8bitsout

he's been cycling a lot

What a bizarre and frustrating "feature". I was bewildered when that was first introduced. Glad I'm not the only one frustrated by it.

I did too

there is a missing step: "believe in yourself"

so is coding solved or no?

That's correct, there is no reference to AIvestor in the article you shared. However, the parent comment of this thread, the one I responded to and the one you are responding to, shares the link to your AI slop product. Once again, I did not have to dig through Google at all - it's all available on your product page. You're repeatedly proving how dense you are.

You literally have a link to your Github on your SaaS product - are you that dense? You included your whole profile on there. It took me no more than 5 minutes to click it, see that you have a repo related to your product, and view one source file of AI slop.

Anyway, I stand by what I said. Advertising with "Look, AI picked my stocks and number went up" is disingenuous.

From the website:

"Quant Competitions Achievement

In 2024, I achieved 7th place at Quantiacs, a global quantitative trading competition. With a background in financial software, I built AIvestor to democratize AI-powered investing tools that were previously only available to institutions."

I have no idea of the legitimacy of Quantiacs, but for someone with these claims what they are selling is extremely unfaithful. Anyone with a sufficient knowledge of markets would understand the issues with what is being presented on the "portfolio" page, and the approach is bunk.

It appears that the product is based on some vibe-coded slop (https://github.com/LaurentiuGabriel/gpt-trading-agent). I personally would feel bad even thinking about trying to sell something like this to people.

I thought LLMs were a great tool for learning new topics - perhaps even complex ones. But overtime, I have had several frustrations with this. First, I get exhausted reading LLM prose. I really don't want to read anything generated by something like Opus 5 at this point. Second, as I dive deeper, I need a way to organize the information in a useful way as I begin to branch out in many different directions. I have tried to use the LLM to fix this by having it generate a web page with diagrams and organized information flow. It's an improvement, but I still run into the issues I described in my first pint - LLM prose is annoyingly dense, and the useful information gets lost in a bunch of noise. You can direct it do something like "use plain English and avoid LLM prose - provide only as much information as necessary to demonstrate the point", but it is once again only a marginal improvement.

And then I begin to think to myself that I should just read a book on the topic written by a trusted source who put a lot of effort into teaching the topic properly and presenting the information in a thoughtful way. So, I am back to books and mostly try to use LLMs to clarify certain questions or ideas I have.

I mean, part of the reason the LLM can do that is because you know enough to direct the LLM to do so and verify the results to some degree, right? It's good to learn new things because:

1. It satisfies you curiosity (and curiosity is always valuable)

2. You can better utilize the LLM to expedite something you now have knowledge about

3. You still improve as an engineer/programmer/prompter/whatever

I still think it's very important not to outsource everything to AI because there is a lot of value in learning and doing things yourself which is an important part of life.

I personally wouldn't classify it as slop from my own very quick glance of the code (who reads the code these days, amirite?) - seems pretty reasonable. Someone already mentioned that in AGENTS.md it is stated that this is a port, so that answers the design question. Out of interest, what is your definition of AI slop?

Ok, I hear you :). I share similar sentiments myself.

I'm curious how the value of your website would be determined in your model of the future and why an AI (at least one of the cloud provider models) wouldn't just persist your data after accessing it once. In other words, the way I am understanding it is that your data has a package value. An AI, if it wanted to access the entire contents, pays the whole package value. And every time it does this, you get paid. So, to really benefit, your data needs some sort of minimum value that is accessed at an appropriate frequency.

Also, in this model Cloudflare basically becomes the centralized gate keeper of you getting paid. And to me, this kind of sucks. It's not a very productive line of thought on my end -- I could see something like this happening as the internet trends toward centralization over time -- but it just feels bad.

My mind sort of shuts off once I recognize something is written by AI. It's really hard to try and force myself to keep reading. Even if a piece of writing walks the line of being written by a human or AI, my mind will want to disengage.

Is it possible for you to provide examples? What were you trying to solve? What was your solution and why was GPT's solution superior and faster?

I'm going to go insane from all of this

Thanks for sharing :)

That's a pretty neat idea. What does "map technical debt, agent readiness, code complexity" look like? How does that get done?

I'm working on my self-host TTS cli application for turning articles into spoken audio which I can stream from my PC to mobile device when I'm out and about.

It's called Vocast: https://github.com/cnrmurphy/vocast

Thinking about adding some things like queuing RSS feed items to be converted to audio and a feature for being able to do the conversion from my phone.

I think that this is common knowledge in market microstructure, but I've read about this specific relationship between market makers and adverse selection in the book, "Trades, Quotes and Prices".