gergely

In Hungary you don't get documentation for these APIs only in pdfs via email, and if you get it the APIs are not stable, constantly breaking. I was always dreaming about creating an automated testing suite and report all of the issues automatically to the national bank, which is the supervisor of all commercial banks in HU, in a hope to punish them.

No one seems to solve the problem when you speak some other language than English but need to mix in English words and speech-to-text that. Because of these words the output is always garbage

Why is it not an extension of Siri search, that is already available on all Macs, has a local LLM too?

go closer irl

Google has just stepped on the IBM path :D

Finally! It is the year of the Linux Desktop! :D

But it is there: If you search for jobs and expose "All filters" there is a filter called "In your network" which filters down exactly to this.

How do you solve the following problems? 1. Whenever you run a natural language question the result will be the same for the same question? 2. How do you teach an agent/LLM for the datamodel of the application that stores the data in the databases?

It always felt like a lottery, if all stars are aligned you can watch it in high resolution

It painfully misses that "there are 5 weeks left" because I have to calculate it. I don't care how much have gone, all I care how much is left!

I have 6 petabytes of parquet where I would need to replace 1 value in each line. Could it handle that?

yet another hungarian nobel prize winner who managed to get it while left hungary long ago. yet hungarians going to be proud of her. this country such a shame.

I have heard rumours that one of the company, that was aquired by IBM, protested against using IBM Notes. Which I can totally relate.

But crit races are not like coming down from Stelvio kind of speed where nervousness counts. Crit races are exactly like cx races but on asphalt or at least where I'm in Europe ;)