alexcombessie

Recent Submissions

1. 1. ▲ LLM Sycophancy: The Risk of Vulnerable Misguidance in AI Medical Advice (giskard.ai) 2 points · 3 months ago · 0 comments
2. 2. ▲ Agentic Tool Extraction: Multi-turn attacks that expose AI agents (giskard.ai) 1 point · 3 months ago · 0 comments
3. 3. ▲ LMEval: An Open Source Framework for Cross-Model Evaluation (opensource.googleblog.com) 2 points · 10 months ago · 0 comments
4. 4. ▲ Show HN: Open-Source Evaluation and Testing for Computer Vision Models (github.com) 3 points · 1 year ago · 0 comments
5. 5. ▲ Vision AI model vulnerability scan (docs.giskard.ai) 1 point · 1 year ago · 0 comments
6. 6. ▲ AI Systems Security: Top Tools for Preventing Prompt Injection (sahbichaieb.com) 2 points · 1 year ago · 0 comments
7. 7. ▲ Scanning LLM app vulnerabilities: Quickstart (docs.giskard.ai) 1 point · 1 year ago · 0 comments
8. 8. ▲ Evaluating LLMs with Giskard in MLflow (databricks.com) 1 point · 1 year ago · 0 comments
9. 9. ▲ Show HN: Automatic generation of LLM guardrails with NeMo and Giskard (docs.giskard.ai) 1 point · 1 year ago · 0 comments
10. 10. ▲ Coursera on Red Teaming LLM Applications (coursera.org) 15 points · 1 year ago · 1 comment