So on that note, OpenAssistant's earlier models used RLHF for instruction-finetuning (
https://
huggingface.co/OpenAssistant/
oasst-rlhf-2-llama-30b-7k-steps-xor
…); The later one seem to use supervised instruction-finetuning. Maybe @ykilcher has some insights whether RLHF wasn't worth the effort vs supervised?
RESEARCH
-
OpenAssistant’s shift from RLHF to supervised instruction-finetuning
By
–
-
Key AI and Robotics Leaders Acknowledged for Innovation
By
–
A huge thank you to Jaxon Khan, Rachel Sutton, Aaron Brindle & Jordan Jacobs (
@radicalvcfund
), Foteini Agrafioti (
@BorealisAI
), Raquel Urtasun (
@Waabi_ai
), Tomi Poutanen (
@Signal1_AI
), Sam Ramadiori (
@BrainBoxAI
), Ramtin Attar (
@PromiseRobotics ) & Liran Belenzon (
@BenchSci
). -
RLHF versus Supervised Instruction Tuning Clarification
By
–
Isn’t RLHF also instruction finetuning? You mean supervised instruction tuned?
-
Large Action Models: LLM Extension for Independent Task Accomplishment
By
–
This is a great article on Large Action Models(LAM), a possible extension of LLMs that can do much more than what they do currently. Large Action Models as "agents that accomplish tasks and make decisions independently". https://
blog.salesforceairesearch.com/large-action-m
odels/
… -
Witnessing extraordinary technological breakthroughs in real time
By
–
just feeling grateful i was born when i was so that i get to be alive to witness this kind of shit
-
Unleash AI Power with ChatGPT Language Model
By
–
Unleash the power of AI with ChatGPT, the state-of-the-art language model developed by OpenAI. Effortlessly generate human-like responses in real-time. Via @ingliguori #ChatGPT #AI #OpenAI #deeplearning #MachineLearning #DataScience #100daysofcoding #DEVCommunity #DataAnalytics
-
Software Billionaire Critiques Billionaire’s FSD Software
By
–
Software billionaire critiques billionaire's FSD software in @IEEESpectrum
-
Eric Schmidt Discusses AI and LLMs Future Development
By
–
And now… a fireside chat with @ericschmidt
, former CEO & Chairman of Google, and @djpersia
, Our Co-founder & SVP of Field Eng! They’ll discuss how AI, including LLMs, will take shape in the coming years. #DataAISummit -
Sensorimotor AI: Future of Robotics and Data Innovation
By
–
As an #AI expert who has researched an array of topics, @jitendramalikcv often wonders about the sensorimotor road to #artificialintelligence — and what it means for the future of innovation in #robotics, #data, and more. #DataAISummit