Re:Can LLMs write better code if you keep asking them to "wr...
by mulmen on Friday January 03, 2025 @03:36PM
(#42589244)
Doesn’t this line of thinking constantly redefine success until all software is only bugs?
Re:Can LLMs write better code if you keep asking them to "wr...
by wmanley on Friday January 03, 2025 @04:41PM
(#42589779)
Ah, so that’s what’s been happening!
Re:Can LLMs write better code if you keep asking them to "wr...
by mulmen on Saturday January 04, 2025 @01:43AM
(#42592978)
My personal theory is that the rapture actually already happened but we didn’t notice because only QA was without sin.
Re:Can LLMs write better code if you keep asking them to "wr...
by CapeTheory on Friday January 03, 2025 @05:43PM
(#42590273)
Always has been
Re:Can LLMs write better code if you keep asking them to "wr...
by econ on Friday January 03, 2025 @11:40PM
(#42592452)
Keep the secret!
Re:Can LLMs write better code if you keep asking them to "wr...
by amoss on Saturday January 04, 2025 @08:39AM
(#42594621)
We prefer to call it "engineering"
Re:Can LLMs write better code if you keep asking them to "wr...
by friendzis on Monday January 06, 2025 @03:28AM
(#42608789)
That's exactly what has been happening for decades now and what things like scrum actively encourage to happen.
Given work item does not fit into allotted timebox? Relax Definition of Done until it does ¯\_(ツ)_/¯
Next step would be to propose hardcoding 99930-3999 as the O(1) result and live with the output just being wrong sometimes. The bug rate is then in the ballpark of most modern software, including LLMs', so I'd say ship it.