I noticed that LLMs need a very heavy hand in guiding the architecture, otherwise they'll add architectural tech debt. One easy example is that I noticed them breaking abstractions (putting things where they don't belong). Unfortunately, there's not that much self-retrospection on these aspects if you ask about the quality of the code or if there are any better ways of doing it. Of course, if you pick up that something is in the wrong spot and prompt better, they'll pick up on it immediately.
I also ended up blowing through $15 of LLM tokens in a single evening. (Previously, as a heavy LLM user including coding tasks, I was averaging maybe $20 a month.)
Initial cost was around $20 USD, which later grew to (mostly polishing) $40 with some manual work.
I've intentionally picked up simple stack: html+js+php.
A couple of things:
* I'd say I'm happy about the result from product's perspective * Codebase could be better, but I could not care less about in this case * By default, AI does not care about security unless I specifically tell it * Claude insisted on using old libs. When I've specifically told it to use the latest and greatest, it upgraded them but left code that works just with an old version. Also it mixed latest DaisyUI with some old version of tailwindcss :)
On one hand it was super easy and fun to do, on the other hand if I was a junior engineer, I bet it would have cost more.
That machine is SOOOOOO FAST. I love it. To be honest, that tasks that I was doing back in the day are identical to today
I disable the "land assist" every time (which often tries to steer me into wildlife or other cars and was clearly not built for use on a single track country roads with hedges and random verges), but this was the first time in 3 years that the "front assist" caused problems.
If that's "high quality", I dread to think what low quality would be.
These aren't hard problems.
These are not hard problems obviously, but getting to 80%-90% is faster than doing it by hand and in my cases that was more than enough.
With that being said, AI failed for the rest 10%-20% with various small visual issues.
They keep being impressive at what they're good at (aggregating sources to solve a very well known problem) and terrible at what they're bad at (actually thinking through novel problems or old problems with few sources).
E.g. all ChatGPT, Claude and Gemini were absolutely terrible at generating Liquidsoap[0] scripts. It's not even that complex, but there's very little information to ingest about the problem space, so you can actually tell they are not "thinking".
However, I've realized that Claude Code is extremely useful for generating somewhat simple landing pages for some of my projects. It spits out static html+js which is easy to host, with somewhat good looking design.
The code isn't the best and to some extent isn't maintainable by a human at all, but it gets the job done.
AFAIK, 43888 is preferred by makemkv forums as it's internal drive can be flashed to support ripping blu-rays as well.
[1] https://www.verbatim.com/prod/accessories/disc-drives--burne...
I guess, provider will always consider your country where the phone number is located. Funny thing, while I'm roaming, my IP address will always be Lithuanian. It does not matter where the world I'm currently staying.
I recall a handful of tools that anyone could use (I was 10-11 and could figure it out) to break and bluescreen Win 98 computers remotely.
10-11 year old me liked the XP theme, the icons were so “fresh”, nearly everything that came before was grey and boring (and the beige boxes didn’t make that better) so it was a welcome change to me at the time.
Now I’m old, I see the joy of grey high contrast consistent UI: what I am doing is more important than the shell around what I am doing.
I've got friends who ran Windows ME and it was rock solid. My experience was very very different, same with Windows 98 SE.
With that being said my PC with Win95 OSR2 was super stable.