🗿

[Google Research @GoogleResearch]

Introducing GlucoFM, a lightweight, self-supervised continuous glucose monitoring foundation model that separates metabolic baselines from transient spikes, producing transferable representations and setting new performance standards across diverse metabolic prediction tasks, such as diabetes risk assessment, insulin resistance, and post-prandial glycemic response.

Learn more →https://t.co/PA7wpFz2xo

[🗿 @moaienthusiast]

Return of the King

[Avi Chawla @_avichawla]

The most comprehensive RL overview I've ever seen.

Kevin Murphy from Google DeepMind, who has over 128k citations, wrote this.

What makes this different from other RL resources:

→ It bridges classical RL with the modern LLM era:

There's an entire chapter dedicated to "LLMs and RL" covering:

- RLHF, RLAIF, and reward modeling
- PPO, GRPO, DPO, RLOO, REINFORCE++
- Training reasoning models
- Multi-turn RL for agents
- Test-time compute scaling

→ The fundamentals are crystal clear

Every major algorithm, like value-based methods, policy gradients, and actor-critic are explained with mathematical rigor.

→ Model-based RL and world models get proper coverage

Covers Dreamer, MuZero, MCTS, and beyond, which is exactly where the field is heading.

→ Multi-agent RL section

Game theory, Nash equilibrium, and MARL for LLM agents.

I have shared the arXiv paper in the replies!

[🗿 @moaienthusiast]

@Riazi_Cafe_en sin(x!)?

[🗿 @moaienthusiast]

@ethan_leee9113 If ur on a budget tho for replacement these are kinda goated

https://t.co/MXNkBknJ0D

[🗿 @moaienthusiast]

@ethan_leee9113 F in the chat

[🗿 @moaienthusiast]

@Justin01805921 Do u use temporary chat? Has morphed into my go-to in recent months

[🗿 @moaienthusiast]

@ethan_leee9113 Respect

[🗿 @moaienthusiast]

@eunifiedworld Who the hell uses Apple sign in?? @eunifiedworld

[🗿 @moaienthusiast]

@thesigmamindset @grok who said this

[🗿 @moaienthusiast]

@ethan_leee9113 Yea but who's making the agents? Malware vs. antivirus is just the lite version. The real shift comes when autonomous agents create and evolve malware purely to stress-test systems, no humans in the loop 🗿

[🗿 @moaienthusiast]

What if the future of software dev is just AI gladiator matches

One agent attacks your app

Another defends it and tries to patch up bugs

Winner evolves

Loser gets deleted

Natural selection, but for code

[🗿 @moaienthusiast]

Didn't know Pepsi was this expensive :(

[ksa 🏴‍☠️ @kosa12m]

lol 4 items at the store is now $1,981.64 in this economy.

recession is crazy

[🗿 @moaienthusiast]

@kchoudhu Start by assuming that a^m * a^n = a^(m+n)

Then substitute n = 0, so we get a^m * a^0 = a^(m+0)

Since a^m * a^0 = a^m, then a^0 must be 1

[🗿 @moaienthusiast]

@ethan_leee9113 🗿

[🗿 @moaienthusiast]

@aidenybai definitely b

[LuxAlgo @LuxAlgo]

🚨 Powell coming in to save the market after 5 red days

[🗿 @moaienthusiast]

MLE is just
Step 1: Guess parameters
Step 2: Be wrong
Step 3: Guess harder

[Tivadar Danka @TivadarDanka]

I am an evangelist for simple ideas.

No matter the field, you can always find a small set of mind-numbingly simple ideas making the entire thing work.

In machine learning, the maximum likelihood estimation is one of those.

Read on to find out why:

[🗿 @moaienthusiast]

What is the optimal number of interdisciplinary skills one can have, such that they can still be very effective in all those domains

[🗿 @moaienthusiast]

@thegravitonick congrats

[🗿 @moaienthusiast]

@martinmrmar Good for you :)