Hacker News new | past | comments | ask | show | jobs | submit | elie222's comments login


Full Stack AI, fsai, is a CLI that uses AI to build a full-stack app for you.

It generates 100+ files of code.

The AI will:

Generate a Next.js app with TypeScript and Tailwind Add shadcn/ui for frontend components Generate pages to create/update/delete data Generate a Prisma/Drizzle schema Add auth via NextAuth.js with GitHub/Discord/Google/Apple log in supported Add account screen to change settings Add Stripe for payments Add Resend to send transactional emails Generate CRUD APIs Add light/dark mode


Tutorial on the new ChatHN library for querying Hacker News with Open AI.

The video explains how the project works behind the scenes.


Created a 5-minute tutorial on how Chart GPT was created:

https://www.youtube.com/watch?v=hDfKFYVQjEM

This video will help you understand the code behind the GPT projects you see popping up on your feed daily, and how to create something like this yourself.


They haven’t lost 16b though.

Unclear if we have accurate info from Sam but the situation is more like 9b in liabilities with 70% of that in liquid and illiquid assets. People getting back that much is highly optimistic but the 16b doesn’t seem accurate at all. FTX already paid users out $5b btw


> 9b in liabilities with 70% of that in liquid and illiquid assets

They have $9B in liabilities, and realistically they have about $1B in realisable assets. On the balance sheet Sam has included about $7B worth of Serum and FTT, both of which vastly exceed their circulating market cap and are also effectively worthless as the businesses they represent have lost all credibility and/or are insolvent (Serum is a decentralised exchange created by FTX)


It's pretty clear that "info from Sam" can't by trusted


The starting point is the assumption that FTX's equity sales left them with a few billion and Alameda's trading left them with a few billion. You have to burn through these billions and then dig a ten billion dollar hole.


That's one case in 2008.

If volume and stakes are low then sure, they're not too reliable.

If you don't think prediction markets aren't great predictors you should make bets against that market. If you're a better predictor than the market you should make good money. In practice most people can't outguess the market. Some experts can and do make good money.

The reason markets are a good predictor because as soon as an expert sees the market make a bad prediction, they'll make a bet against the market. This in turn will move the price towards the true price. Assuming there are enough experts out there with large enough pockets (which is true for popular bets) then the market will quickly reflect the experts' view of events which is by definition very hard to beat (you have to be more expert than the experts).


Learnt a lot from this.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: