Thank you for writing this up (and getting it put into a video). I sent this blog post to my parents and my mum has decided to forward it on to all of her friends after watching.
Seems easily digestible and approachable for a specific target audience.
Pretty much anything computer graphics related seems to follow the sage advice that "a close approximation is better than an accurate simulation", if that's the kind of thing you're looking for?
My Family recently (in the last couple of years) started to breed Ragdoll cats in the U.K.
In an attempt to support what's involved in this I built Ardent for them. It covers a bunch of the day-to-day concerns (weighing and health tracking), Lineage and Inbreeding prevention, and Owner Pack generation for handovers to new Owners.
I doubt it'll be of interest to folks here - but my Family recently (in the last couple of years) started to breed ragdoll cats in the U.K.
This has been my personal project to understand where I personally find LLMs useful as coding assistants, and where I don't. One easy to spot example is, front-end + copy. Another area I've enjoyed it is talking through how I'd design and build functionality and features ahead of time.
It's been very interesting, and is helpful to folks I care about, even if no-one else ends up using it!
I'm not trying to call out Sentry.io specifically here, I'm just using them as the example because it happened today. In fact, in general I'm a happy customer of theirs.
I'm trying to understand the motivations behind companies that aren't open about their uptime (or other issues, such as data breaches etc).
Why is it not encouraged/rewarded (or perceived as such) to be up front and open about these things? It seems that amongst the HN crowd it has been valued, and folks are appreciative and supportive of these things (vocally and with their wallets) - so why is it not more common practice?
The more I've used it, the more I've disliked how poor the results it's produced, and the more I've realised I would have been better served by doing it myself and following a methodical path for things that I didn't have experience with.
It's easier to step through a problem as I'm learning and making small changes than an LLM going "It's done, and production ready!" where it just straight up doesn't work for 101 different tiny reasons.
I've had little success with Agentic coding, and what success I have had has been paired with hours of frustration, where I'd have been better off doing it myself for anything but the most basic tasks.
Even then, when you start to build up complexity within a codebase - the results have often been worse than "I'll start generating it all from scratch again, and include this as an addition to the initial longtail specification prompt as well", and even then... it's been a crapshoot.
I _want_ to like it. The times where it initially "just worked" felt magical and inspired me with the possibilities. That's what prompted me to get more engaged and use it more. The reality of doing so is just frustrating and wishing things _actually worked_ anywhere close to expectations.
Seems easily digestible and approachable for a specific target audience.