• 9 Posts
  • 1.27K Comments
Joined 3 years ago
cake
Cake day: July 7th, 2023

help-circle



  • Right. But that was from a time where it was your friends and family who had your number, so having to change it was a major hassle not only for you. With it being asked by so many services, that’s eventually ending up in the dark web.

    Many people don’t call anymore. A similar group blocks all calls from unknown numbers due to constant robocalls. So a phone number today is just another data point to fingerprint someone. Its usefulness turned into an artificially created need by services that want a cheap way to tell real users from robots.


  • yeah, phone numbers have been used primarily to fight spam and fake accounts, so my guess is that this practice will become even more common with stricter policies around phone number registration. I hate it.

    This basically turns phone numbers into a deregulated government ID number. You’d think they had learned something with SSNs by now.





  • I’m not even sure it does work. Prime only tried trivial packages, but based on my experience with agentic coding, I’m not convinced they’re able to deliver a fully functional package of medium size while being truly clean room.

    Also, there’s an anecdotal comment on youtube of someone who tried this (on a small package) and they mention the clean room was violated (the AI added implementation instructions to the documentation), had performance issues, and the best part, the generated code had an MIT license. Now I wish Prime had looked at the LICENSE files created.



  • Ok, let’s think this through. Whoever “hires” them ends with a legally questionable codebase to say the least, that has worst architecture and performance than its open source counterpart, while also being unmaintainable and likely costing more to fix than building something the right way in the first place.

    So they’re taking money from people trying to do this shit? Great.






  • Not really, there are ways to count tokens before running an inference. Some providers make tokenizers public, so they even work offline. APIs also usually return rolling costs per response and have budget limits - though some could have more fine-grained limits.

    Users who are surprised by the bill are usually not paying attention to each call, or using autonomous subagents, or a setup where they have little or no control to what is sent to the provider.

    So the problem isn’t really the API provider, as much as it’s the tooling around it, which makes it too easy to overspend.