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

I'm working on a new type of calculator with natural language, similar to Soulver but for the web, in multiple languages and with AI mode

https://ottercalc.com/

It has the ability to generate a small notebook from a problem description using AI (still has a lot of room to improve), but the calculation uses a deterministic engine.

Right now I'm working on collaboration.


It is a novel idea. Excellent implementation.

"I’ve also learned that many people don’t use English to interact with agents"

WTF... that's weird. English is not my first language but I still ask every question in English. Does the LLM write code comments in other languages then?


I created a similar tool a year ago -> https://infiniteutils.com/internet/linkedin-post-generator


Funny how easy it is to turn any banal situation into something that sounds profound.

I put my situation as "Playing with a frisbee, alone." and your person says "Life is like a Frisbee. You can't control the wind. You can only adjust your throw."


Error 1102 Worker exceeded resource limits


It's a strange realization that this looks so much like LinkedIn because it actually is LinkedIn.

It seems that an LLM is deliberately being forced to generate in the style of LLM slop.


I'm building a source code analyzer with AI. It's a TUI that you poin at a local codebase and it generates Mermaid diagrams.

While I was doing it I needed to render those diagrams as ASCII and I was surprised there's no Python library for Mermaid to ASCII. So I wrote one: https://github.com/fasouto/termaid (https://termaid.com/)


Love it! Thanks for sharing. I use mermaid a lot, and this I will use to embed my diagrams as ascii in my text docu.


I tried to do the same in 2015 (blablacar for packages, startup name was tomandgo) and we couldn't solve that problem, it is genuinely hard.

I think in our case the main problem was incentives, we were suggesting low prices for the people sending packages but we forgot that the drivers need an incentive to drop it.

Best of luck!


[flagged]


Honestly, I don't know. We did it for all our country (Spain) and we found the same problem as you. Feel free to reach out if you have any question, email in my profile


I released an open source library to remove metadata from images: https://github.com/fasouto/picscrub

Was more complex than I thought. Still missing support for some RAW formats and had to fix some bugs

I also created a website to showcase how it works -> https://picscrub.com/


https://fabiosouto.me/

Right now it sucks but I'm creating the new version. Writing always take more time than I anticipate...


The article nails the pattern but I think it's fundamnetally an incentives problem.

We're drowning in tweets, posts, news... (way more than anyone can reasonably consume). So what rises to the top? The most dramatic, attention-grabbing claims. "I built in 1 hour what took a team months" gets 10k retweets. "I used AI to speed up a well-scoped prototype after weeks of architectural thinking" gets...crickets

Social platforms are optimized for engagement, not accuracy. The clarification thread will always get a fraction of the reach of the original hype. And the people posting know this.

The frustrating part is there's no easy fix. Calling it out (like this article does) get almost no attention. And the nuanced followup never catches up with the viral tweet.


Not affiliate marketers are thieves


The whole industry is based upon on nonconsensual surveillance and other taking of personal information, so yes they are.


Less theft, more stalking.


Interesting approach... Initially I thought it was bit overkill but I found myself picking my phone when I have a site blocked on my laptop.

Happen more than I'm willing to admit, so I guess I will give a try


nextdns lets you set times when domains are blocked. Originally I had it just for my computer but soon realized I needed it for my phone as well.


I'm planning to address the issue for phones as well in the future.


I built a DNS resolver on Proxylity[1] as a demo but it didn’t occur to me that block by default was a use case. I might have to add that.

My suggestion: Allow by ASN would be a clean (simple) way to get all of Google, etc., allowed at once.

[1] https://github.com/proxylity/examples/tree/main/dns-filter


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

Search: