It would be cool if one could visualise (graph wise) the number of posts around different hypes (eg. crypto, not sure what else was prominent like AI) throughout the history of HN.

You have that in Chinese models. But you need to have a hell of a infrastructure to run those trillion parameter models.

This is something I would like to know as well.

But if not, does anybody know a recommended way to attach vision to deepseek flash (on a self-hosted infrastructure)?

Generally you just add a vision model as an MCP server like this: https://github.com/DavidEasden/opencode-vision

I would probably just give it a few days.

Deepseek is usually very good with open weights, they don't necessarily drop immediately, sometimes in a few hours, sometimes in a couple days.

I agree with a commenter above/below (depending where this comment lands). For some time models won't do this. And any review from review agents would caught this. For most of the AI programming there needs to be a more stricter (automated) review process now. Most SAST tools would caught this type of security issue.

How often do you talk about low code details in the meetings? It is mostly about requirements and goals (IMHO) and "architecture"/design, and now I wouldn't even bother my peers with questions about the code as I can let AI tell me how things work exactly as written in the code, not some thing that someone remembers or thinks how it works (in large codebases, most developers only know in detail the things they are working on currently or from recent history)

> It is mostly about requirements and goals and architecture/design

People vibe code because they have no clue about any of that. Not because they're slow typers.

In my experience, not everyone can really do this stuff by typing. I think you need to be creative, resourceful, inventive, open minded and have ideas how to approach the typing/prompting. I see many people struggle in using AI.

> In my experience, not everyone can really do this stuff by typing. I think you need to be creative, resourceful, inventive, open minded and have ideas how to approach the typing/prompting. I see many people struggle in using AI.

The problem, for the profession, is that the set of people who can really do this stuff by typing is close to "all of them". I'm not seeing anyone struggle with using AI. I see struggles from professional software developers because they are trying to get quality output, but if you don't have a bar for quality, just about everyone can create their own software.

A poster a few months ago had a Show HN about his 7 year old kid, barely able to read, who was happily vibing up games.

I can attest to the other side as well, that I have seen professional software developers outputting code of lower quality than AI. And I would say that during my career (18 or so years) I have met a small number of quality software developers or engineers. Although that might be because I was not in Silicon Valley where most of the smart/hotshot engineers converge.

How does that work if you depend on the output of the first prompt?

I write prompt for another feature or fix.

They had that?! I saw that some people wrote skills and plugins to call claude cli and gemini cli to still be able to use the subscription. I would also wish that this was supported out of the box, something similar to goose cli providers or acp providers (https://block.github.io/goose/docs/guides/acp-providers). But I don't want to spend testing yet another agent harness or change the workflow when I somewhat got used to one way of working on things (the churn is real).