I've used Cursor for work for a few years, but I'm really not a fan of giving all of my data to Musk. Also I think I want to spend less time writing code by hand.

I tried Antigravity but it's utter garbage.

I heard some good things about Opencode+open models/ollama cloud, but opencode seems slightly buggy when running it over ssh.

I'm really reluctant to give my money to the 2 leaders in the field, I don't think I want to contribute to them making more money, but I could be convinced if there was no doubt they're the best, which I'm not totally sure of.

I'm also on a limited budget and don't want to get a 200$ subscription unless there is zero doubt it's worth it.

My main focus is building MVPs around AI/agents, mobile apps, and scraping/automation.

In your opinion is there a clearly superior solution today you'd recommend? In terms of capabilities, value for money, usage limits.

Comments URL: https://news.ycombinator.com/item?id=49040025

Points: 2

# Comments: 2

I think it would be nice to have some apps with a different approach.

Comments URL: https://news.ycombinator.com/item?id=47321604

Points: 3

# Comments: 2

When checking what could be blocked from their google account, I realized that 60 of their saved passwords/mails were available in plain text when connecting to their google account from a new laptop(with no other input than mail and password), it's even exportable to a nice csv. This apparently seems to be default behavior.

Isn't that insane?

Am I naive to just realize that this is apparently normal to have this kind of stupid design from a trillion dollar tech company?

Is there any sane way of explaining why anyone could have thought that this was an acceptable idea?

Comments URL: https://news.ycombinator.com/item?id=41362703

Points: 3

# Comments: 5

I'd recommend using some boilerplate from github in your favorite stack even if it might be a little bit longer to build a product with it.

It's not that far from reality, most models sees images in very low resolution/limited colors, so not so far from this description

Regular captchas are easily solvable by multimodal LLMs, we're reaching a point where what's hard for software to solve is also hard for humans.

At some point they'll probably have to charge by usage instead of a flat subscription.

It was either:

A. This guy is worth twice our maximum budget

B. He's used to technical stacks that have absolutely nothing to do with ours

C. New grads perform better at leetcode than him(not saying that's a good metric, but that's not ageism)

D. Culture fit.

Also I think that in a lot of cases it's more "we can't afford to pay a guy with 20 YoE" than ageism, maybe you're punching below your weight.

Recently I noticed that I get more answers for jobs that seems too hard for me than too easy.

(V)RAM+processing power+storage(I mean what kind of average user wants to clog half their hard drive for a subpar model that output 1 token a second?)

It's not comparable, the benefits you get in western Europe are 10x better than what you get anywhere in the USA.

The US top 1% are number 1, the US bottom 10% have it worse than most or even almost all people from western Europe.

Then they might look into something else than stripe if they have a terrible problem with stripe like having their funds locked for weeks or if they think they charge too much fees.

I'm wondering if there is any good software (whether it's open source or on a freemium/per usage pricing), that allows you to just work on your features and nothing else, basically copy/paste a few API keys, write an API route, a react form and a view, and you have a working product.

I tried some open source boilerplates on github, but they weren't up to the task, either outdated and bugged or way too complex and badly written and it was a pain to add anything.

I'm mostly looking for something made with typescript/node or that is language agnostic

Comments URL: https://news.ycombinator.com/item?id=40894293

Points: 2

# Comments: 4

Then find how the pagination works, usually it's a get number parameter or a cursor in the URL.

Some websites will have a limited number of results on the same search, so you'll need to tinker with the faceted search, it's a "simple" loop, for example:

for (i in categories)

      for (j in price_ranges)
    
          for (k in price_ranges.pages[j])
  
                  get_products_on_the_page()