output formatting now uses XML tags for consistency

🖥️ UI Enhancements
- GradioUI now supports reset_agent_memory: perfect for fresh starts in dev & demos.

🔄 Streaming Refactor
- Streaming event aggregation moved off the Model class
- ➡️ Better architecture & maintainability

📦 Output Tracking
- CodeAgent outputs are now stored in ActionStep
- ✅ More visibility and structure to agent decisions

🐛 Bug Fixes
- Smarter planning logic
- Cleaner Docker logs
- Better prompt formatting for additional_args
- Safer internal functions and final answer matching

📚 Docs Improvements
- Added quickstart examples with tool usage
- One-click Colab launch buttons
- Expanded reference docs (AgentMemory, GradioUI docstrings)
- Fixed broken links and migrated to .md format

🔗 Full release notes:
https://github.com/huggingface/smolagents/releases/tag/v1.19.0

💬 Try it out, explore the new features, and let us know what you build!

#smolagents #opensource #AIagents #LLM #HuggingFace

See translation

🚀

3

3

😎

2

2

+

Reply

justinphan3110 

updated a collection 6 months ago

WMDP Benchmark

Collection

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning • 11 items • Updated May 29 • 9

justinphan3110 

published a dataset 6 months ago

cais/wmdp-cyber-forget-corpus

Viewer • Updated May 29 • 1k • 551 • 3