Hacker Newsnew | past | comments | ask | show | jobs | submit | ramoz's commentslogin

We're doing so much planning and reviewing with coding agents like Claude Code and OpenCode.

I spent a day over break building a better UX for reviewing coding agent plans.

Plannotator - Annotate and review coding agent plans visually, share with your team, send feedback to the agents with one click.

Demo video: https://www.youtube.com/watch?v=a_AT7cEN_9I

https://github.com/backnotprop/plannotator


Yea, I'm in a particular health community. A lot of anxious individuals, for good reason, end up posting a lot of nonsense they derived from self-influenced chatgpt conversations.

That said, when used as a tool you have power over - ChatGPT has also freed up some of my own anxiety. I've learned a ton thanks to ChatGPT as well. It's often been more helpful than the doctors and offers itself as an always-available counsel.


Another user above described the curve as K-shaped and that resonates to me as well. Above a certain line of knowledge and discernment the user is likely to benefit from the tool. Below the line, the tool can become harmful.

Ive had fairly complex health issues and have never had issues with ChatGPT - other than I worry about the vast majority people in my scenario who do not understand AI.

AI can enable very misleading analysis and misinformation when a patient drives the conversation a certain way. Something I've observed in the community I'm a part of.

Not talking about acid reflux or back pain.


The other harnesses would arguably give them even richer data and product insights.

I would like for the weighting to be stronger (e.g. newness - im still getting fairly stale recs), otherwise yes very cool.

You think anthropic is losing money now with the weekly limits? And while hitting the gas on mass market?

I don’t think it wipes the context window.

I think they are just hitting the consumer market hard. I have friends who have never coded & are using Replit. That said, not a single one of them has launched.

I can second this. I'm an online coding instructor and within our company Replit was the website/environment we were told to use with our students. I really didn't like it due to all the AI features (I believe that when you're learning to code you shouldn't use LLMs) but the collaboration features were really good.

Unfortunately they added a limit to the number of collaborators per account and we had to stop using it.


I think you mean tailscale

Here is a link to their commercial offerings.

https://tailwindcss.com/plus?ref=top


There should be a monthly option - I'd pay for that.

If the goal is to support them, they do offer a subscription: https://tailwindcss.com/sponsor#insiders

While the content is different, it’s much cheaper than Tailwind Plus. If you use AI, it may even be more useful than Plus because of the great agent rules and discord community.


i just gave my favorite LLM a screenshot of one of those components and it recreated it perfectly. i paid $0.

i dont see how any business model can compete with free. maybe they can focus on branding like Pepsi or Coke and see if developers will make their decisions based on that.


> i just gave my favorite LLM a screenshot of one of those components and it recreated it perfectly. i paid $0.

Because it's most likely in the training data. I.e., it stole it for you.


Y'know, this is the one time that i thought lawyers wouldn't let it slide. I still don't understand why apparently there aren't _massive_ class-action (or similar) lawsuits worldwide against AI companies. LLMs are full on copyright-removal machines.

lawyers are paid to know legal from illegal thats why they charge thousands of dollars an hour.

Copyright washing as a service.

how do you know it recreated perfectly. Is it equally customizable? Is it equally accessible? And your LLM models cost money too. If you use the API keys, you can quickly see the cost.

Being 100% honest even though it sucks to be the truth - it doesn't matter if its customizable or accessible or not because you just ask the LLM to do that for you.

Or ask the LLM to customize it to your specific use case since most people really only really care about their situation - not for it to be customizable to everyones use case.


Even with AI, I'd still use a component library. It reduces the surface area you have to maintain and keeps your look consistent. The same reasons to use them before AI.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: