News for hackers. Stuff that matters.

A comment on Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable. Parent comment

Re:Cybersecurity researchers aren't happy about the guardrai... by ainch on Wednesday June 10, 2026 @08:50PM (#48484892)
Anthropic's claim was that Deepseek collected ~150k conversations.

https://www.anthropic.com/news/detecting-and-preventing-dist...

I think the extent of distillation by Deepseek specifically is overstated. For comparison, Minimax collected over 13m 'exchanges', which starts to sound a lot more like large-scale distillation.

[ Parent | on HN ]
Re:Cybersecurity researchers aren't happy about the guardrai... by kube-system on Wednesday June 10, 2026 @09:03PM (#48484980)
Ah, dang it. My college professors warned me about this: the Wikipedia page I read the other day is wrong!
[ Parent | on HN ]
Re:Cybersecurity researchers aren't happy about the guardrai... by 59nadir on Thursday June 11, 2026 @03:14AM (#48487286)
Did you read a Wikipedia page, or did you read a LLM-generated summary? When I looked this number up yesterday the LLM summary claimed it was millions, but I opened the Anthropic post I was looking for and verified it was indeed just 150,000. Are you sure you weren't just being lazy and trusting the summary?
[ Parent | on HN ]
Re:Cybersecurity researchers aren't happy about the guardrai... by kube-system on Thursday June 11, 2026 @10:22AM (#48490786)
I said what I meant:

https://en.wikipedia.org/wiki/DeepSeek

> In February 2026, Anthropic accused DeepSeek of using thousands of fraudulent accounts to generate millions of conversations with Claude to train its own large language models.[57]

[ Parent | on HN ]
Re:Cybersecurity researchers aren't happy about the guardrai... by zxexz on Thursday June 11, 2026 @02:39AM (#48487001)
If that's all it took to make Deepseek so good, I'll gladly ship High-Flyer all my personal 150k claude/chatgpt conversations in exchange for Deepseek 5 (and a rack of B200s or Ascend chips)
[ Parent | on HN ]