Priyam Ghosh

documenting our journey so far for solving hyper-personalization in AI Agents.. a ver crucial step towards solving for AGI.. All this started as a vague project idea with @venky1701 ..making a website that helps researchers read research papers more easily.. but not like Anara or any other websites like that.. The idea was to help researchers in a very natural way..to keep this essence of reading papers..not just drop them AI summary which most of these websites do..basic RAG systems.. Our idea overtime evolved.. - Making Memora initially.. a SDK that gives memory to AI Agents but the engineering behind was not upto the mark nor it was well thought.. - We slowly re-thought the whole idea and landed on building infrastructure for the next generation of AI Agents. - Hence MetaCognition Labs was born.. we are very close to solving for self-evolving memory substrate. - Our whitepaper and public pre-print are ready and which be shared soon. We at MetaCognition Labs, are solving for the most crucial part inside human brain... Memory. Crazy to have @venky1701 @sauhard_07 in this venture. Stay tuned for the biggest drop.

We just wrote the first-ever Ebook on Context Engineering and AI Memory Over the past few months, me and my team have been accumulating all knowledges and materials we've read so far while building @metacognitionai . Here's a glimpse of it. We break down things going on today in this domain and also connect possible Neuroscience frontiers at the intersection of context engineering. Post reading this, you can literally build your own context engineering company from scratch. We're planning a long-form course on this as well. Releasing it soon for some people to review. Comment below or reach out to me on DM to get access :) cc: @PriGoistic @sauhard_07

@venky1701 @metacognitionai if interested to know more reach us out !

Here is MetaCognition (@sauhard_07 , @PriGoistic @venky1701 ) submitting our video for round 2 of Vibecon by @emergentlabs and @ycombinator LFGG!!!

@hannahkmi hii, interested in working on the team, checkout my profile and let me know!! prigoistic.me

@eddybuild prigoistic.me Check out me profile and lmk, interested to connect and work

@venky1701 🙈🙈🙈

Things my co-founders do 5am in the morning

We're flying around the Moon. Come watch with us. Live coverage of Artemis II prelaunch activities begins Friday, March 27, when the crew arrives at @NASAKennedy. Here's the full Artemis II event schedule — keep checking back for the latest updates: go.nasa.gov/4s0lHjB

If satan was ugly and unpleasant, no one would fall for his trickery.

so i was revisiting oops after few years and remembered the struggle i had initially understanding it.. so many terms and their works feel similar.. but i am a hardcore gamer.. and i knew games where the best applications of Object Oriented Programming.. and back in the day at school during 6th-7th grade.. it was only about Clash Royale... so i thought why not write a blog around OOPs taking inspo from principles in Clash Royale.. if you are someone who struggles with understanding OOPs concepts and having an intuition around it.. Do give it a read !! prigoistic.me/blog/oops-thro…

Energy dynamics are brutal, wdym I have to understand Free Energy States and quadrillion hypothesis and theorms just to force everything down to convergence through marginal approximation in graphical models????

@jenish1235 hey claude send money to my bank account type shit

The way we all are paying for bunch of system prompts #aiistakingover

lately I have been spending a lot of time thinking about the brain not just in a philosophical way but in a mathematical way.. I have been diving deep into computational neuroscience trying to really validate the maths I have been building and grounding it in how biological memory systems actually behave. the more I study it the more I feel like spectral graph theory diffusion and iterative solvers are not just abstract math concepts they genuinely resemble how the brain stabilises forgets consolidates and compresses meaning... I wrote a long piece connecting spectral graph theory with advanced memory dynamics in the human brain. if you feel you fw this then give this blog a read and if you are a specialist in this field..do reach me out if you feel to discuss on this further. prigoistic.me/blog/spectral-… also check out @metacognitionai this is something we do here everyday.

@barticz how do i apply ?

For founders who dream harder. pucek.capital

"Building in our discoveries only make it harder to see how the discovering process can be done" and somewhere at @metacognitionai we are building a system which lets itself self-evolve as per the user, not because of what it has discovered but because it has the ability to do.

I was reading an famous essay by Richard Sutton, titles The Bitter Lesson, talking about the flow and development of AI research however, the ending line really intrigued me. "We want AI Agents that can discover like we can, not which contains what we have discovered"

Felt the judging was a bit non-technical oriented but yah have to deal with it at the end. Connected with Founders at Runable !! And got some descent merch!

Participated at @runable_hq Ship it Sprint. The organizing team was really cool and cooperative. From the schedule to food everything was flawless. Well we didnt win cause our product wasnt compatible with running on Runable.. which was one of the criteria for the sprint.

a step closer to launching !

well interesting updates, we have achieved spatial intelligence !! ( kinda) currently the system is still based on a verifier system but yah close to making actual world models. Coming Soon. Build Tomorrow. Today.

@arpit_bhayani @metacognitionai this is how we plan to solve for it.

Everybody keeps saying AI memory is going to be huge. I have been reading about it and building on it for weeks now, and honestly, I am struggling to see why. RAG, multi-RAG, and their variants can solve most real problems. Memory really comes into play only when you need personalization. The number of use cases that actually require deep, user-level personalization is pretty small (CX support, healthcare, etc.), where continuity matters. Even those can usually be handled with RAG and its variants. Is it all about being able to update memory as new evidence or data shows up? So why is there so much discourse and discussion around memory? What big use case is everyone trying to cater to here? Please educate me :)