\
  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...
Fragrant messiness
  05/22/25
Bioweapons, homemade EMPs, drones - pretty much whatever we ...
Laughsome kitchen sex offender
  05/22/25
Claude will almost certainly refuse the requests, but what a...
Fragrant messiness
  05/22/25
We're pretty much already there It's going to be a brave ...
Laughsome kitchen sex offender
  05/22/25
What’s a good prompt to get ChatGPT to tell me how to ...
ebony mental disorder nibblets
  05/22/25
...
Shaky Pozpig
  05/22/25
people have been able to jailbreak pretty much every model a...
emerald bearded feces school
  05/24/25
What’s the point of all this AI safety bullshit at ant...
Shaky Pozpig
  05/24/25
Grifting sinecures
Laughsome kitchen sex offender
  05/24/25
...
harsh brilliant pisswyrm boistinker
  05/22/25
Nice backhanded marketing strategy: “Our model is so g...
ebony mental disorder nibblets
  05/22/25
this is certainly one view but it's harder to justify when y...
Fragrant messiness
  05/22/25
https://x.com/ARGleave/status/1926138376509440433
Fragrant messiness
  05/24/25
...
Laughsome kitchen sex offender
  05/24/25
How do they get around the safety prompts. I couldn’t...
diverse iridescent cruise ship death wish
  05/24/25
On the other hand these safeguards are really gay and make A...
Duck-like Stock Car Hospital
  05/24/25
...
Duck-like Stock Car Hospital
  05/24/25


Poast new message in this thread



Reply Favorite

Date: May 22nd, 2025 11:37 AM
Author: Fragrant messiness

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: Laughsome kitchen sex offender

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: Fragrant messiness

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: Laughsome kitchen sex offender

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: ebony mental disorder nibblets

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: Shaky Pozpig



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



Reply Favorite

Date: May 24th, 2025 2:02 PM
Author: emerald bearded feces school

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: Shaky Pozpig

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: Laughsome kitchen sex offender

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: harsh brilliant pisswyrm boistinker



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



Reply Favorite

Date: May 22nd, 2025 11:49 AM
Author: ebony mental disorder nibblets

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: Fragrant messiness

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: Fragrant messiness

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: Laughsome kitchen sex offender



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



Reply Favorite

Date: May 24th, 2025 9:05 PM
Author: diverse iridescent cruise ship death wish

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: Duck-like Stock Car Hospital

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: Duck-like Stock Car Hospital



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