Building verification layer @PramaanaLabs
Palo Alto, CA
Joined November 2021
- Tweets604
- Following404
- Followers445
- Likes15.8K
Mit Dave retweeted
483 days ago, @5aitec and I raised $20M from @binnybansal to build ShopOS
Millions of brand images and videos later we learned: the model was never the hard part. Getting it right the 10,000th time is
Today, we’re launching @sloosh_ai to give every creator that secret sauce 👇
Mit Dave retweeted
Current Frontier LLM models hallucinate with Tax queries on phase-outs, miss quadratic interactions, and leave money on the table; all while sounding confident.
Formal verification of these outputs at run-time is the only meaningful way to address this.
Cell-by-cell 1040 modeling + machine-checked proofs that your tax plan is compliant and provably optimal. Audit-defensible. Fearless.
Authored by: Yoshiki Takashima
Read how we turn complex tax optimization into verifiable truth → pramaanalabs.ai/blog/audit-d…
Mit Dave retweeted
The room I wanted to be in when we started Pramaana didn't exist. The people working on formal verification weren't in the same room as the people deploying AI into regulated domains.
One year later, we're building that very room.
June 10th, San Francisco.
verificationsummit.ai
Outputs that sound right are not the same as outputs we can prove right.
The next phase of AI runs on verified systems: formal methods, theorem provers, runtime checks, provable agents.
It's time to verify AI !
Join us on the 10th of June at SF !
@PramaanaLabs @boldcapfund
Mit Dave retweeted
We are hosting the launch edition of verification summit.
A technical-first gathering for engineers, founders, researchers and practitioners building verified AI & formalization for real world domains.
Apply: luma.com/597otp0a
verificationsummit.ai
Q.E.D.
Mit Dave retweeted
Building a general-purpose AI agent with only open-source models is hard. Making it consistent, reliable, and fast enough for production usage is even harder.
We at @SentientAGI have been optimizing both👇
Today we’re revealing SERA (Semantic Embeddings & Reasoning Agent): the AI architecture behind SERA-Crypto, our state-of-the-art agent for token research, DeFi analysis, and on-chain reasoning, combining 50+ APIs into market insights.
👉 #1 open-source agent on DMind, ahead of Perplexity Finance & Gemini, within ~2% of GPT-5 Medium on Web3 reasoning
👉 #1 on our live crypto benchmark (198 real user queries across 11 categories), beating GPT-5, Grok 4, Gemini 2.5 Pro, and Perplexity Finance
More in 🧵
Mit Dave retweeted
all the cool meetups / hangouts / potlucks happens in san francisco
but who are the people living in south bay? (like me)
reply below / tag the people you know, for something ☕️
rt, spread the word
tl;dr want to make friends in south bay too (sf friends are cool too lol)
👇
Mit Dave retweeted
Your outie handles every single error by pattern matching Option/Result types. No exception goes uncaught. He carefully defines React error boundaries with helpful user messages.
Mit Dave retweeted
The new NBA Tabletop view on Vision Pro is one of the coolest things I’ve ever seen!
Here’s a slightly longer video than my usual to show you the experience.
Mit Dave retweeted
Millenials are the final generation to not be internet and AI native. In fact, they grew up with frontiers.
It's important for us to share the tactile and analog nature of our work so designers and engineers don't default to AI slop.
Teach the craft.
Mit Dave retweeted
@sentient_agi **Loyalty and Wealth creation in the era of AI**
AI will align humans into new communities — new digital countries — with their own values and aspirations
Closed AI cannot be trusted for this. It is manipulative and has hidden agenda
We must build Loyal AI which is *open* and *controllable*
Mit Dave retweeted
📢 We’re excited to release the AI fingerprinting library that we’ve been developing since our whitepaper in September.
This OML library enables fingerprinting AI models, making it possible to prove who owns an open AI model. Here is to AI loyalty.
github.com/sentient-agi/oml-…
Mit Dave retweeted
Come build AI agents powered by open source LLMs @agihouse_org that play Werewolf! Attending invited speakers include:
@tydsh Meta AI Research Scientist Director
@Chi_Wang_ AutoGen Founder
@sewoong79 UW, Data Comp
@hstyagi Sentient Co-Founder
Register by: Oct. 28th below 👇
Mit Dave retweeted
Werewolves, wake up. Who do you choose to eliminate today?
Reason, deceive, expose. Welcome to the first ever Werewolf Agents Tournament.
Teams will build AI Agents that will battle in a giant Werewolf (aka Mafia) Arena at AGI House in Hillsborough.
This dynamic environment presents a unique competitive system for testing the advancing capabilities of agents fully built on open source AI models. We believe such environments will be key to the path towards community-built open AGI.
Apply if you have what it takes: app.agihouse.org/events/agi-…
