Dspys advertising aside, imho it is a library only for optimizing an existing workflow/ prompt and not for the use cases described there. Similar to how I would not write "production" code with sklearn :)
They themselves are turning into wrapper code for other libraries (e.g. the LLM abstraction which litellm handles for them).
Can also add:
Option 3: Use instructor + litellm (probabyly pydantic AI, but have not tried that yet)
Edit: As others pointed out their optimizing algorithms are very good (GEPA is great and let's you easily visualize / track the changes it makes to the prompt)
The sklearn to me is (and mirrors) the insane amount of engineering that exists/existed to bring Jupyter notebooks to something more prod-worthy and reproducible. There’s always going to be re-engineering of these things, you don’t need to use the same tools for all use cases
Hmm not quite what I meant. Sklearn has it's place in every ML toolbox, I'll use it to experiment and train my model. However for deploying it, I can e.g. just grab the weights of the model and run it with numpy in production without needing the heavy dependencies that sklearn adds.
That initial drop reminds me of one of the things that stuck to me from my thermodynamic lectures / tests: If you want to drink coffee at a drinkable temperature in t=15min, will it be colder if you add the milk first or wait 15min and then add milk? (=waiting 15 min because the temperature differential is greater and causes a larger drop). Almost useless fact, but it always comes up when making coffee.
This is true if the milk is in the fridge the whole time. With the milk out the whole time, it's nearly the same, exact answer depends on the geometry of both containers.
To an extent, but with caution and charity. A lot of exceptionally good people have come from bad families - one of the Borgias was a saint, for example. A lot of exceptionally nasty people seem to have perfectly nice families.
Of course sometimes people who are, for example, brought up to be racist, are racist.
Agreed, I think it also acts as a hiring filter to scan for candidates that have been exposed to this kind of language and can speak it fluently. The bigger the cooperation, the more widespread that is though, don't see it as often in mid sized companies. Was looking into a director role at a large org and there were lots of very new words thrown at me very quickly.
One thing I'd love the US to do was something that happend in Germany ~2015, where they bought a lot of "Steuer-CD"s, with leaked info about people hiding money in offshore accounts. Then they allowed everyone to self report and applied more scrutiny to larger corporations which in total added several billions in revenue.
The US passed FATCA in 2010, you can't operate a foreign bank that touches US anything without snitching out accounts with US persons as ultimate beneficial owner.
rumors I've heard was that github is mostly run by contractors? That might explain the chaos more than simple vibe coding (which probably aggravates this)
What would be cool if this somehow could do a comparison by provider. E.g. in the last outages anthropic models running on vertex were apparently less affected than those deployed elsewhere. (Not saying that one is better than the other, but would be a neat read out).
reply