Disclosure without a deadline WILL be ignored.

It does not matter if it's Google or your local boyscouts club, any organization requiring users to provide information that can be abused in the wrong hands takes on a responsibility to handle such data responsibly.

Still, it's just a temporary hindrance. Nothing a decent system prompt can't take care of until the models evolve.

The author acts as if taxes are not a completely fluid system, that will quickly adept to ensure revenue keeps flowing, squeezing wherever the squeezing is the juiciest. It does not need cautious calibration.

I use a custom tool, that basically merges all my code into a single prompt. Most of my projects are relatively small, usually maxing out at 200k tokens, so I can just dump the whole thing into Gemini Pro for every feature set I am working on. It's a more manual way of working, but it ensures full control over the code changes.

For new projects I usually just copy the llm.md from the tool itself and strip out the custom part. I might add creating it as a feature of the tool in the future.

A few days ago I tried to use AntiGravity (on default settings) and that was an awful experience. Slow, pondering, continuously making dumb mistakes, only responding to feedback with code and it took at least 3 hours (and a lot of hand holding) to end up on a broken version of what I wanted.

I gave up, tried again using my own tool and was done in half an hour. Not sure if it will work as well for other people, but it definitely does for me.

A local, project specific llm.md is absolutely something I require though. Without that, language models kept on "fixing" random things in my code that it considered to be incorrect, despite comments on those lines literally telling it to NOT CHANGE THIS LINE OR THIS COMMENT.

My llm.md is structured like this:

- Instructions for the LLM on how to use it

- Examples of a bad and a good note

- LLM editable notes on quirks in the project

It helps a lot with making an LLM understand when things are unusual for a reason.

Besides that file, I wrap every prompt in a project specific intro and outro. I use these to take care of common undesirable LLM behavior, like removing my comments.

I also tell it to use a specific format on its own comments, so I can make it automatically clean those up on the next pass, which takes care of most of the aftercare.

It's just not a very good fit for Firefox. I assume it would run on a cloud service, which is very much a privacy issue. Especially because it appears to be something "free", making my data the product.

You need talented people to make good stuff, but at this time most of them still fear the new tools.

The only real mistakes it makes are some model specific quirks, like occasionally stripping out certain array index operators. Other than that, it works fine with 150.000 token size conversations. I've gone up to 500.000 with no real issues besides a bit of a slowdown. It's also great for log analysis, which I have maximized to 900.000 tokens.

The whole concept is meant to poke fun at the idea of me "checking up on her" (I file her tax returns) and the entire theme is 80s pimp styled.

Every time she submits something, she'll get a random pimp remark, like "Go get that money for me, girl!". She just rolls her eyes and ignores it, but it's what made it fun for me to work on it.

Edgy stuff like that could jeopardize my account in the near future. It might just be security now, but an automated "naughty words detector" will be an obvious next step.

I doubt I will invest any more time in hobby app development if I have to deal with some humorless overbearing watchdog telling me what I can and cannot install on my own device. Very sad to see Android following Microsofts anti power user direction.

I always have that, but I only hear a random high pitched tinnitus noise in one ear, rising and falling in volume for max 10 seconds, about once every few months.

I can still hear old CRTs in my forties, although it's less maddening now. They had those mosquito devices, that are intended to repel kids, for a while at a shopping mall near me. They repelled me very effectively as well.

A friend once thought it was funny to try the 15.000Hz silent ringtone on me, although I had told him not to. It made me react without conscious input and I nearly broke his phone.

I've always wondered if there is a correlation between developers and people that can enjoy tough but fair games like Super Meat Boy because of this.

It kind of forces you to always put such data in external files, which is better for code organization anyway.

If it's not necessary for understanding the code, I'll usually even leave this data out entirely when passing the code over.

In Python code I often see Gemini add a second h to a random header file extension. It always feels like the llm is making sure that I'm still paying attention.

Are those hours completely without value, because I used genAI during most of them? It involved a LOT of consideration and a few pretty tough choices. But because I didn't do my 10.000 hours, and it's sad for those that did, I'm not allowed to create this way?

Whatever, I'm still putting it on my wall. It means more to me than most "legit" art does.