
Benhao Tang PRO
benhaotang
AI & ML interests
Physics Master student in theoretical particle physics at UniversitΓ€t Heidelberg, actively looking into the possibilities of integrating AI into future physics research.
Recent Activity
liked
a model
1 day ago
deepseek-ai/DeepSeek-V3-0324
liked
a model
7 days ago
ds4sd/SmolDocling-256M-preview
liked
a model
9 days ago
KandirResearch/CiSiMi-v0.1
Organizations
None yet
benhaotang's activity

reacted to
albertvillanova's
post with π
17 days ago
Post
3681
π New smolagents update: Safer Local Python Execution! π¦Ύπ
With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. π
Here's why this matters & what you need to know! π§΅π
1οΈβ£ Why is local execution risky? β οΈ
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2οΈβ£ New Safety Layer in smolagents π‘οΈ
We now inspect every return value during execution:
β Allowed: Safe built-in types (e.g., numbers, strings, lists)
β Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3οΈβ£ Immediate Benefits π‘
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4οΈβ£ Security Disclaimer β οΈ
π¨ Despite these improvements, local Python execution is NEVER 100% safe. π¨
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5οΈβ£ The Best Practice: Use Sandboxed Execution π
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6οΈβ£ Upgrade Now & Stay Safe! π
Check out the latest smolagents release and start building safer AI agents today.
π https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Letβs discuss! π
#AI #smolagents #Python #Security
With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. π
Here's why this matters & what you need to know! π§΅π
1οΈβ£ Why is local execution risky? β οΈ
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2οΈβ£ New Safety Layer in smolagents π‘οΈ
We now inspect every return value during execution:
β Allowed: Safe built-in types (e.g., numbers, strings, lists)
β Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3οΈβ£ Immediate Benefits π‘
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4οΈβ£ Security Disclaimer β οΈ
π¨ Despite these improvements, local Python execution is NEVER 100% safe. π¨
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5οΈβ£ The Best Practice: Use Sandboxed Execution π
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6οΈβ£ Upgrade Now & Stay Safe! π
Check out the latest smolagents release and start building safer AI agents today.
π https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Letβs discuss! π
#AI #smolagents #Python #Security

replied to
their
post
about 1 month ago
OK, grok 3 deep research also failed on my benchmark...
And this is the final solution it gives me:
Use wsl --shutdown before hibernating; if it fails, try net stop LxssManager.
What? How about just tell me if WSL have problem, just do not using WSL... How can this be a solution when there is even an official troubleshooting guide that provide more solutions. This is the even worst than gemini and perplexity, at least they read the official guide, just got lost in github issue threads... Now I really want to know how OpenAI's compares to mine, if I have 200 dollars.