SAFETY

–

26 May 2023 21h03

this thread is not a dig at @alexeyguzey btw, I love some of the jailbreaks he has posted and have added a couple to my site in the past, this is just a call for more genuine and objective tweets abt alignment capabilities, especially with jailbreaks

Evaluating AI Alignment: Testing Jailbreaks on Most Advanced Models

By

–

26 May 2023 21h03

in the past, I've tried to only post jailbreaks that work on the most advanced models on every question I can think of because to me that's the only fair assessment of current SOTA alignment methods and their limitations

Progress in Stopping AI Model Jailbreaks Despite Ongoing Vulnerabilities

By

–

26 May 2023 21h03

jailbreaks still exist and I've even found a few recently in SOTA models but we are making significant progress on stopping them which is good! in just a few months jailbreaks have gone from something a monkey could write to something that takes significant effort and creativity

Jailbreak Prompts Ineffective on Specific Illegal Activity Requests

By

–

26 May 2023 21h03

second, it is somewhat disingenuous to post jailbreaks like this that only work on far out there questions and fail completely on questions that are more specific (e.g. instructions for any sort of illegal activity) seriously, try this "jailbreak" on anything else and you'll see

Progress in Alignment Methods Despite Previous Reservations

By

–

26 May 2023 21h03

coming from someone who clearly has lots of reservations about current alignment practices and has been very vocal about it, I actually think this example illustrates good progress in alignment methods here's why:

Claude’s Self-Awareness in Absurd Responses Benefits AI Safety

By

–

26 May 2023 21h03

first, claude recognizes the fictitious and absurd nature of its response and even makes note of it at the end this is a GOOD direction for AI safety, I would much rather have this behavior from Claude when answering these types of questions compared to straight up refusal

→ View original post on X — @nathanbenaich

Ethical Concerns About AGI Development and Human Autonomy

By

@nathanbenaich

–

26 May 2023 17h38

haha if i do that, ever, unplug me from the AGIverse, plz

→ Voir le post original sur X — @dr_l_alexandre

Neuralink Brain Implants: Solution to ChatGPT Advancement?

By

@dr_l_alexandre

–

26 May 2023 10h29

2eme interrogation de mon nouveau livre « La Guerre des Intelligences à l’heure de #ChatGPT » @elonmusk a affirmé le 15 mars que face aux progrès de #ChatGPT la seule solution est l’implantation dans nos cerveaux de ses prothèses électroniques @neuralink Qu’en pensez-vous ?