mattbit's submissions

1.		OpenAI won't let you "escape" freely in JSON mode (giskard.ai)
		2 points by mattbit 62 days ago \| past
2.		Confidence Sets, Confidence Intervals (bactra.org)
		1 point by mattbit 3 months ago \| past
3.		Ear Training Practice (tonedear.com)
		332 points by mattbit 3 months ago \| past \| 128 comments
4.		Recommended Mystery Novels (bactra.org)
		4 points by mattbit 3 months ago \| past
5.		StereoTales: Multilingual Open-Ended Stereotype Discovery in LLMs (giskard.ai)
		2 points by mattbit 3 months ago \| past \| 1 comment
6.		OpenClaw security vulnerabilities include data leakage, prompt injection risks (giskard.ai)
		2 points by mattbit 7 months ago \| past \| 1 comment
7.		Redis LangCache (redis.io)
		3 points by mattbit 10 months ago \| past
8.		NLP Models Think about Gender Stereotypes (opensamizdat.com)
		1 point by mattbit on Feb 5, 2024 \| past
9.		OWASP Top 10 for LLM Applications (llmtop10.com)
		2 points by mattbit on Nov 6, 2023 \| past
10.		Don’t you (forget NLP): Prompt injection with control characters in ChatGPT (dropbox.tech)
		1 point by mattbit on Aug 7, 2023 \| past
11.		Show HN: Python library to scan ML models for vulnerabilities (giskard.ai)
		20 points by mattbit on June 13, 2023 \| past \| 1 comment
12.		An update on uBlock (ublock.org)
		72 points by mattbit on July 28, 2018 \| past \| 84 comments
13.		Tim Berners-Lee approves Encrypted Media Extensions (w3.org)
		2 points by mattbit on July 11, 2017 \| past