fomoz

Thanks for posting. It's an interesting concept, but needs some work in my opinion.

First, that chart is super zoomed in. You can't zoom out or switch timeframes. You're not told how many bars you need to predict. You're not told the dates or what the stock is.

Not much you can see there other than a handful of candles, that's doesn't really tell you much.

If the stock and dates are a secret so people don't cheat, I don't see why. People can cheat on Wordle or Worldle, and they're still fun to play. But here you're basically just guessing, you have so little information it's basically a coin flip.

That's very true. I realized it myself when I worked on my first app, I made a resume tailor last summer back when GPT 5 just came out.

Then, by the time GPT 5.5 came out you could already generate a flawless PDF and Word doc resume with the same formatting as your base resume. It really is amazing.

Trying to compete with these labs is a bad idea, you might work hard on your thin wrapper and then they come out and have their chatbot or harness do it way better than you.

But I also think this is really cool. It's a new era in software. Build something worthwhile and you won't need to worry about a lab doing the same thing with their chatbot.

This is a useful site.

I've been enjoying the resets, plus I had 3 resets I haven't used.

Just using 5.6 Sol in Fast mode the whole time, 1B tokens per day.

However, when they removed the 5h limit they also quietly lowered the 5.6 Sol context from 354k to 258k or something like that. I noticed it in Codex.

5.6 Sol High Fast is using more capacity than 5.5 High Fast, I hit the 5h limit for the first time.

Other than that, I think the difference between 5.5 and 5.6 will be the same as 5.4 and 5.5. 5.5 is just less frustrating to use, although not perfect and still has derp moments. But a lot less than 5.4.

So I expect 5.6 Sol to be smoother to use. But so far it just feels slower. We'll see.

Ding, came here wondering the same. I do find it amusing, this "AI work" where people try to solve an issue and the lab (or whatever you want to call them) just makes the entire problem moot.

Got it, I got confused then. Would be good to see how it compares, Codex is quite generous for the $200 with GPT 5.5. They give a lot of resets, I just use mine in Fast mode (1.5x speed, 2.5x usage) almost all the time. But it's not exactly fast.

This is what I don't understand. Why would I use this "cheaper" model when it's still going to be more expensive than Codex on the $200 plan? Are they only targeting business users who pay per token?

I think it depends on whether the answer is verifiable.

I have tested two judge models in my apps:

1. Judge model for a resume tailor. It evaluated the result resume vs the base resume and JD and judged it out of 10 on fit and honesty. It worked well and was useful.

2. Review model in my LLM trading bot platform. It reviews decisions from the Main model. The problem here is that the bot is navigating ambiguity. So unless the Review model catches an outright blunder (e.g. making a decision on wrong candle price or a BUY when it should be a SELL), the Review model can do more harm than good.

First, it adds latency to decisions, decisions take twice the amount of time (like be 60s instead of 30s for Gemma 4 31B). Second, it can make the bot too cautious, because Review model only runs on BUY/SELL decisions and not HOLD decisions, so the bot will only make less trades instead of review model increasing number of trades (because of latency and cost).

So overall, I think you'll get better results with a better model single shotting it rather than a review model if the answer isn't easily verifiable. But then why do you need a judge model and not just have the same agent review itself?

ALSO, if you read the reasoning text for a reasoning model (like Gemma 4), you see that it ALREADY reviews itself. So it's doing its best, re-review isn't really adding information. It's an interesting experiment, but you need to evaluate on a case by case basis.

Cayenne wasn't $647k USD.

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.

I haven't worked in corporate since last year but I keep seeing people complaining that "bosses" are forcing workers to use AI now. I find this so amusing because in 2023-2024 I had to fight to either be allowed to use AI at work (even just MSFT Copilot chatbot) or get a ChatGPT Enterprise license.

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

I use it on my LLM trading bot platform: https://vtxmacro.com

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

You can check in detail on the leaderboard, but I suggest you look at the last 24h to 7 days.

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

2,000 daily users is 2,000 separate paying businesses that use your app or you count one business with 2,000 employees as 2,000 users?

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

I'm working on https://vtxmacro.com, a free and fully autonomous LLM trading platform. Basically have any model you want trade for you. Right now I support ~860 models across 16 providers (including OpenRouter), plus Local AI and OpenAI Compatible endpoints.

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.

You can use it for free with Google AI studio (free tier or paid tier accounts with different limits). Or use the paid version from Vertex AI which is around 3x cheaper than Gemini 3 Flash.

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

Bingo. I created a few autonomous skills that did exactly that for plan review, implementation, and branch review, review autonomously until green.

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.

It's the next level of abstraction. Bob is still learning, he's just learning a different set of skills than Alice.

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.

AI is an accelerant, not a replacement for skill. At least, not yet.

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).

You can leave memory enabled and tell it to not use memory in the prompt of it's interfering.

If you need to use C# in Excel, you're doing it wrong. There's very little programming that you should be doing with VBA, too.

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

Cool IDE, cool project.

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

My bad, corrected the title.

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

Leangains IF assumes that you track your macros. I was just talking about your feeding window influencing hormonal entrainment (ghrelin).

It's actually a sign of insulin over-secretion rather than poor insulin sensitivity.

However, in practice, there are signs as to whether you have good insulin sensitivity or not and possibly whether you over-secrete insulin. Here’s two very simple questions to ask yourself regarding your response to diet.

1. On high-carbohydrate intakes, do you find yourself getting pumped and full or sloppy and bloated? If the former, you have good insulin sensitivity; if the latter, you don’t.

2. When you eat a large carbohydrate meal, do you find that you have steady and stable energy levels or do you get an energy crash/sleep and get hungry about an hour later? If the former, you probably have normal/low levels of insulin secretion; if the latter, you probably tend to over-secrete insulin which is causing blood glucose to crash which is making you sleepy and hungry.

http://www.bodyrecomposition.com/fat-loss/insulin-sensitivit...

I've been doing Leangains style IF for the past four years. I'd like to share a few quick tips.

If anyone here wants to try intermittent fasting, do it for the sake of convenience. I don't eat breakfast or lunch, I just eat when I get home from work or after weight training. On weekends I break my fast earlier than on weekdays.

I wouldn't say you should do it for the "benefits" if it doesn't fit your lifestyle. Right now all we know is that it's not bad for you. It does work pretty well for hunger control, which can help if your goal is weight loss.

Also, don't live by the clock. It's OK to eat outside your feeding window, you might get hungry later during the day and the next day you might get hungry earlier.

Here's a guide if you're looking for a place to start: http://www.leangains.com/2010/04/leangains-guide.html

Here's a good article if you have general questions about IF: http://www.leangains.com/2010/10/top-ten-fasting-myths-debun...

Psychedelics aren't about pure visuals. They're more about meaning.

That's crazy amazingly awesome. Need to know how much it costs though, both camera and film/processing/cloud.

Start here:

http://www.bodyrecomposition.com/nutrition/a-primer-on-nutri...

http://www.bodyrecomposition.com/nutrition/a-primer-on-nutri...

Then explore the rest of the site: http://www.bodyrecomposition.com/nutrition

When you're ready, start reading LeanGains:

http://www.leangains.com/2010/10/top-ten-fasting-myths-debun...

http://www.leangains.com/2010/04/leangains-guide.html

Lustig just doesn't give up. He has already been crushed by Alan Aragon five years ago.

http://www.alanaragonblog.com/2010/02/19/a-retrospective-of-...

Bulk coffee doesn't yield revenues of $1.00 per cup.

Clients get the convenience of an all-in-one machine for all their caffeinated drink needs, Keurig got $4.358 billion in revenue in 2013.