Language Models are Changing AI: The Need for Holistic Evaluation. New benchmarking method, Holistic Evaluation of Language Models (HELM) has been developed at the Center for Research on Foundation Models to help provide transparency in LMs. @RishiBommasani
, @PercyLiang
, Tony Lee
ETHICS
-
HELM: Holistic Evaluation Method for Language Models
By
–
-
Configurable AI Models and Safety Mode Control Options
By
–
i think it’s very reasonable for “default models” to be inoffensive, but within some pretty bounds i think people should be able to configure the models to behave how they’d like, eg like turning off safe mode
-
Philosophy Author Chatbot Project Using GPT-3 Fine-Tuning
By
–
philosophy author chatbot thing w gpt background: need to create something for my philosophy of AI class idea: fine-tune gpt3 models on text from authors we have read in class and create a chat application where users can talk to these models
-
Democracy Under Threat: Free Speech Versus Protecting Democratic Values
By
–
Why does the free world have to put up with this shit? Do we have to give enemies of democracy a voice to attack us? I am sorry I heard this idiotic drivel and more sorry that there are so many others who will pay attention to the chuckle head. https://t.co/IdPSKK4GQO
— Bob Gourley – e/acc (@bobgourley) 1 décembre 2022Why does the free world have to put up with this shit? Do we have to give enemies of democracy a voice to attack us? I am sorry I heard this idiotic drivel and more sorry that there are so many others who will pay attention to the chuckle head.
-
Blurred Line Between AI Training and Copyright Infringement
By
–
There’ll be a fuzzy & heavily litigated line between training an AI and copyright infringement. Is it a fuzzy interpolated search restating data from Yelp, Quora, Stack Overflow? Or remixing a thousand copyrighted artists, coders, authors? Or is it learning, thinking, creating?
-
Fighting for Open AI Systems Against Closed Approaches
By
–
Don't lose hope! It's always a pendulum between closed and open and very cool open stuff will follow if we keep fighting for it like you've been doing!
-
AI Advances Enable Rapid Disinformation Distribution Like Printing Press
By
–
The invention of the printing press led to an easy and fast distribution of disinformation. Advances in AI are doing the same.
-
Institutional corruption and incompetence in AI domains
By
–
Same for institutional corruption and incompetence. If you notice it in your domain, it’s likely pervasive.
-
CICERO’s Diplomacy Strategy: Honesty as a Winning Tactic
By
–
☑️ Using honesty as a tactic: 3X Diplomacy World Champ @thegoffy and @adamlerer speak to CICERO’s strength as a Diplomacy player through its use of honesty. 📺 Watch the full video 👉 https://t.co/Lk4R4xW0jj#CICERObyMetaAI pic.twitter.com/axOdVVypjd
— AI at Meta (@AIatMeta) 1 décembre 2022Using honesty as a tactic: 3X Diplomacy World Champ @thegoffy and @adamlerer speak to CICERO’s strength as a Diplomacy player through its use of honesty. Watch the full video https://
youtu.be/kexYmcu1Zro #CICERObyMetaAI -
Chalmers explores consciousness and AI at NeurIPS conference
By
–
A delightful romp by NYU philosopher David Chalmers opened this year’s NeurIPS AI conference with big-picture stuff. // @davidchalmers42 // #AI #artificialintelligence #deeplearning #consciousness #sentience