anton
First time I hear of this training method, input inversion, where the answer (output) is used as the input and the question is used as the output for training

Also worth noting, fine-tuned models (flan-t5) serve as better starting points for downstream tasks https://t.co/BLNsgWYSXe
tweet

Weird AI Generations
New Disney mythical movie about Monkey https://t.co/d61U296sCp
tweet

Meta AI
📣 New paper: Emergence of Maps in the Memories of Blind Navigation Agents

Humans have the ability to navigate poorly lit spaces by relying on touch and memory. Our research shows that blind AI agents can learn to do the same.

Read the paper ➡️ https://t.co/XY5kNU5FwR https://t.co/IbfumhR4ZU
tweet

dave
How AI has transformed VC in 2023 https://t.co/dK84So4exe
tweet

Rob Henderson
“married women in their early 30s are most likely to have an affair, perhaps reflecting a motivation to switch mates while their desirability is still high.” https://t.co/SzdCAGPZtc
tweet

proxima centauri b ▫️ open edition live!
RT @fedhoneypot: 🫠 https://t.co/Ei7v3IeuCT
tweet

David Marx
RT @eye_for_ai: February 14 is Valentine's Day. - by Philipp #AiArt #AiiA #AiArtCommunity #AiArtSociety #AiLust https://t.co/YjxjKTWrZv
tweet

KaliYuga
RT @NerdyRodent: Felt vs Wool - you decide ;) https://t.co/hjX8ApghQ5
tweet

Project Veritas
RT @sal_gueli: https://t.co/ImkgE03EpB
tweet

Aran Komatsuzaki
RT @ShayneRedford: ✨New Paper✨What’s the best completely public competitor to #ChatGPT?

Flan-T5 beats all public models we tested:
Flan-T5 3B ▶️ T0++ 3B ▶️ OPT-IML 175B ▶️ GLM-130B ▶️ Flan 2021 3B ▶️ NIv2 3B

We release the @GoogleAI 🌟Flan Collection🌟data + methods for Instruction Tuning!

1/ https://t.co/cpDPcRMgUP
tweet