crewindream
If parsing fails - how often can you do anything else than just abort and log/show an error..
Checked exceptions are nice in theory, but it is very context dependent if checked’ness is useful, I would prefer that libraries do not expose them.
2. Carbon seems to be brittle.
I fully agree.
> It's the same conflict of interest quite literally any business has.
I know that you know what I meant ;) In the long term it is just as you say - overcharging (eventually corrected by competition forces), but in the short term it can be additional revenue, blamed on a bug, but making some manager look good.
Maybe their laptop experience is completely on another league, but I have doubts
Also i doubt there was jira ticket with “make llm more verbose”, rather ticket with “bug makes llms too verbose” gets prioritised taking revenue impact into account.
It’s like that saying “What Andy giveth, Bill taketh away”, but in this case it is one company.
There is definitely a conflict of interest.
This needs to be routine to be given asevidence…
…Unless you know exactly how the llm was trained and then how it was applied
Idea being that for user it is less frustrating to wait for animation to end, than to see some hourglass/waiting indication.
Other way could be to actually visually indicate action queue depth.
On average it is has same amount of crappy UI experience, just in different places.
Record actions until interrupt.
Animation should not be considered interrupt.
An Error message should be treated as interrupt.
2.Asking for hard evidence of top spies secretly spying on heads of other states is … (not sure if there is a word for it; some blend between: unrealistic, unreasonable and oxymoron’ish. If they do their job well, you will not find it out, also it might be illegal or punishable to present such evidence)
(E.g. If you have problems hiring for a weird stack, it increases hiring cost; you have problems with dependency zoo maintenance it increases costs; if it took a year to build a framework that could've been a bash script, it increased the cost)
Every other architecture “metric” should be useful/convenient proxy towards reducing overall cost.