An unconsidered corner of alignment fine-tuning.
ETHICS
-
Stories in AI: Interview with Chirag Shah on Responsible AI Systems
By
–
In Stories in AI's Countdown to the Year End 2022, I sit down with @chirag_shah
, a professor at the University of Washington and Co-Director of RAISE (Responsible AI Systems and Experiences). As someone who has tremendous experience in both the research a… -
ChatGPT removes similar strings, suggesting hidden control codes
By
–
The fact that ChatGPT removes not just this string, but any string formatted similarly, suggests there exist other control codes by ChatGPT, e.g. to mark the boundaries between user input and prior model output within the prompt context.
-
Simulating Reality: LLMs and the Simulation Hypothesis Question
By
–
The reason that emulating virtual machines, chatrooms, and APIs inside large language models is exciting, isn’t just because “haha cool nerd stuff”. It means we are that much closer to simulating all of our world in it. And if we can do it… how would we know we aren’t in one?
-
GenAI as Public Good: Automation, Augmentation and Inequality
By
–
There will be a lot of focus on ‘will AI automate or augment?’ But if you follow argument espoused by @EMostaque that GenAI should be a public good, it becomes a universal resource. But, if it’s controlled by a few – it will invariably lead to huge disparities.
-
Multimodal Learning for Objective Representation
By
–
To address these issues, it is necessary to learn a vast amount of multimodal information (sound, image, text, etc.) using A LOT of data, in the hope of achieving the most objective representation of the world possible—something that is nearly impossible, yet still feasible with an 80-20 rule.
-
ChatGPT: Human Evaluation of Solutions
By
–
But with models like #ChatGPT, it goes beyond that. We don’t just want to know if it works or not. Instead, we aim to select the best-performing solutions from multiple options by having a human assess them.
-
Fastest Route Not Always Straight Line Challenge
By
–
The demonstration that the fastest route is not always the straight line… 😉
— Pascal Bornet (@pascal_bornet) 5 décembre 2022
Keep that in mind when facing challenges. Is that your experience as well?#inspiration pic.twitter.com/8qDbFuOzxDThe demonstration that the fastest route is not always the straight line… Keep that in mind when facing challenges. Is that your experience as well? #inspiration
-
Safety Guidelines Modified: Known AI Jailbreaks No Longer Work
By
–
not retraining doesnt mean not modifying the safety guidelines, which is what people have been observing (see the links, a lot of the known jailbreaks dont work anymore)