sleazebreeze

Joined 14 years ago

Karma
484
Submissions
162
Member since
Aug 17
View on Hacker News

Recent submissions

Comment · 11 days ago
Is any of this real or just juicy vibe coded marketing? The pricing doesn't have any details, which makes me think this is mostly vaporware.
Comment · 16 days ago
What exactly is the logical fallacy there?
Comment · 1 month ago
Comment · 1 month ago
What do you think is happening?
Comment · 1 month ago
Apparently most readers have read too much AI output that they don’t recognize a bit of irony as a joke.
Comment · 1 month ago
At my previous company, a distinguished engineer did this. Used generated slides he hadn't looked at until presenting to the entire staff+ engineer group. The slides weren't good and he mostly ignored them.
Comment · 1 month ago
Claude models are the ones that need this the most and in my experience with this specific skill only maintain the conciseness for a few turns at most before they completely forget and are back to their unfathomable verbosity. That's with it instructed to use it in my sparse global CLAUDE.md and also manually repeating it regularly during sessions. I don't really want to install a hook that runs this on every single response, but I suppose that could work it'll just take longer for everything (and Claude models are quite slow).

I don't think we can skill our way out of this one.

Comment · 2 months ago
Yes and the last bit is always mysterious and inscrutable. I have to think way too hard to figure out what the actual problem is. I’ve noticed it does a lot of explaining the mechanics of the problem it found, but almost never explains why it’s important until I ask.

And the worst part is that this little problem will keep sneaking into the context of future sessions, unless you spend the time to fix it. Even if it isn’t important, I’ll sometimes have Claude fix it so it will shut the F up about it going forward.

Comment · 4 months ago
Too bad Google can’t compete in consumer or professional AI either
Comment · 5 months ago
They teased it as such. Reckless and stupid political stunt.
Comment · 5 months ago
What exactly is the concern here by Headway? Are they afraid AI deep fakes will be receiving therapy?

Obviously they are doing data collection and selling training data of emotional conversations to AI labs. But what's their stated justification? I can't figure it out.

Comment · 5 months ago
You aren't allowed to dismiss vibe coded software based on the slop vibes. It must be well-researched and human reviewed in order to have an opinion.
Comment · 6 months ago
Many libraries have ebooks. I am familiar with the app Libby in parts of the US.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton