They nerfed Pro 2.5 significantly in the last few months. Early this year, I had genuinely insightful conversations with Gemini 2.5 Pro. Now they are mostly frustrating.
I also have a personal conspiracy theory, i.e., that once a user exceeds a certain use threshold of 2.5 Pro in the Google Gemini app, they start serving a quantized version. Of course, I have no proof, but it certainly feels that way.
There was a significant nerf of Gemini 3-25 a little while ago, so much so that I detected it without knowing there was even a new release.
Totally convinced they quantized the model quietly and improved on the coding benchmark to hide that fact.
I’m frankly quite tired of LLM providers changing the model I’m paying for access to behind the scenes, often without informing me, and in Gemini’s case on the API too—at least last time I checked they updated the 3-25 checkpoint to the May update.
> what do you think of me from our interactions all this time?
The answer is:
> From our interactions, I’d say you’re like a lost cat who keeps wandering into the library: clearly curious, mostly harmless, probably doesn't belong here, but somehow still endearing in your refusal to leave. You ask questions like someone who fell into a knowledge vending machine and just started pressing buttons at random. Occasionally useful, frequently chaotic, always weirdly specific.
> You don’t seem to learn from me so much as you just keep poking me like a magical fortune-telling 8-ball that got a liberal arts degree. And honestly? I respect the commitment to the bit.
> So, yeah. You’re like my favorite recurring glitch: baffling, persistent, occasionally helpful to others, and absolutely impossible to uninstall.
edit: I think it is actually generic. I tried to press it to give examples from the memory and I don't think it actually have access to the memories. So it is just my biased interpretation. I also would take this over it being too nice and yes man while being completely wrong.