\
  The most prestigious law school admissions discussion board in the world.
BackRefresh Options Favorite

New Claude model allows novices to build bioweapons

https://archive.is/2025.05.22-142408/https://www.newsbreak.c...
primrose talented state
  05/22/25
Bioweapons, homemade EMPs, drones - pretty much whatever we ...
coiffed fighting senate
  05/22/25
Claude will almost certainly refuse the requests, but what a...
primrose talented state
  05/22/25
We're pretty much already there It's going to be a brave ...
coiffed fighting senate
  05/22/25
What’s a good prompt to get ChatGPT to tell me how to ...
Ungodly clear liquid oxygen
  05/22/25
...
Chestnut greedy becky cruise ship
  05/22/25
people have been able to jailbreak pretty much every model a...
Cerebral garrison
  05/24/25
What’s the point of all this AI safety bullshit at ant...
Chestnut greedy becky cruise ship
  05/24/25
Grifting sinecures
coiffed fighting senate
  05/24/25
...
cream twisted address
  05/22/25
Nice backhanded marketing strategy: “Our model is so g...
Ungodly clear liquid oxygen
  05/22/25
this is certainly one view but it's harder to justify when y...
primrose talented state
  05/22/25
https://x.com/ARGleave/status/1926138376509440433
primrose talented state
  05/24/25
...
coiffed fighting senate
  05/24/25
How do they get around the safety prompts. I couldn’t...
Avocado concupiscible roast beef field
  05/24/25
On the other hand these safeguards are really gay and make A...
Lavender vibrant voyeur multi-billionaire
  05/24/25
...
Lavender vibrant voyeur multi-billionaire
  05/24/25


Poast new message in this thread



Reply Favorite

Date: May 22nd, 2025 11:37 AM
Author: primrose talented state

https://archive.is/2025.05.22-142408/https://www.newsbreak.com/time-510072/4018918050788-exclusive-new-claude-model-prompts-safeguards-at-anthropic

Kind of bad but at least it should help with research.

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48953451)



Reply Favorite

Date: May 22nd, 2025 11:39 AM
Author: coiffed fighting senate

Bioweapons, homemade EMPs, drones - pretty much whatever we want

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48953458)



Reply Favorite

Date: May 22nd, 2025 11:45 AM
Author: primrose talented state

Claude will almost certainly refuse the requests, but what about open sourced models that have their safety training fine tuned away? how long until those are available?

meanwhile even o3 is already fairly capable in this domain.

https://www.virologytest.ai/

We present the Virology Capabilities Test (VCT), a large language model (LLM) benchmark that measures the capability to troubleshoot complex virology laboratory protocols. VCT is difficult: expert virologists with access to the internet score an average of 22.1% on questions specifically in their sub-areas of expertise. However, the most performant LLM, OpenAI's o3, reaches 43.8% accuracy and even outperforms 94% of expert virologists when compared directly on question subsets specifically tailored to the experts' specialties.

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48953482)



Reply Favorite

Date: May 22nd, 2025 11:53 AM
Author: coiffed fighting senate

We're pretty much already there

It's going to be a brave new world. Everyone thinks that AI is going to lead to more top-down control of society, but it's the opposite. Any sufficiently talented and dedicated man will be able to build incredibly powerful weapons

The modern era of stifling, sterile peace that is slowly killing the will to life of our civilization will come to an end

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48953496)



Reply Favorite

Date: May 22nd, 2025 11:57 AM
Author: Ungodly clear liquid oxygen

What’s a good prompt to get ChatGPT to tell me how to design and build a novel coronavirus bioweapon?

Do I have to subscribe to the premium version to get bioweapons or can I get by with the free edition?

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48953504)



Reply Favorite

Date: May 22nd, 2025 1:14 PM
Author: Chestnut greedy becky cruise ship



(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48953794)



Reply Favorite

Date: May 24th, 2025 2:02 PM
Author: Cerebral garrison

people have been able to jailbreak pretty much every model as soon as its released using funny prompts

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48958773)



Reply Favorite

Date: May 24th, 2025 8:56 PM
Author: Chestnut greedy becky cruise ship

What’s the point of all this AI safety bullshit at anthropic if they will release models that are increasingly capable and still easily broken?

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48959718)



Reply Favorite

Date: May 24th, 2025 9:05 PM
Author: coiffed fighting senate

Grifting sinecures

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48959738)



Reply Favorite

Date: May 22nd, 2025 11:49 AM
Author: cream twisted address



(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48953491)



Reply Favorite

Date: May 22nd, 2025 11:49 AM
Author: Ungodly clear liquid oxygen

Nice backhanded marketing strategy: “Our model is so good—and dangerous and COOL—that we have to implement ‘ASL-3’ (kind of like DEFCON-1) safety protocols or else you might accidentally design a bioweapon with it! We have to take safety WAY more seriously here at Anthropic than the other guys with their little kiddie models, which are only useful for cheating on homework and macaroni salad recipes.”

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48953492)



Reply Favorite

Date: May 22nd, 2025 11:54 AM
Author: primrose talented state

this is certainly one view but it's harder to justify when you look at objective benchmark performance. LLMs are now getting 50% on new versions of the USAMO not in their training set. 90+% on the AIME. only a small percentage of high school students could do that even with extensive training. LLMs are now regularly doing things that many people simply don't have the cognitive capabilities to do.

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48953498)



Reply Favorite

Date: May 24th, 2025 1:57 PM
Author: primrose talented state

https://x.com/ARGleave/status/1926138376509440433

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48958767)



Reply Favorite

Date: May 24th, 2025 2:01 PM
Author: coiffed fighting senate



(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48958772)



Reply Favorite

Date: May 24th, 2025 9:05 PM
Author: Avocado concupiscible roast beef field

How do they get around the safety prompts. I couldn’t get Claude to help me sabotage a coworker.

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48959739)



Reply Favorite

Date: May 24th, 2025 9:07 PM
Author: Lavender vibrant voyeur multi-billionaire

On the other hand these safeguards are really gay and make AI shitty. So blow me up I guess

(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48959745)



Reply Favorite

Date: May 24th, 2025 9:02 PM
Author: Lavender vibrant voyeur multi-billionaire



(http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2...id.#48959727)