Re:Evergreen: A Provably Safe Systems Language
by 0c3ca83 on Wednesday November 04, 2026 @11:58AM
(#50368400)
It's so strange how much effort goes into producing a language that you don't even care enough about the write.
[ Parent
| on HN ]
Re:Evergreen: A Provably Safe Systems Language
by gchamonlive on Wednesday November 04, 2026 @12:05PM
(#50368490)
[delayed]
Re:Evergreen: A Provably Safe Systems Language
by 0c3ca83 on Wednesday November 04, 2026 @12:20PM
(#50368661)
you can ask ai to write code in existing languages with large training sets, and it'll do better because of the large volume of training data.
if you're all-in on ai, you want to prioritize familiarity for agents.
Re:Evergreen: A Provably Safe Systems Language
by gchamonlive on Wednesday November 04, 2026 @12:24PM
(#50368693)
[delayed]
Re:Evergreen: A Provably Safe Systems Language
by ModernMech on Wednesday November 04, 2026 @01:14PM
(#50369389)
That would imply the AI should write every program in Python from now until the end of time; but just because the AI is most familiar with Python doesn’t mean we have to throw everything we know about system design and using the right tools for the job out of the window.
Re:Evergreen: A Provably Safe Systems Language
by 0c3ca83 on Wednesday November 04, 2026 @02:55PM
(#50370657)
Yes, Python or Rust would make sense.
Re:Evergreen: A Provably Safe Systems Language
by ModernMech on Wednesday November 04, 2026 @03:57PM
(#50371402)
Not in every situation for all time, that's my point. Which language the AI should use will evolve over time as use cases and computing hardware evolve. It isn't the case that language design is now ossified at whatever existed in 2023.
Also, what you're saying implies Python and Rust should stop evolving as languages, as changing the language would invalidate the vast quantity of work the AI has been trained on.
Re:Evergreen: A Provably Safe Systems Language
by 0c3ca83 on Wednesday November 04, 2026 @04:19PM
(#50371695)
> Not in every situation for all time, that's my point.
I think I mostly disagree.
Re:Evergreen: A Provably Safe Systems Language
by gchamonlive on Friday November 06, 2026 @12:51PM
(#50395731)
[delayed]
Re:Evergreen: A Provably Safe Systems Language
by jeremyloy_wt on Wednesday November 04, 2026 @12:06PM
(#50368497)
To me it’s about determinism and feedback. Agents will make mistakes but if they get clear feedback from the tools they use, they will produce a good result.
There are a shrinking number of reasons to geenfield projects with non-strict or unsafe languages now.