\
  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...
Confused Stag Film
  05/22/25
Bioweapons, homemade EMPs, drones - pretty much whatever we ...
cheese-eating contagious dysfunction
  05/22/25
Claude will almost certainly refuse the requests, but what a...
Confused Stag Film
  05/22/25
We're pretty much already there It's going to be a brave ...
cheese-eating contagious dysfunction
  05/22/25
What’s a good prompt to get ChatGPT to tell me how to ...
aromatic seedy school chad
  05/22/25
...
Razzle flushed university mexican
  05/22/25
people have been able to jailbreak pretty much every model a...
translucent up-to-no-good marketing idea parlor
  05/24/25
What’s the point of all this AI safety bullshit at ant...
Razzle flushed university mexican
  05/24/25
Grifting sinecures
cheese-eating contagious dysfunction
  05/24/25
...
drab blood rage
  05/22/25
Nice backhanded marketing strategy: “Our model is so g...
aromatic seedy school chad
  05/22/25
this is certainly one view but it's harder to justify when y...
Confused Stag Film
  05/22/25
https://x.com/ARGleave/status/1926138376509440433
Confused Stag Film
  05/24/25
...
cheese-eating contagious dysfunction
  05/24/25
How do they get around the safety prompts. I couldn’t...
Electric mad-dog skullcap
  05/24/25
On the other hand these safeguards are really gay and make A...
filthy supple useless brakes
  05/24/25
...
filthy supple useless brakes
  05/24/25


Poast new message in this thread



Reply Favorite

Date: May 22nd, 2025 11:37 AM
Author: Confused Stag Film

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: cheese-eating contagious dysfunction

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: Confused Stag Film

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: cheese-eating contagious dysfunction

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: aromatic seedy school chad

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: Razzle flushed university mexican



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



Reply Favorite

Date: May 24th, 2025 2:02 PM
Author: translucent up-to-no-good marketing idea parlor

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: Razzle flushed university mexican

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: cheese-eating contagious dysfunction

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: drab blood rage



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



Reply Favorite

Date: May 22nd, 2025 11:49 AM
Author: aromatic seedy school chad

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: Confused Stag Film

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: Confused Stag Film

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: cheese-eating contagious dysfunction



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



Reply Favorite

Date: May 24th, 2025 9:05 PM
Author: Electric mad-dog skullcap

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: filthy supple useless brakes

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: filthy supple useless brakes



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