Gemini writes pretty shitty code in my experience. We tried it out for a grand total of half a day at work before deciding it wasn't worth our time and switched back to Opus.
ChatGPT writes like it's life depends on it and refuses to correct its own mistakes. It'll figure out a way to write 4k lines for something that could've been done in 500
There are plenty of people who are willing to work for the government and the pay is pretty decent. But their stack is often Microsoft based and their IT is located in Apeldoorn.
Who in their right mind would want to travel all the way to Apeldoorn.
A good example of internal development in the government is the police. They have internal development teams.
That'd be really appreciated. For me it just kept repeating the same phrase or just started reflecting on the prompt itself for a sentence or two after which it started spouting random nonsense like a pasta recipe.
it's one huge grift. The fact that people (or most likely bots) in this thread are even reacting to this positively is staggering. This whole "experiment" has no value
I'm personally especially interested in 'Latent Reflection'. I've tried to make something similar never got to a point where I was happy with the output the AI model gave me.
performance for a tool like this isn't really a huge priority imho. Libraries should have compatibility as a priority over performance unless it's the stated goal.
More and more projects are moving to Codeberg, and I'm wondering; at what point will a critical mass be reached? Or will we end up with a fragmented ecosystem?