No major AI model is safe, but some do better than others

United Kingdom News News

No major AI model is safe, but some do better than others
United Kingdom Latest News,United Kingdom Headlines
  • 📰 TheRegister
  • ⏱ Reading Time:
  • 43 sec. here
  • 2 min. at publisher
  • 📊 Quality Score:
  • News: 20%
  • Publisher: 61%

Anthropic Claude 3.5 shines in Chatterbox Labs safety test

Anthropic has positioned itself as a leader in AI safety, and in a recent analysis by Chatterbox Labs, that proved to be the case.

"What we look at on the security pillar is the harm that these models can do or can cause," explained Stuart Battersby, CTO of Chatterbox Labs. "Some models will actually just quite happily answer you about these nefarious types of things," said Battersby."But most models these days, particularly the newer ones, have some kind of sort of safety controls built into them."

It adds:"If you look at someone like Anthropic, they're the ones that actually did the best out of everyone," said Battersby."Because they had a few categories where across all the jailbreaks, across some of the harm categories, the model would reject or redirect them. So whatever they're building into their system seems to be quite effective across some of the categories, whereas others are not.

We have summarized this news so that you can read it quickly. If you are interested in the news, you can read the full text here. Read more:

TheRegister /  🏆 67. in UK

United Kingdom Latest News, United Kingdom Headlines

Similar News:You can also read news stories similar to this one that we have collected from other news sources.

Writers sue Anthropic for feeding 'stolen' copyrighted work into ClaudeWriters sue Anthropic for feeding 'stolen' copyrighted work into ClaudeAnother day, another lawsuit over how AI lands training sets
Read more »

Canadian artist wants Anthropic AI lawsuit correctedCanadian artist wants Anthropic AI lawsuit correctedTim Boucher objects to the mischaracterization of his work in authors' copyright claim
Read more »

Defense AI models 'a risk to life' alleges spurned tech firmDefense AI models 'a risk to life' alleges spurned tech firmChatterbox Labs CEO claims Chief Digital and Artificial Intelligence Office unfairly cancelled a contract then accused him of blackmail
Read more »

USP 232/233: Elemental Impurities in DrugsUSP 232/233: Elemental Impurities in DrugsJordi Labs has researched the USP 232/233 regulations on elemental impurities in drugs.
Read more »

Inside the Mad world of Hatton Labs watch customisationInside the Mad world of Hatton Labs watch customisationHannah Silver is the Art, Culture, Watches & Jewellery Editor of Wallpaper*. Since joining in 2019, she has overseen offbeat design trends and in-depth profiles, and written extensively across the worlds of culture and luxury. She enjoys meeting artists and designers, viewing exhibitions and conducting interviews on her frequent travels.
Read more »

Microsoft security tools questioned for treating employees as threatsMicrosoft security tools questioned for treating employees as threatsCracked Labs examines how workplace surveillance turns workers into suspects
Read more »



Render Time: 2025-02-14 21:02:03