HackerTube.dev

Nicholas Carlini - Black-hat LLMs | [un]prompted 2026

unprompted · 388.6K views · 2026-03-25 · 26:28

Open on YouTube ↗

If playback is restricted in your region, try opening the original video. Use Mark watched to add it to your marked videos.

Overview

Nicholas Carlini of Anthropic talks at [un]prompted 2026 about how adversaries could misuse current LLMs for attacks. He shows recent models finding zero-day vulnerabilities in heavily tested software, including a SQL injection in Ghost.

On Hacker News

HN cites it as a concrete demonstration that LLMs have suddenly become strong at finding and exploiting vulnerabilities.

Recommended by 9 HN people across 2 months · HN mentions 2026–2026

Topics

Security & hackingLLMs & generative AI
Search by tags
zero-daysecurityllmfuzzingexploit developmentclaude

What people said

knowaveragejoe · 2026-04 · Strong recommendation

I'm sure they do, yet the models really are getting scarily good at this. This talk changed my view on where we're actually at: [VIDEO]

Read the original HN comment ↗
wkandek · 2026-05 · Recommendation

This matches with what Nicholas Carlini from Anthropic said a the [un]prompted conference - [VIDEO] . Very worth watching.

Read the original HN comment ↗
panstromek · 2026-04 · Recommendation

The talk "Black-Hat LLMs" just came out a few days ago: [VIDEO] Looks like LLMs are getting good at finding and exploiting these.

Read the original HN comment ↗

Sources

Video by unprompted, played through YouTube.

Data and selection notes

HN summaries and labels may contain AI errors. HN dates refer to discussions, not video publication.

HN Library: HackerTube export (2026-10-31) and open-index/hacker-news. Upstream summaries and classifications may contain AI errors.

Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.

Selection checks
  • SaaS & AI candidates: Matches the configured criteria
  • Editor-approved picks: Editorial review is required

Rule matches identify candidates. They do not guarantee video quality or financial results.

About the library and its sources