News for hackers. Stuff that matters.

A comment on If AI brings 90% productivity gains, do you fire devs or build better products?. Parent comment

Re:If AI brings 90% productivity gains, do you fire devs or ... by roncesvalles on Sunday March 22, 2026 @01:25PM (#47479840)
Did you use the best model available to you (Opus 4.6)? There is a world of difference between using the highest model vs the fast one. The fast ones are basically useless and it's a shame that all these tools default to it.
[ Parent | on HN ]
Re:If AI brings 90% productivity gains, do you fire devs or ... by fweimer on Sunday March 22, 2026 @02:21PM (#47480490)
To make this more confusing, there is a fast mode of Opus 4.6, which (as far as I understand it) is supposed to deliver the same results as the standard mode. It's much more expensive, but advertised as more interactive.
[ Parent | on HN ]
Re:If AI brings 90% productivity gains, do you fire devs or ... by moffkalast on Sunday March 22, 2026 @02:47PM (#47480732)
Opus is not cost effective.
[ Parent | on HN ]
Re:If AI brings 90% productivity gains, do you fire devs or ... by senordevnyc on Sunday March 22, 2026 @03:39PM (#47481268)
Compared to what? I spent about $700 last month on Cursor, mostly on Opus 4.6. The time it saved me is at least 10-20x more valuable than that. I keep trying to use GPT-5.3 Codex, because it's like 40% cheaper, but then the quality doesn't always seem quite as good, and it's honestly not worth it to me to save a couple hundred bucks a month for something that's 10% worse. The multiplicative value of what I'm building means it's worth it to pay extra for the SOTA model in almost all cases.
[ Parent | on HN ]
Re:If AI brings 90% productivity gains, do you fire devs or ... by roncesvalles on Monday March 23, 2026 @09:16PM (#47497469)
The cost-effectiveness of something that doesn't work is 0.
[ Parent | on HN ]