Hacker Newsnew | past | comments | ask | show | jobs | submit | 650REDHAIR's commentslogin

Why?

It's good at spotting stuff, like:

* Overusing verbs

* Poor structure

* Bad transitions between grafs

* Passive voice

And even bigger-picture stuff, like "you might want to zoom in here" or "this section isn't paying off". I've only in the past few months started using it for proofreading, and it's pretty solid.

But if you take any of its words, you're infecting your writing with Claude's tone, and it will show.

It's super useful as a reader of your writing. It's a terrible collaborator, unless you're writing for an audience of middle managers.


I’ve always had a sophisticated vocabulary, now people think my content is AI generated. Frown.

Vocabulary is only part of it. LLM style is pretty recognizable, and most people don’t normally write like that. One reason is because they’re trained in a lot of marketing material, news articles, and the like. If it sounds like a self-unaware middle manager writing on LinkedIn, but it isn’t one, it’s probably an LLM.

The guy you are responding to has "All comments Copyright © 2010, 2011, 2012, 2013, 2015, 2018, 2023, 2031 Thomas H. Ptacek, All Rights Reserved." in his HN profile....

Sounds like a hedge against Agentic bots.

I hit the Claude limit within an hour.

Most of my tokens are used arguing with the hallucinations.

I’ve given up on it.


Do you use Claude Code, or do you use the models from some other tool?

I find it quite hard to hit the limits with Claude Code, but I have several colleagues complaining a lot about hitting limits and they use Cursor. Recently they also seem to be dealing with poor results (context rot?) a lot, which I haven't really encountered yet.

I wonder if Claude Code is doing something smart/special


In my case I've had it (Opus Thinking in CC) hit 80% of the 5-hour limit and 100% of the context window with one single tricky prompt, only to end up with worthless output.

Codex at least 'knows' to give up in half the time and 1/10th of the limits when that happens.


I don't want to be That Guy, but if you're "arguing with hallucinations" with an AI Agent in 2026 you're either holding it wrong or you're working on something highly nonstandard.


That’s been my experience and has lead to hours of wasted time. It’s faster for me to read through docs and watch YouTube.

Even if I submit the documentation or reference links they are completely ignored.


Because I’m sick of paying $20 for an hour of claude before it throttles me.


I thought Bezos paid enough in bribes for it to not affect AWS/Amazon?

Sorry, donated.


I use that and Mr. Chilly.

Mr. Chilly is one of those niche apps that sparks joy and reminds me of the early app days.


This was directly inspired by Mr Chilly which was designed by my friend Anna Bleker.

It's an excellent iOS app: https://mr-chilly.com/

My goal was to do something similar as a Claude Code skill


I use Mr Chilly to demonstrate to non-SF folks how many microclimates SF (and the Bay Area has).

Only suggestion: separate Inner and Outer Sunset since there can be a massive difference between near Ocean Beach and near Irving/9th Ave in autumn (ie. SF's hottest season).

Edit: nevermind, just saw both inner_sunset and outer_sunset in /neighborhoods. I'd assumed it was merged based on the human readable list on the landing page. Thanks for the fun API!


thanks I will update the homepage to reflect this.


How is this not the top of the front page?

Are we just immune to these headlines now because we don’t expect anything different from Microslop? Just an assumption that they’ll have a catastrophic failure once a quarter or more.


I’m endlessly frustrated with the Microslop experience over the last 12 months.

What are my alternatives? We utilize the entire 365 suite and it feels daunting to migrate everything to individual services.


From what I’ve seen - that’s been their goal this whole time ;)


We are a small team and rely on outlook, 365, etc.

The last year has been miserable for outages.

What are the alternatives with better uptime?


In what world is meta strongly left-biased?


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

Search: