The most prestigious law school admissions discussion board in the world.
|
 |
 
|
New Claude model allows novices to build bioweapons
Poast new message in this thread
Date: May 22nd, 2025 11:37 AM Author: Burgundy Hell Fanboi 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. |
Date: May 22nd, 2025 11:39 AM Author: Light hairraiser mother station Bioweapons, homemade EMPs, drones - pretty much whatever we want (http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2#48953458) |
 |
Date: May 22nd, 2025 11:45 AM Author: Burgundy Hell Fanboi 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.
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. |
|
Date: May 22nd, 2025 11:53 AM Author: Light hairraiser mother station 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 |
|
Date: May 22nd, 2025 11:57 AM Author: contagious lodge 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? |
|
Date: May 22nd, 2025 1:14 PM Author: concupiscible range tank (http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2#48953794) |
|
Date: May 24th, 2025 2:02 PM Author: Poppy home 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#48958773) |
|
Date: May 24th, 2025 8:56 PM Author: concupiscible range tank 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#48959718) |
|
Date: May 24th, 2025 9:05 PM Author: Light hairraiser mother station Grifting sinecures (http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2#48959738) |
|
Date: May 22nd, 2025 11:49 AM Author: bearded school (http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2#48953491) |
|
Date: May 22nd, 2025 11:49 AM Author: contagious lodge 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#48953492) |
|
Date: May 22nd, 2025 11:54 AM Author: Burgundy Hell Fanboi 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#48953498) |
|
Date: May 24th, 2025 1:57 PM Author: Burgundy Hell Fanboi https://x.com/ARGleave/status/1926138376509440433 (http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2#48958767) |
|
Date: May 24th, 2025 2:01 PM Author: Light hairraiser mother station (http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2#48958772) |
|
Date: May 24th, 2025 9:05 PM Author: Very tactful kitchen 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#48959739) |
|
Date: May 24th, 2025 9:07 PM Author: doobsian casino french chef 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#48959745) |
|
Date: May 24th, 2025 9:02 PM Author: doobsian casino french chef (http://www.autoadmit.com/thread.php?thread_id=5728798&forum_id=2#48959727) |