I think this will flop. Even amazing halo car EVs have poor resale value, and this one isn't it. It will not keep value like an analog Ferrari, but may be better than Rimac because it's a Ferrari and if they limit supply.

I'm all for EVs by the way, I drive a Model 3 Performance and I love it. Just not feeling this design at all.

It was mismanagement then and it's mismanagement now, the more things change the more they stay the same.

You can use it for free, forever, if you just run the bot in your browser (client mode). Server mode is premium, but you don't need it to run the bots.

I posted about it in this comment: https://news.ycombinator.com/item?id=48085993#48088468

We've been playing with different settings and models since January, older wallets have had some bleed with Gemini 3 Flash and bot settings that didn't perform well.

We've been running bots exclusively on Gemma 4 31B and 26B for the last 7-10 days and they've been either breaking even or trading very well, it really depends on the coin. I think around 10-30% gain for the good cases for the week.

It's still experimental, I only put $100 into each bot (and that's what I recommend to my users) so it's not crazy money, but once we're comfortable we'll put more money into it.

https://vtxmacro.com/leaderboard?t=24h

How many paying clients (companies, not people) do you have?

The bot settings (system prompt and user prompt, temperature, reasoning, etc.) are 100% transparent and customizable, and all users can view and copy anyone else's settings from the leaderboard. The goal is to build the best trading bots possible by seeing what works.

You can run a bot on Gemini 4 31B with a free tier Google AI Studio account (I'm running 5 bots on it myself). Or just run Gemma 4 26B on your PC if you have the GPU for it. I'm running 5 on my 5090, so I'm trading with 10 bots total.

The platform is connected to Hyperliquid and you can trace all the trades on the blockchain from the user's Analytics page (always public).

The way it works is you set a loop interval (default 1 minute) and the model receives the candles, market stats, indicators, account balance, current positions and so on and decides Buy, Sell, or Hold and how many units.

It's still experimental but I have already processed 1m+ prompts, 10k+ trades, and almost $1m in volume since January 2026. I have around 15 bots running right now, you can check their PnL on the leaderboard (public). I've made a lot of changes in the last few weeks so most recent either 24h or 7d results are the most relevant. The model you use is super important (Gemma 4 31B so far is the best value I found, better than Gemini 3 Flash and you can run it for free) and also the coin you choose is important too. Preferably, you want something that's trending. My friend's bot did well with ZEC and VVV this week.

Right now I'm working on improving reliability (I bought a Japanese VPS to run my own HL node), and this weekend I moved the app from Render to my own DC VPS for 10x+ cheaper and 1000x more bandwidth (25 TB instead of 25 GB, seriously if you're using Render and want cheaper infra look into buying your own VPS).

I'm also implementing CLI/MCP for OpenClaw support. And next is an automatic screener that will use LLMs to pick the most promising cryptos to trade (since I noticed this has a huge effect on PnL).

If you have questions, let me know, the Trade page has my Telegram group link.

I'm using Gemma 4 31B in my app with 5 agents, 1.5k requests per day, each.

I was using 100M+ tokens per day, $250 per day or so and only paying $160 per month to GitHub.

I cancelled my GHCP sub and switched to Codex last week, so far so good but I miss Gemini 3.1 Pro for UI work.

Also, the premise that it took each of them a year to do the project means Bob was slacking because he probably could've done it in less than a month.

I built a full stack app in Python+typescript where AI agents process 10k+ near-real-time decisions and executions per day.

I have never done full stack development and I would not have been able to do it without GitHub Copilot, but I have worked in IT (data) for 15 years including 6 in leadership. I have built many systems and teams from scratch, set up processes to ensure accuracy and minimize mistakes, and so on.

I have learned a ton about full stack development by asking the coding agent questions about the app, bouncing ideas off of it, planning together, and so on.

So yes, you need to have an idea of what you're doing if you want to build anything bigger than a cheap one shot throwaway project that sort of works, but brings no value and nobody is actually gonna use.

This is how it is right now, but at the same time AI coding agents have come an incredibly long way since 2022! I do think they will improve but it can't exactly know what you want to build. It's making an educated guess. An approximation of what you're asking it to do. You ask the same thing twice and it will have two slightly different results (assuming it's a big one shot).

This is the fundamental reality of LLMs, sort of like having a human walking (where we were before AI), a human using a car to get to places (where we are now) and FSD (this is future, look how long this took compared to the first cars).

I made my Restailor project open source. You're welcome to use the code in case you're looking for a new job or just want to play around with an LLM integration for this purpose. You're also welcome to use my prompts.

It's working end-to-end and I built the infra to scale and support a lot of users using it (Next.js + FastAPI + Redis + Postgres). It also has applied job tracking and analytics.

LLM integrations are with Anthropic, Google, OpenAI, and xAI.

Please let me know if you have any questions.

Thanks!

Comments URL: https://news.ycombinator.com/item?id=47346676

Points: 1

# Comments: 0

Most of your programming should be DAX plus a bit of worksheet functions. Some SQL to filter your data before loading into Power Pivot.

SQL yes, of course. You run SQL queries to load data into Power Pivot through a native SQL Server driver or native drivers for your DB or worst case ODBC.

Then you do all the BI analytics in DAX and show results in pivot tables. DAX is a very fast, concise and very, very powerful language for analytics. This is the whole purpose of OLAP.

Check out this video when you have time :)

https://www.youtube.com/watch?v=0WwFJ0Zg3d8

At the same time, it can all be done in Power Pivot and Power Query as long as you know how to use them.

Comments URL: https://news.ycombinator.com/item?id=13661373

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=13660933

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=13653902

Points: 3

# Comments: 0

I don't see anything objective about that article, it looks like an opinion piece.

Comments URL: https://news.ycombinator.com/item?id=12951747

Points: 6

# Comments: 4

Comments URL: https://news.ycombinator.com/item?id=12802919

Points: 1

# Comments: 0