This was pretty much my first experience with LLM code generation when these things first came out.
It's still a present issue whenever I go light on prompt details and I _always_ get caught out by it and it _always_ infuriates me.
I'm sure there are endless discussions on front running overconfident false positives and being better at prompting and seeding a project context, but 1-2 years into this world is like 20 in regular space, and it shouldn't be happening any more.
Often times I come up with a prompt, then stick the prompt in an LLM to enhance / identify what I’ve left out, then finally actually execute the prompt.
Cite things from ID based specs. You’re facing a skill issue. The reason most people don’t see it as such is because an LLM doesn’t just “fail to run” here. If this was code you wrote in a compiled language, would you post and say the language infuriates you because it won’t compile your syntax errors? As this kind of dev style becomes prevalent and output expectation adjust, work performance review won’t care that you’re mad. So my advice is:
1. Treat it like regular software dev where you define tasks with ID prefixes for everything, acceptance criteria, exceptions. Ask LLM to reference them in code right before impl code
2. “Debug” by asking the LLM to self reflect on its decision making process that caused the issue - this can give you useful heuristics o use later to further reduce the issues you mentioned.
“It” happening is a result of your lack of time investment into systematically addressing this.
_You_ should have learned this by now. Complain less, learn more.
Ridiculous that this has a crypto label. It's the same game as all of the senior people I know who have been hit with fake anti virus, fake software updates, fake banking apps etc.
Start small and harmless, take a small payment, request higher access, get a screen share or account password. Game over.
That's weird.. I don't recall feeling like it was a money thing that I had a Spectrum, only that my parents had made the 'wrong' call on a 50/50 decision (though I will forever be grateful for that early exposure to programming!)
Trying to search for local prices back then is tricky, but they look to have been in the same ballpark (£180-200).
The c64 peripherals we’re way more expensive too. Commodore had an official cassette player as well as a floppy disk drive that weren’t cheap. Though I suspect I in the long run probably spent more money on worn out joysticks
Sellers generate fake orders for their products using real identities, actually send the product to those people, but leave a fake review in their name.
I've tried raising the issue repeatedly with Amazon, but I've now given up and look forward to the random crap I get sent almost on a monthly basis.
Better idea: Only verified buyers who have been on Amazon for X amount of time (or some other process to gain trust) should be allowed to leave reviews.
I never experienced it myself, but I’ve seen reviews claiming they had a letter in their package that they’d get X currency if they leave a 5-star-review.
Sorta similar but different, I left a 3 star review for something (cheap headphones that were OK but not great), and got a few emails after it offering me credit etc. if I changed it to a 5 star review.
I didn't, but did report it to Amazon (no idea if they cared at all.)
$21 a month per user.....to host it on my own hardware....no thanks. If I am hosting on my own hardware then you get a one-time-fee, none of this subscription nonsense.
It's still a present issue whenever I go light on prompt details and I _always_ get caught out by it and it _always_ infuriates me.
I'm sure there are endless discussions on front running overconfident false positives and being better at prompting and seeding a project context, but 1-2 years into this world is like 20 in regular space, and it shouldn't be happening any more.