HNHacker News
TopNewBestAskShowJobs

harisec

39 karma · joined May 30, 2022

submissionscomments

Context Bombs: stopping AI attackers in their tracks

agentic.tracebit.com·2 pts·harisec·
0

Security research in the age of AI tools

invicti.com·2 pts·harisec·
0

My Thoughts on the Future of "AI"

nicholas.carlini.com·2 pts·harisec·
0

Coinbase, Binance Plan to List Donald Trump's Official Trump Token

coindesk.com·2 pts·harisec·
0

How to jailbreak most/all LLMs using Assistant Prefill

invicti.com·3 pts·harisec·
0

System prompt exposure: how AI image generators may leak sensitive instructions

invicti.com·1 pts·harisec·
1

Analyzing WordPress hack access logs with NotebookLM

invicti.com·1 pts·harisec·
0

Volkswagen considers historic German plant closures in cost-cutting drive

reuters.com·1 pts·harisec·
0

LLM Dreams – images from automatically generated LLM prompts

harisec.github.io·3 pts·harisec·
3

New phone sparks worry China has found a way around U.S. tech limits

washingtonpost.com·7 pts·harisec·
0

The bear case with LK-99

citriniresearch.com·3 pts·harisec·
0

Universal and Transferable Attacks on Aligned Language Models

llm-attacks.org·6 pts·harisec·
1