HN Explorer

Ask HN: Agents get dumber before release of new model version?

9 points by sporkland ↗ HN
I've noticed an effect with openai where my codex agents seem to perform worse in the week(s) leading up to a new release. I'm wondering if the vendors tweak effort params at all to free up hardware to host the new version. It's a double win as the new model will look night and day better to their regular users when the new model is released presumably with effort back at normal levels.

Is this a known phenomenon? Are any folks trying to measure any of this objectively?

7 comments

[ 2.9 ms ] story [ 20.7 ms ] thread
Fizzadar
Reminds me of a similar effect around iPhone releases (https://www.statista.com/chart/2514/iphone-releases/, many others). Can’t say I’ve noticed any change.
cyanydeez
more likely there's some pressure on GPU vs CPU compute resources while the AI company tries to scale out a new model, leading to some type of degradation.

Assuming it's not apple like fraud.

suprjami
Yes, this is already a widely circulated unproven LLM conspiracy theory.
faangguyindia
yes, when they come with 5.5

5.3 becomes 5.4

and optimization and improvement to 5.4 are provided as new 5.5

this gives boost effect via anchor/decoy.

PreownedPlaid
I figure it's because limited compute, must redirect some for latest product