๐ They're live! Dive into #AIAlignment at the #AlignmentWorkshop with videos now on YouTube & our site, all with captions & transcripts. ๐บ For more insights, check out our blog post. โจLinks below ๐๐Be inspired, engage, and share your favorite insights!
๐ Reflecting on a fantastic #NeurIPS2023 #AIAlignment Workshop! ๐
๐ 149 attendees energized the main event
๐ 500+ at our Monday social
๐ง 12 talks, 25 lightning talks
๐ Keynote by Yoshua Bengio
๐ค What inspired you the most? Share your thoughts!
๐ฅ As we embrace the holiday season, we're excited to share a special announcement: The NOLA Alignment Workshop videos are now live! Warm up your winter with insights from leading #AIAlignment researchers at alignment-workshop.com/nola-2023. Happy Holidays! ๐ทโ๏ธ
๐ก๐ฌFAR AI #AIAlignment Research Update! Weโre exploring AI robustness, value alignment, & model evaluation. Weโve made strides in adversarial attacks for superhuman systems, mechanistic interpretability, scaling trends & more! far.ai/post/2023-12-fโฆ
The AI Existential Threat: Will AI Go Anti-Human? Clip: Some Future Day Show Ep. 2 feat. Robert Scoble, tech visionary #ai #artificialintelligence #ai safety #ai alignment #SomeFutureDay via Robert Scoble
Connect with the #AIAlignment community at #NeurIPS2023 ! Join us Dec 11 at Le Meridien New Orleans, 7:30 pm for the Alignment Workshop: Open Social event! ๐ค๐ฌ Please help spread the word and share in your network! ๐
alignment-workshop.com/nola-2023-openโฆ
๐ Exciting Research Alert! ๐ง ๐ค #AIAlignment #Diversity #LLMs . With the ongoing debate on #Diversity in #AIAlignment #RLHF , we ask the questions
๐ฅ Is it possible to align with #DIVERSE user preferences using the current single reward #RLHF pipelines?
๐ซNO !!!
Pondering #AIAlignment with acclaimed author Brian Christian. Exploring the influence of reinforcement learning and the 'frame problem' in AI. What does it all mean? Listen to the podcast to find out! superset.com/feed/season-4-โฆ
Will be presenting 2 papers at #ICLR ICLR 2024 this year on #AIAlignment #Robustness #RLHF #OnlineRLHF #AISafety
(Missing #ICLR unfortunately). Drop by our Poster sessions and reach out with any questions :)
#AI #Alignment #ChatGPT #AI alignment
Most AI gurus can't say it outloud cause they reveal their hypocrisy
Ethical Vegan(not plant-based )
Atleast Sam Altman acknowledges it
Currently looking into AI and existential risk with OpenAI 's leading experts #AIsafety #AIalignment UvA Amsterdam ๐ญ๐ค #ELLISunitAmsterdam
Deploy AI to be your digital compass, aligning your content with the magnetic north of your audience's interests and desires. #DigitalCompass #AIAlignment
Is it just me who thinks there are thousands of hidden messages in The Good Place, or is this a well-known โthingโ? The Good Place is taking it sleazy Ted Danson Paperclip Minimizer โธ๏ธ,โถ๏ธ #aialignment