Re:Are you expected to run five Python type-checkers now?
by nijave on Monday June 08, 2026 @05:00PM
(#48451978)
Because the English to code translation step is fallible
Re:Are you expected to run five Python type-checkers now?
by hocuspocus on Monday June 08, 2026 @06:57PM
(#48453591)
Which is precisely a reason for not using Python, despite LLMs being good at it.
Re:Are you expected to run five Python type-checkers now?
by nijave on Wednesday June 10, 2026 @07:18AM
(#48474613)
Why is that?
Re:Are you expected to run five Python type-checkers now?
by wolvesechoes on Tuesday June 09, 2026 @02:59AM
(#48457543)
> With writing code in english now, why have it use a slow weak language?
Because the feedback loop of writing few lines of Python inside Jupyter cell is much shorter than with your currently favorite AI tool. It costs less too.
Re:Are you expected to run five Python type-checkers now?
by mountainriver on Tuesday June 09, 2026 @02:37PM
(#48465537)
Implementing whole features is? What are we talking about?
ML still has a depth of libraries that can't be replicated easily but ML work is decreasing by the day with LLMs.