
making models design better @kritapp • I’m gonna be king of the Pirates.
Joined June 2014
- Tweets1.4K
- Following970
- Followers1.1K
- Likes5.6K
Jaideep Singh retweeted
After years of being an AI Engineer and growing @myreader_ai solo to 100k+ users, I have decided to offer up my services to existing businesses.
If you are a business and want to implement AI in your organization - build AI agents, automate workflows, figure out the right AI setup for your team, I can help.
No promises but I know way too much that a single call can probably save you thousands.
Only opening up 1-2 slots for businesses that really need help.
If interested, DM me.
Jaideep Singh retweeted
Today I am launching a live translation app for Beta - Ouvir.
It can live translate any language to any language in any scenario - dinner table, tours, meetups, coffee shops. Just put it on the table or in your hand, put earphones in and listen in your native language.
Hardest part was capturing audio properly in noisy environments to which it does pretty well.
Sign up for beta here: ouvirtranslate.com
Jaideep Singh retweeted
How did that random company get your email address?
You gave it to them. So did I every signup, every "download the PDF," every checkout.
So I built Maski. A different email address for every service you use.
It's live today 👇
Jaideep Singh retweeted
wrapped up my time at @GigabrainGG this month.
got to build something I'm genuinely proud of. learned a ton working alongside @0xchetan .
grateful for the ride. best wishes to the team and everything coming next for them.
as for me, actively looking for what's next. if you're building something ambitious and need someone who ships fast, let's talk 🫡
Jaideep Singh retweeted
Your motivation on an idea is the reason you will keep working on it not whether market wants it or not.
Jaideep Singh retweeted
We need to stop talking about product design in absolutes… there are no rules. Everything is made up. Do what makes sense and feels right.
Jaideep Singh retweeted
Meowmail now lives in your browser 🧩
• one-click temp address generation
• real-time inbox - emails arrive instantly
• read full emails right from the popup
• zero sign-ups. just a clean disposable inbox wherever you are.
Jaideep Singh retweeted
just launched meowmail—temp emails without the noise. no ads, no spam, no sign-ups. you get a clean inbox you can actually make your own. worth a try if you need it 🔒
feedback & thoughts appreciated! 🙌
seems obvious but:
things that are changing rapidly:
1. context windows
2. intelligence / ability to reason within context
3. performance on any given benchmark
4. cost per token
things that are not changing much:
1. humans
2. human behavior, preferences, affinities
3. tools, integrations, infrastructure
4. single core cpu performance
therefore,
ngmi:
1. "i found this method to cut 15% context"
2. "our method improves retrieval performance 10% by using hybrid search"
3. "our finetuned model is cheaper than opus at this benchmark"
4. "our harness does this better because we invented this multi agent system"
5. "we're building a memory system"
6. "context graphs"
7. "we trained an in house specialized rl model to improve task performance in X benchmark at Y% cost reduction"
wagmi:
1. product/ui
3. customer acquisition
4. integrations
5. fast linting, ci, skills, feedback for agents
6. background agent infra to parallelize more work
7. speed up your agent verification loops
8. training your users, connecting to their systems and working with their data, meeting them where they are
Jaideep Singh retweeted
I blew up a trade testing my own bot.
Not a bug. Not bad logic. Just needed to see if it worked under real conditions.
That felt stupid. So I built the fix.
Jaideep Singh retweeted
We've raised $6.5M to kill vector databases.
Every system today retrieves context the same way: vector search that stores everything as flat embeddings and returns whatever "feels" closest.
Similar, sure. Relevant? Almost never.
Embeddings can’t tell a Q3 renewal clause from a Q1 termination notice if the language is close enough.
A friend of mine asked his AI about a contract last week, and it returned a detailed, perfectly crafted answer pulled from a completely different client’s file.
Once you’re dealing with 10M+ documents, these mix-ups happen all the time.
VectorDB accuracy goes to shit.
We built @hydra_db for exactly this.
HydraDB builds an ontology-first context graph over your data, maps relationships between entities, understands the 'why' behind documents, and tracks how information evolves over time.
So when you ask about 'Apple,' it knows you mean the company you're serving as a customer. Not the fruit.
Even when a vector DB's similarity score says 0.94.
More below ⬇️
Jaideep Singh retweeted
i'm looking for some help from anyone who is in pharmacology and maybe microbiology to help me validate these findings
spoq-neuro-report.vercel.app
my sister is suffering from a rare disease which is drug resistant, it's a shot in the dark but on paper everything looks sound to me, need expert review before i share with her doctors
i have full pdf on this available with all references, etc.
i can share that in a dm please dm or reply so i can dm you if you can be of any help in this matter
Replying to @prasann_pandya
i have an ai scientist running, going through literature, running computational simulation, creating computationally validated new drugs, novel mechanistic approaches, etc.
for my sister's rare disease
i have spoq-neuro running 24/7, it's not running right now because i ran out of tokens
based on some research low hanging fruits it suggested which i'm going to share with the docs
in theory it's solid
spoq-neuro-report.vercel.app
i'm trying to look for people in pharmacology and maybe microbiology to help me validate these finding, human reviewed and approved added credibility, before i share to her doctors.
Jaideep Singh retweeted
Gatekeeping cancer cure for pharma profits is the lowest human beings could ever go.
Jaideep Singh retweeted
I wanted to build a video editor into X like other social apps. I had expected it to take 3 months of engineering time.
Today I decided to try prototyping it myself. I one-shotted a full in-browser editor in 15 minutes.
It felt like I could replace the entire Adobe software suite by Sunday.
Then I asked myself: will videos even be edited manually in 3 months? Chatbots can do reasonably well now.
Product development is getting extraordinarily difficult when the world is changing so fast.
Jaideep Singh retweeted
The Design System era is dead. Top-down design is forever broken. Having a consistent aesthetic may have been nice in the past, but today there are too many players and too many creative possibilities to dictate a single aesthetic for the entire world. The future belongs to those who embrace the broad multitude of creative expression rather than those attempting to tame it.
Jaideep Singh retweeted
It's no longer about "should designers code", but whether designers should design in code
Jaideep Singh retweeted
🚨 Myreader for Teams — launching next week
Shared library for your org. Upload once, everyone searches.
$100/mo (teams) · $5k one-time (self-host)
Founding rates locked forever. Limited spots.
DM us for early access →
on subtraction
adding is easy. someone asks for a feature, you build it. user hits a bug, you patch it. flow feels blocked, you add a shortcut. new trendy idea, you add a new concept. repeat until you have 50 buttons and no one knows where to start.
the hard part isn't building anymore. it's choosing:
- what to make – and what to leave out
- how to make it – so it strengthens the system instead of fragmenting it
- what to remove – even when it works, if it doesn't belong
addition is momentum. subtraction takes conviction.
you have to see the whole, not just the parts. you have to believe that fewer things, done right, will carry more weight than a hundred things scattered.
most products don't die from missing features. they die from accumulation. from losing clarity. from becoming everything and meaning nothing.
think slower, then act fast. slow down after the burst. tie it all back. so the foundation can carry what comes next.
keep focused, and simplify.






















