Gpt is really good in vision stuff, or at least their MoE seems to be really cohesive. From my experience Claude models can be really good at language but the moment they need to look at a picture and decide why the design is not good what parts need improvement it degrades a lot. My easiest benchmark is giving them a screenshot of a feature in my app and tell it "identify non-normative UI blocks and improve readability and consistency". Sol does a great job at re-structuring the page into composable units that build upon each other and the general looks and feels of the app. Claude tends to over-focus one one part while completely forgetting about the rest or the cohesion as a whole.

Comments URL: https://news.ycombinator.com/item?id=49211040

Points: 7

# Comments: 4

I'm pretty sure you've hit the nail on the head. Especially now with LLM's you'd be surprised of how many people are running full on production apps that are coded solely by an agent, deployed with a mix of random providers (supabase + fly.io + whatever) and have no clue about what Kafka is. They are never going to ask for it because... they don't know they can, and why they should. They ask an agent "connect to stripe" and the agent codes your typical webhook ingestion mechanism, never proposes advocating for an event polling loop. Whenever there is a bug they will tell the agent to fix it and the agent will just write a webhook deduplication mechanism and that's it. You'd be surprised how little supposedly technical people care about the current state of technologies.

PS: Thanks for the feedback on the writing.

Just one correction. My spec doesn't force /scroll/ URL's, just proposes it as a convention.

Comments URL: https://news.ycombinator.com/item?id=49184216

Points: 247

# Comments: 102

"This looks like AI, closed". And you as a new IC with no connections, no community visibility have no recourse to fight back against it. Anti-ai people love boasting about humans > systems and forget about those humans that will surely be negatively affected by this, even if low number.

If you are a new programmer who is just learning and spend time creating a PR for a project you have a lot of respect for and the first interaction is someone falsely accuses you of using LLM's then closes your PR you've now removed someone who could have genuinely grown into your community from ever joining.

Not only that but since now you are by default a suspect of having used an LLM (and you need to prove you didn't use one) why even bother not using one? You are going to get accused of it either way.