heystefan

I don't get it either.

Love this! Added to bookmarks. Wish it had a counter for bonus words so I know if I missed them.

lol same

Please ignore them, the images definitely helped understand the issue better. Don't anchor on a couple of grouchy hn posters.

Commenting to follow up.

Thanks for clarifying, just wanted to point out it's not 1 to 1 with CC. Happy user of Conductor here btw, great product!

I don't think this is true. Try running `/skills` or `/context` in both and you'll see.

Warm and convivial voice.

So when you say "X attempts" what does that mean? You just start a new chat with the same exact prompt and hope for a different result?

I had the same experience. Plus you never know what's the best way to use eg. Nano Banana -- it works better in AI Studio versus their regular Gemini chat.

Not sure where all the Toast hate is coming from in this thread, but I know two instances of Toasts that I use daily and they help a lot:

- macOS screenshots

- Linear toasts after every action (with common actions on them such as copy link)

UT99>

Half the time nanobanana doesn't do anything to the photo from my experience, also confirmed in some of these examples.

They didn't describe Italy as Eastern Europe, they said you can hire in Eastern Europe for far less. Eg. you can do that from Italy and keep people in the same timezone and relatively close by.

Seems like a great app, but I have to ask:

https://scriberpro.cc/about/ Are you trolling people with this page's design? Unreadable colors AND a wobble effect? :D

Is it me or did they use to avoid calling it "AI"?

I wonder how it compares to https://ai-sdk.dev

The only missing piece from this article is: the prompt itself should also be generated by AI, after going through my convos.

My dad will never bother with writing his own "system prompt" and wouldn't care to learn.

This is something I would definitely use, as my company pays for v0 today for these exact purposes (product design/PM).

I've tried some of the same prompts I've done on v0 but didn't notice a lot of difference -- needs a lot of back-and-forth, as with v0. So not sure what would make me switch at this point.

Could one usecase be generating an audiobook with this from existing books? I wonder if I could fine-tune the "characters" that speak these lines since you said it's a single pass whole the whole convo. Wonder if that's a limitation for this kind of a usecase (where speed is not imperative).

Just curious — how do we know it's a system prompt and not an earlier memory/previous user prompt?

As a front-end dev with very limited backend+db knowledge, would I be able to use this?

(Maybe not Series A and millions of users, but def. in production for a side project.)

Just in product design terms, why not make this default on?

Not sure why this is front page material.

The thinking is very surface level ("AI art sucks" is the popular opinion anyway) and I don't understand what the complaints are about.

The author is tired of AI and likes movies created by people. So just watch those? It's not like we are flooded with AI movies/music. His social network shows dull AI-generated content? Curate your feed a bit and unfollow those low effort posters.

And in the end, if AI output is dull, there's nothing to be afraid of -- people will skip it.

So, can I somehow use the 1913 Webster dictionary on MacOS? It's not in the list of configurable ones.

(If not possible, Terminal would work too.)

^ What he said. There's something in story/branding/nostalgia too.

Huh, I thought some of those were green screen.

Cool idea! Been experimenting with similar stuff, still trying to solve for detecting when a question ends.

BTW at one point it got confused and said that it doesn't have the ability to continue a lecture. I even have a recording in case you need it.

Can I detect analog stick drift with this?

That's amazing, went down a spiral of other projects too. Crazy stuff.

Also reminded me of this ferrofluid clock my buddy built back in the day: http://www.hellorhei.com