zlacker
[return to "Scaling long-running autonomous coding"]
◧
1. andrew+M41
[view]
[source]
2026-01-20 11:10:27
>>srames+(OP)
Test suites just increased in value by a lot and code decreased in value.
◧◩
2. utopia+XW1
[view]
[source]
2026-01-20 16:36:59
>>andrew+M41
Doubt it, code will be generated to pass tests, not the intent behind the tests.
◧◩◪
3. Art968+nO3
[view]
[source]
2026-01-21 04:21:54
>>utopia+XW1
What makes you think the next generation models won't be explicitly trained to prevent this, or any other pitfall or best practice as the low hanging fruit fall one by one?
[go to top]