HN Explorer

Gemini models increasingly stucking in thinking loop

11 points by StizzurpXDD ↗ HN
Using Google Antigravity and Google AI Studio, I have noticed that Gemini models, which includes 3.1 Pro and 3.5 Flash, are increasingly stucking in thinking loops. It has become much more common. So I did a 100 tasks test and out of them, 3.5 Flash got stuck in a loop 23 times, while 3.1 Pro was a lower 16 times.

8 comments

[ 3.0 ms ] story [ 27.4 ms ] thread
StizzurpXDD
All the tasks done were in Google Antigravity 2.0.
skerit
Was this not the case earlier? I've had it stuck in loops from day 1, even when Gemini 3 came out. I've never been able to actually use it for anything because it goes absolutely mental after a handful of turns.
haky_nash
conflicting instructions in prompts and though signatures being passed down across toolcall chains solved this for me
xnx
Do you have a single example?
chris_wot
I dunno about stuck, but I get a lot of errors that prevent me from submitting new prompts.
GL26
Do you have a website available to show the sessions ?
daft_pink
I find when I use Gemini Web Chat that it often just starts over mid-conversation and doesn't remember the rest of the context of the conversation whereas Claude and ChatGPT never do that.