Never used your project but don’t let this thread get you down.
Clearly OP loves it - don’t let those who don’t know it or don’t like it be the voices that ring loudest in your ears even if they hurt the most.
I worked professionally in open source at a company with lots of funding. The tools I worked on were used by millions and millions.
Every negative comment hurt so much. Every angry user I wanted to talk to. Most of them wanted to TALK AT me. It all hurt. And I was being paid. The engineers on my teams were burnt by the community time and time again.
If you love what you’re doing and you have a growing or happy audience - stay the course. Listen to criticism, decide if you agree (and maybe take some time when it hurts because the criticism might be valid), make a decision and move on.
Also, and this is going to be tough, maybe think about expanding or modifying what you mean when you say making Lemmy accessible for everyone.
Do you mean making a UI that will become the majority default or making a UI that brings some features (or perspective) for users who see value in those features? Trying to make something for everyone in a pond as small as the fediverse, where there are already a plethora of options is a big lift.
Above all, do you. And that includes this comment which I encourage you to promptly ignore. ;)
Depends what you’re doing.
4o is way better at analytical work. Think big datasets and statistics. It’ll provide the Python it used for analysis so you can double check.
Claude is far superior for more challenging development tasks. For example I found ChatGPT pretty useless for a lot of Scala troubleshooting and rubber ducking.
Claude 3.5 Sonnet is much better though far from error free. Also not free if I remember correctly.
Both get stuck in weird loops, make stuff up and leave things out when taken at face value.
Ultimately they have their own strengths and either can be a force multiplier.