About one and a half years ago I was an early adopter of DSPy and I had better results (compared to LlamaIndex) with structuring unstructured data just by putting it in DSPy models, before any optimization step whatsoever.
Also, IMO DSPy didn't take off because it requires preparing train and test datasets and that takes time and effort. Now with Gepa I expect things are getting very interesting, the optimizations can come just from descriptions.
IMO LangGraph is currently used a lot as an agent and RAG framework, DSPy doesn't have the same use case, even though there's overlap. And I think the montly numbers doesn't do justice, because what I see now is a lot of companies doing things wrongly.
I agree that Opencodr is using a lot of RAM, but regarding the features, I am ak only using the built in features and I wouldn't say they are too many, they are just enough for a complete workflow. If you need more you can install plugins, which I haven't done yet and it's my daily driver for four months.
I have non-coder friends who are vibe coding apps. The process isn't smooth, vut they are definitely excited for the new abilities they get from the models. Maybe they are a minority, but they definitely exist.
All wrongs in Gatsby have been gotten right in Astro. What will happen next remains to be seen, but currently Astro is amazing for a few specific cases it covers. The performance, developer experience and documentation are all great.
the LLM doesn't have the concept of time and it doesn't incorporate new data, unless it's put into the context, so I don't see the point of this suggestion.
Reading about the the complexity of Rust makes me appreciate more OCaml. OCaml also has a Hindley Milner type system and provides similar runtime guarantees, but it is simpler to write and it has a very, very fast compiler. Also, the generated code is reasonably fast.
Javascript wins by keeping the costs down. Companies today want to do more with less, which is how it should be and you are still free to choose from a myriad of technologies. When you pair this setup with LLMs, it's actually the best it has ever been IMO.
In theory yes, but in practice I wouldn't say that for example the way Facebook and Instagram developed is an example of superiority in social media design that has won. Honestly, technology can make life worst and we should find against that.
Also, things like visual arts and music can be watered down by devaluating the real stuff and equaling it with AI generated stuff.
Arguably, we used to be better at making physical stuff, we used to make beautiful amps, synths and drum machines, which to this day are highly valued only has software equivalents today.
It's also important that most of AI content created is slop. On this website most people stand against AI generated writing slop. Also, trust me, you don't want a world where most music is AI generated, it's going to drive you crazy. So, it's not like photography and painting it is like comparing good and shitty quality content.
IMO the shift towards AI was very detrimental to the job market, because every company started to work on their AI strategy and not on their core competencies. This has resulted in most companies failing to materialize their AI strategies, while burning their cash. One of the reasons for this is that the average company competes against Goliaths that have infinite funding.
At first many companies stopped developing mobile apps and I think mobile app devs were the first hit.
Second, the frontend developers were hit because of how the AI can generate good enough websites, however, they aren't hit as hard as the mobile developers.
This has spread into most parts of the stack with a variable impact.