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

> I've spent the weekend trying my hand at making an AI assistant SaaS (I can't believe this doesn't exist yet!)

you mean another wrapper ?


Do you know of any good ones?


there's plainly, just run a search on perplexity or else. Most YC startup are AI wrapper in some sort...


I haven't been able to find any AI personal assistants, please point me to any you may know.


The entire market is focused on productivity ones that all have the same feature set, no real originality in the offerings IMHO.

There are a lot of low hanging fruit that can be tackled. From helping people stay focused to managing household schedules. I honestly don't even think the product has to be SaSS, a 16GB VRAM GPU, or a well equipped MacBook, can do everything with locally.


They keep asking for a specific recommendation and gets there are tons out there


thanks for the tip!


> It seems to me that "vibe checks" for how smart a model feels are easily gameable by making it have a better personality.

I don't buy that at all, most of my use cases don't involve model's personality, if anything I usually instruct to skip any commentary and give the result excepted only. I'm sure most people using AI models seriously would agree.

> My guess is that it's most of the reason Sonnet 3.5.1 was so beloved. Its personality was made much more appealing, compared to e. g. OpenAI's corporate drones.

I would actually guess it's mostly because it was good at code, which doesn't involve much personnality


money is already in very large part digital.


Most digital money is scriptural. Cryptos aren’t.


HTMX is certainly easier, but it's the worse if you want to actually learn FE


Strong disagree, it would be a great way to learn vanilla html/CSS/js without kneecapping yourself.


How do you learn JS by using htmx exactly ?


Because htmx is limited in scope. And it's encouraged to use JS for the parts of your app that would benefit from it. But it's encouraged to do so in a way that fits with web standards. Eg https://dev.to/yawaramin/handling-form-errors-in-htmx-3ncg


Couldn't one say the same thing about using any framework that provides capabilities that otherwise would have to be learned?


As someone who isn't a web developer, what do you mean by that?


HTMX abstracts functionality into pseudo-HTML attributes, allowing you to handle tasks like event binding and DOM/content manipulation that would typically require JavaScript. By using HTMX, you primarily focus on learning HTML and its attributes, with minimal need to learn JavaScript.


Not sure how to interpret what you're saying.

HTMX allows you to learn the very basics: the HTML which is almost verbatim turned into DOM which the browser renders. It's the FE. Everything else is layers upon layers of abstraction which ultimately compile down to the DOM representation of HTML.

...or to put it differently, quoting HTMX's author: using HTTP to transfer HTML? How queer!


Sounds like you don't know anything about FE except htmx...


He has a point though


seems awesome. FYI got a react error screen when trying calendar with time, not sure exactly how sorry


markdown works better than json too


I did that with json too, and got better result


If it's proven to be a real issue, we might expect to see models trained on a lot of synthetic data with less knowledge but highly capable to reason, and other models less capable to reason but with large knowledge.


same

> Certainly. Here's a real-life example of three events A, B, and C that demonstrate the correlation pattern you've described:

A: Ice cream sales B: Temperature C: Sunscreen sales

Explanation:

1. A and B are correlated: Ice cream sales (A) tend to increase as temperature (B) rises. People are more likely to buy ice cream on hot days, creating a positive correlation between these two events.

2. B and C are correlated: Temperature (B) and sunscreen sales (C) are also positively correlated. As the temperature increases, people are more likely to spend time outdoors and therefore buy more sunscreen to protect their skin.

3. A and C are uncorrelated: However, ice cream sales (A) and sunscreen sales (C) are not directly correlated. While both may increase during warmer weather, there isn't a direct causal relationship between the two. People don't necessarily buy more ice cream because they're buying sunscreen, or vice versa.

This example demonstrates how two events can be indirectly related through a third event (in this case, temperature) without having a direct correlation with each other.

Would you like me to elaborate on this example or provide additional information about correlation?


another:

Here's another example of three events A, B, and C that follow the correlation pattern you described:

A: Coffee consumption B: Work productivity C: Typing speed

Explanation:

1. A and B are correlated: Coffee consumption (A) and work productivity (B) often show a positive correlation. Many people drink coffee to increase alertness and focus, which can lead to improved productivity at work.

2. B and C are correlated: Work productivity (B) and typing speed (C) are generally positively correlated. As people become more productive, they often type faster to keep up with their increased output.

3. A and C are uncorrelated: However, coffee consumption (A) and typing speed (C) are not directly correlated. While coffee might indirectly influence typing speed through increased productivity, there's no direct causal relationship between drinking coffee and typing faster.

This example shows how work productivity acts as an intermediary factor, connecting coffee consumption and typing speed without them being directly correlated.

Would you like me to provide another example or explain any part of this in more detail?


> 3. A and C are uncorrelated: However, coffee consumption (A) and typing speed (C) are not directly correlated. While coffee might indirectly influence typing speed through increased productivity, there's no direct causal relationship between drinking coffee and typing faster.

Hmm, not too sure how much I buy that... ;)


Seems wrong, per hnlandfr's comment. How about: a) insomnia, b) coffee consumption, c) typing speed.

Edit: also it's wrong in a basic way because coffee does make you type faster. I somehow overlooked that.


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

Search: