ninjaa

For me I had so many

When I saw the DaVinci API in July 2022 I was floored - I realized you'd never have to write a college essay by hand again Whenever it was Stability's Stable Diffusion appeared - that was ridiculous too When I saw Code Interpreter for the first time I was obsessed, I said yo codegen is the path to AGI When I took a crack at solving ARC-AGI 2 using SOTA methods my mind truly opened to the fact that LLMs can reason, albeit through brutal enumeration and discovery When I encountered Claude Code and Codex as well

Basically ... I've been drinking the kool aid the whole time. It has almost always tasted great. Many times I've retreated back into "oh it's just a technology it has limits" and also sometimes I've lost myself to a touch of "AI psychosis". But overall I have a great relationship with it. It's nowhere nearly as addicting as e.g. internet porn was when I was a teenager. And one gig I had at a Fortune 10 enterprise, our small team of 5 shipped 12 apps in 15 months in an enterprise where typically they ship 1 app and 1 feature per year. This was 2025 ... so clearly we realized we were getting ~10x productivity thanks to Gen AI koding.

Bananas.

FTR I also do not question that we will possibly reach fairly general and yet poorly controllable intelligence with multi agent systems in a few more iterations. I give that a 30% chance of seeing a genuine flash of that at some point in 2027. And 80% in 2028.

I'm not yet afraid of being left behind this is one happy Lobster.

What does Jim Cramer have to say?

At OpenAI's DevDay 2025 there was a talk called "Shipping With Codex", where Aaron Friel was introduced as tbe world's top user of Codex. He explained his method and said he would open source it soon. He hasn't yet AFAIK, so I have.

I find the technique mind-blowing efficient and efficacious. It has transformed my productivity completely. YMMV but take a look!

Excited to hear how you guys are getting your coding agents to do bigger and bigger tasks autonomously.

Don't call it a coverup

Lol students fake stuff. These actor-less statements got to go for humanity's sake.

IMO all digital content is going to have to be signed so the provenance trail can be crawled by an AI across devices.

https://aditya-advani.medium.com/how-to-defeat-fake-news-wit...

My $0.02 please

Recommended plan 1. Find a new-ish laptop immediately. You can get a decent used one for $1K on backmarket.com. Invest in an ergonomic mouse and an iPad for 2nd monitor as well. 2. Do only high value tech work that pays or you learn something that will pay. Be hungry and stay homeless but do not work as an Uber driver it's a poverty trap by design. 3. Find a host family, welcoming community or marry up. You can't beat depression or get back on your feet alone. One suggestion is: go to SLC and get involved in Hacker and / or rock climbing communities.

Def get rid of the desktop computer. You don't have a desk and are unlikely to for long time.

Again my $0.02 please it's hard but you're on the right track IMO

wow congrats!!

Really simple react client that uses WebRTC to connect to OpenAI's Realtime API

Great starter template

TL;DR We do codegen using Gemini for 3Blue1Brown's amazing Python math animation library Manim.

Generates awesome explainers, even when the topic is probably not part of the pre-trained data. They aren't production quality of course, but fairly accurate and great explainers. I liken it as relatable to a whiteboard session.

Looking forward to feedback - especially on how we can make the output better and do LLM evals as well!

GNU has a really concept called the GNS for Gnu Naming System. And what it was was that each human or org would have their own tld directory, and we could navigate the web through other actors, and they could pass trust for zones on to others. So, for example, I could resolve the same page as somepage.ninjaa.site or someotherpage.adept.site. This way you could create a trusted internet by just trusting the published link tld directory of people & institutions you know.

https://datatracker.ietf.org/doc/html/rfc9498 https://en.wikipedia.org/wiki/GNUnet

Oh that's pretty smart

I use BaseQL which is a GraphQL layer for Airtable. It's worked for 3 years. For performance reasons after we translated our catalog we had to put in postgres + hasura as middleware but we still use BaseQL all over. It's rad. https://www.baseql.com/

Being able to get data joined across sheets is priceless.

This is pretty awesome. Memex world

This is super great. The core mechanic is absurdly great and works much much better than I expected.

I also see that it's not an end-to-end language tutoring solution but a companion you can use to test your real-world language skills. Awesome stuff.

If you're interested in reaching out to real language schools, I run a marketplace for pre-college programs, Language Schools are like 20-30% of our business. Let me know!

I am happy though, that we finally may talk about what our unfiltered thoughts are, and how much we are expected to control them or curate them, and how to do so in a psychologically helpful way.

Urlbox has a beautiful website. And the invisible calendar is beautiful too. Would it happen to render multiple calendars concurrently? (I share an office, seems like the perfect xmas gift)

It's Dickensian out there Like the ghost of Tom Joad

This is a great idea. One suggested improvement is if I could resume tracking time on a previous item. If so, I would use consider using this app to track time spent on various projects.

Great UX direction, cool idea, congrats on launching! Was fun and easy to play with.

Code interpreter likely solves most of these: https://aditya-advani.medium.com/mitigate-gpt-4-hallucinatio...

I argue that with Code Interpreter, GPT-4 can indeed reason in lots of cases, although it's more brittle and expensive than it seems to be on the very polished surface level. Working on proving this in lots of cases.

They keep trying this shady type of thing every few months

smart

Stability, runway, my father had a bankruptcy where he was accused of having his hand in customer funds. I strongly believe the right kind of partner can unlock incredible wealth in this case.

It's a B2C business with a B2B side (we also sell to schools and affiliate with SAT courses and college counselors).

What I meant was that when going out for fundraising in Silicon Valley your financial model is often compared to that of a B2B SaaS as they are both asset-light web software companies. Having studied those, I now realize why investors are so gung ho on B2B SaaS. The relative predictability of success, high profit margins, stickiness and network effects are quite simply hard to beat.

At the time, we didn't know where else to get $500K-$1.5M. Turns out $220K and some pain and hustling was enough. Thank God the fundamentals are really sound and upside is really there.

Now we're more looking into nondilutive funding and our lines of credit are burgeoning so it's possible VC won't be needed altogether. Not ready to close the door yet though, especially to the most selective programs and institutions both now and down the line. If we got into YC we would definitely accept, or even some other selective program like NFX FAST we would definitely consider very seriously.

I spent a long time thinking about business like this after a decade and a half of hard knocks in SaaS and marketplaces where I simply hadn't been thinking clearly at all. That's how we came up with Best Parents (www.bestparents.com) in 2020. It's the first marketplace for high-end, in person, short courses and travel experiences for teenagers worldwide. My wife has expertise in the education sales industry from Turkey and Europe, for me deciding to jump into this particular business with her involved reasoning from my first principles, which greatly overlapped with the ones presented here in this doc. So this post is my confirmation bias speaking!

About Best Parents

1. It sells the world - we have customers from over 30 countries now

2. Demand is inelastic - families are always going to seek out programs for their kids abroad / away from home

3. Cannot easily be substituted or copied - the suppliers have to trust you, that trust has to be earned over years

4. Minimal labor requirements - our website is automatically translated into 4 languages with AI

5. Enjoys low overhead

6. Does not need big cash outlays

7. Cash billing - we have a 6 month billing cycle, we hold all the cash

8. Relatively free of regulation - also common sense prevails

9. Portable / easily moveable - we live in SF but have spent 3 or 4 months travelling this year

10.Loads of fun intellectually - thinking about how AI can guide teenagers to better and more diverse experiences, teach them and their families how to appreciate and contextualize those experiences, teach suppliers what to offer and how to improve their offerings ... v fulfilling. Feels like the real future of education

11.Leaves me with some free time now, prospectively lots later. Still just our startup's second year in sales, my first year full-time, lots of product to build

12.Income is not limited by personal output

What I was surprised by was how little VCs in general seemed to respect my reasoning. I had not been anticipating that kind of a tepid reaction. There's a lesson I learned here - that the businesses VCs are generally looking for are far from the ones entrepreneurs logically probably want to consider. I believe that after the popping of the crypto bubble the whole ecosystem as it recovers will wend its way back to a more balanced, forward looking place where enriching the lives of children and helping families overcome their generational trauma by joining an international parenting community is seen plainly by many as exactly what it is - world-changing and relevant.

Another thing I did come to realize was just how sweet a business B2B SaaS and Enterprise SaaS really is. Wow. It's a money printing machine, makes marketplaces look relatively paltry even though eBay was "The Perfect Store" like the book @Animats cited. Oh well, at the end of the day the business has to satisfy your intellectual and emotional needs for you (i.e. me) to give it that 150%. And this one's a winner with 20%ish gross margin and really decent basket sizes.

Dropshipping is a great business idea. Amazon's price fixing has made it a zero sum game

Interested. I currently use GPT to write the majority of my commit messages and catch bugs at commit time.

Great idea. All my scripting is in Python so waiting for that SDK!

Looks dope

Did this end?? There's nothing after Feb 28.