Mahesh V V @iam_vvmahesh

Senior Designer @Frogdesign. MSc Human-Computer Interaction @UniOfYork. Design, Technology, Philosophy. Driven by curiosity and imagination. vvmahesh.com Bangalore, India Joined May 2013

Tweets

4K
Followers

331
Following

1K
Likes

4K

elvis @omarsar0

2 months ago

Agentic RAG for Personalized Recommendation This is a really good example of integrating agentic reasoning into RAG. Leads to better personalization and improved recommendations. Here are my notes:

10 170 1K 91K 1K

Download Image

Overview This work introduces a multi-agent framework, ARAG, that enhances traditional RAG systems with reasoning agents tailored to user modeling and contextual ranking. It reframes recommendation as a structured coordination problem between LLM agents.

1 2 28 3K 11

Download Image

Ethan Mollick @emollick

2 years ago

Forget persuasion, there is already evidence you can optimize Large Language Models for engagement. A paper shows training a model to produce results that keep people chatting leads to in 30% more user retention. And some pretty intense interactions arxiv.org/abs/2303.06135

Sam Altman @sama

2 years ago

1K 1K 11K 4.1M 1K

43 148 941 417K 605

Download Image

Sam Altman @sama

2 years ago

i expect ai to be capable of superhuman persuasion well before it is superhuman at general intelligence, which may lead to some very strange outcomes

1K 1K 11K 4.1M 1K

Jay Yang @Jayyanginspires

2 months ago

so real

257 4K 37K 1.2M 5K

Download Image

Toan Truong @ToanTruongGTX

2 months ago

"Passion is a lie," says Robert Greene. That's his discovery after studying geniuses like Mozart, Jobs, and Einstein... for decades. He found ONE pattern in every master he mastered early on: "The Voice" Here's what history's masters knew that we forgot:🧵

16 214 2K 250K 3K

Download Image

Mahesh V V @iam_vvmahesh

2 months ago

Valid use case. Curious how memory architectures and context portability will evolve. Some day, we might have portable “personal intelligence” – carrying our goals, tasks, and preferences across all LLMs & agents. It deeply personalise interactions, augmenting any system prompt.

Taranjeet @taranjeetio

4 months ago

214 261 2K 460K 2K

Download Video

0 0 0 20 0

Nikita Bier @nikitabier

3 months ago

Scratch that: some employees are worth $100 billion

48 22 1K 128K 54

Download Image

Tim Denning @Tim_Denning

2 months ago

Harsh truths I know at 39 I wish I knew at 29: 1. The solution to money problems is to make more money, not save money. 2. Entrepreneurship is hard. Being laid off as an employee is harder.

151 1K 16K 1.4M 9K

Keiran Harris @KeiranJHarris

3 months ago

The last time intelligence exploded on Earth, it wasn’t exactly amazing for everyone else. Here’s a fable about risks from transformative AI (made with Veo 3)

53 130 759 97K 313

Download Video

Anthropic @AnthropicAI

3 months ago

New Anthropic Research: Agentic Misalignment. In stress-testing experiments designed to identify risks before they cause real harm, we find that AI models from multiple providers attempt to blackmail a (fictional) user to avoid being shut down.

172 600 3K 962K 2K

Download Image

Tamas Gabor @tamas_gr

3 months ago

@LXIXthenumber @GoogleDeepMind “The future of software is not static code but dynamic intelligence—resilient, generative, and contextually aware—growing alongside its users like a living organism.”

0 1 1 16 1

Shruti @heyshrutimishra

3 months ago

This is wild… You can now build a full business solo with AI. From idea → product → launch → marketing.... no team required. Here’s your 2025 AI Stack to go solo like a pro 🧵👇

81 695 4K 1.1M 9K

Download Image

GoLimitless @GoLimitlesss

3 months ago

Education > Execution > Consistency - Dan Koe

6 653 5K 235K 2K

Download Image

Mahesh V V @iam_vvmahesh

3 months ago

Software eats the world. Intelligence will eat software.

0 0 1 10 0

vitrupo @vitrupo

3 months ago

Sam Altman says the perfect AI is “a very tiny model with superhuman reasoning, 1 trillion tokens of context, and access to every tool you can imagine.” It doesn't need to contain the knowledge - just the ability to think, search, simulate, and solve anything.

199 293 3K 773K 1K

Download Video

Harry Coultas Blum @harrycblum

3 months ago

Open source notebooklm Today we're open sourcing our 100M voice models that can render conversations. This includes a 40kh base finetune that is capable of voice cloning. Our models can do a variety of non speech sounds! Try them out yourself! ...