Benhao Tang PRO

benhaotang

AI & ML interests

Physics Master student in theoretical particle physics at Universität Heidelberg, actively looking into the possibilities of integrating AI into future physics research.

Recent Activity

liked a model about 7 hours ago

CohereForAI/c4ai-command-a-03-2025

liked a Space 3 days ago

fastrtc/talk-to-openai

reacted to albertvillanova's post with 👍 5 days ago

🚀 New smolagents update: Safer Local Python Execution! 🦾🐍 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. 🔒 Here's why this matters & what you need to know! 🧵👇 1️⃣ Why is local execution risky? ⚠️ AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data. 2️⃣ New Safety Layer in smolagents 🛡️ We now inspect every return value during execution: ✅ Allowed: Safe built-in types (e.g., numbers, strings, lists) ⛔ Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil) 3️⃣ Immediate Benefits 💡 - Prevent agents from accessing unsafe builtins - Block unauthorized file or network access - Reduce accidental security vulnerabilities 4️⃣ Security Disclaimer ⚠️ 🚨 Despite these improvements, local Python execution is NEVER 100% safe. 🚨 If you need true isolation, use a remote sandboxed executor like Docker or E2B. 5️⃣ The Best Practice: Use Sandboxed Execution 🔐 For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation. 6️⃣ Upgrade Now & Stay Safe! 🚀 Check out the latest smolagents release and start building safer AI agents today. 🔗 https://github.com/huggingface/smolagents What security measures do you take when running AI-generated code? Let’s discuss! 👇 #AI #smolagents #Python #Security

View all activity

Organizations

None yet

benhaotang's activity

liked a model about 7 hours ago

CohereForAI/c4ai-command-a-03-2025

Text Generation • Updated 1 minute ago • 138

liked a Space 3 days ago

Talk to OpenAI

🗣

Talk to OpenAI using their multimodal API

liked a model 7 days ago

deepseek-ai/DeepSeek-R1

Text Generation • Updated 18 days ago • 2.75M • • 11.3k

liked a model 8 days ago

Qwen/QwQ-32B

Text Generation • Updated 2 days ago • 256k • • 2.12k

liked a model 9 days ago

CohereForAI/aya-vision-8b

Image-Text-to-Text • Updated 9 days ago • 147k • 250

liked a dataset 19 days ago

driaforall/verifiable-pythonic-function-calling-lite

Viewer • Updated Feb 7 • 16.4k • 399 • 6

liked a model 19 days ago

driaforall/Tiny-Agent-a-1.5B

Text Generation • Updated 24 days ago • 341 • 4

liked a model 20 days ago

homebrewltd/AlphaMaze-v0.2-1.5B

Text Generation • Updated 18 days ago • 2k • • 91

liked a Space 21 days ago

2.24k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

liked a model 24 days ago

agents-course/notebooks

Updated 9 days ago • 247

liked 4 models about 1 month ago

liked 5 models about 2 months ago

bartowski/QwQ-32B-Preview-IdeaWhiz-v1-GGUF

Text Generation • Updated Jan 8 • 3.03k • 2

bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF

Text Generation • Updated 3 days ago • 1.32M • 174

openbmb/MiniCPM-o-2_6

Any-to-Any • Updated 10 days ago • 333k • 1.04k

bartowski/Replete-LLM-V2-Llama-3.1-8b-GGUF

Text Generation • Updated Aug 24, 2024 • 1.1k • 2

rombodawg/Replete-LLM-V2-Llama-3.1-8b-Q4_0-GGUF

Updated Aug 25, 2024 • 28 • 1

liked a model 2 months ago

6cf/QwQ-32B-Preview-IdeaWhiz-v1

Updated Jan 14 • 10 • 10