That wasn't very helpful...

I’m confused. You say that you “go to” an annual event, but then you describe it at a massive private festival that you’re self organizing. Which is it?

I'm curious: what do you do when the LLM starts hallucinating, or gets stuck in a loop of generating non-working code that it can't get out of? What do you do when you need to troubleshoot and fix an issue it introduced, but has no idea how to fix?

In my experience of these tools, including the flagship models discussed here, this is a deal-breaking problem. If I have to waste time re-prompting to make progress, and reviewing and fixing the generated code, it would be much faster if I wrote the code from scratch myself. The tricky thing is that unless you read and understand the generated code, you really have no idea whether you're progressing or regressing. You can ask the model to generate tests for you as well, but how can you be sure they're written correctly, or covering the right scenarios?

More power to you if you feel like you're being productive, but the difficult things in software development always come in later stages of the project[1]. The devil is always in the details, and modern AI tools are just incapable of getting us across that last 10%. I'm not trying to downplay their usefulness, or imply that they will never get better. I think current models do a reasonably good job of summarizing documentation and producing small snippets of example code I can reuse, but I wouldn't trust them for anything beyond that.

[1]: https://en.wikipedia.org/wiki/Ninety%E2%80%93ninety_rule

GDPR was created to legitimise trade of personal data. It was done in a two step approach. First there was a cookie law, to train people to give consent to anything that pops up without reading, then GDPR where people give consent to data processing without even thinking about it.

Then big corporations have a legal basis for trade of such data where before GDPR it was a grey area. Now they can say - users have consented for us to slice, dice and sell all the data related to them.

GDPR was never about protection or to benefit citizens. One of the greatest deceptions.

When I read this, some kind of interferences/ images are parasitizing my mind; drawn cartoon with colors of the princess in Aladdin, the Disney one; cinematic/documentary video of a cobra in the desert that rises up its head.

Sometimes it's voices, sometimes it's music; what parasites lives in the mind of someone that has aphantasia ? How do you think when solving a mathematical problem ? How do you design an algorithm ?

The results do stick.

My first experience was random, when I tried a new, legal LSD variant[1], during the end of the pandemic, summer 2021.

I tried first ~40µg, while still finishing work (code).

Didn't feel anything so I took another 40 and then went dancing two hours later. At 80µg the LSD was just below psychoactive, so that dose was too high, in retrospect. I now use 40µ and that is perfect for me.

The only indicator I had, after the night, was external. Three followers came to me, out of the blue, and told me: "you were my best tanda tonight, thank you." (A tanda is a block of three-four songs danced together, before you change partners).

That struck me as odd/very surprising, at the level of dancing I was at then. A comment like this was something I would hear once-twice a year, if lucky. But three in one night?

After that the praise kept coming from other tango people I danced with for years before, i.e. they felt the change.

That's when I started experimenting with it and it has just become another tool to improve since then.

People who disregard this I tell to talk to dozens of dancers who know me for years.

They didn't know about what caused it. Yet they saw/see and felt/feel the change in my dancing and particularly musicality (which was, until then, my biggest struggle).

[1] LSD.shop