I also didn't realise you were on this paper Rupesh. So cool! How do you feel about the rise of GRU and friends nowadays? https://
arxiv.org/abs/1503.04069
LLMS
-
GRU Neural Networks Rise in Deep Learning Research
By
–
-
LLM Objectivity Issues: Reinforcing Beliefs Over Critical Thinking
By
–
Finding myself wishing that LLMs were giving me more objective thoughts, rather than trying to reinforce my beliefs. Every turn I ask Claude to “revisit your assumptions”, it flips back and forth. Almost like it treats the message as an instruction to flip its view.
-
Entropy Approximation Methods in Machine Learning Models
By
–
all the experiments in the paper approximate Hᴷ(x | θ) using bits under arithmetic coding, which is equivalent to cross-entropy here Hᴷ(x) is approximated using the formula for entropy of random uniform distribution for synthetic, and AC/xentropy of 'reference model' for text
-
AI Disruption Risk for Professionals and Hallucination Issues
By
–
Maître Éolas Suivez plutôt les juristes modernes comme @Alex_Tsico Ne soyez pas impatient d’être ÉCRABOUILLÉ par l’IA Comme nous médecins Cela va arriver GPT gagne 1 point de QI par semaine Oui il y a des hallucinations Surtout chez les vieux qui savent pas prompter
-
Groq Prepares for Major Inference Expansion Milestone
By
–
We’ve spent the last decade preparing for exactly this. #MoreInference
-
Neural Tangent Kernel: Timeless Mathematical Foundation vs LLM Research
By
–
maybe, but unlike most research e.g. in LLMs, the neural tangent kernel is simply *true* and thus will still be relevant in 5 or 10 or 50 years
-
Practical usage of custom GPTs for productivity tasks
By
–
Been sleeping on GPTs outside of code and writing. Slide Maker and CV Writer are surprisingly solid.
-
The Importance of Contextual Pairing for AI Models
By
–
Most people pick a favorite model and never test. This thread is a reminder that the real value comes from contextual pairing.
-
Using ChatGPT as a full-time intern for automation
By
–
This is why ChatGPT is my full-time intern lol.
-
Gemini 2.5’s quiet builders will outpace larger teams
By
–
Gemini 2.5 is underrated. The people quietly building systems like this are going to be the ones leading teams of one that outpace teams of ten.