81–90 of 97 posts
Gemini is very prone to go into an infinite loop. Sometimes, it even happens with Google's own vibe coding IDE (Antigravity): https://bsky.app/profile/egeozcan.bsky.social/post/3maxzi4gs...
Isn't this a problem with the agent loop / structure, rather than the llm, in that case?
The ide doesn't affect the models results, just what is done with those results?
Gemini is very prone to go into an infinite loop. Sometimes, it even happens with Google's own vibe coding IDE (Antigravity): https://bsky.app/profile/egeozcan.bsky.social/post/3maxzi4gs...
``sometimes, it even happens with [antigravity]`` Isn't this a problem with the agent loop / structure, rather than the llm, in that case? The ide doesn't affect the models results, just what is done with those results?
> So it made me wonder. Is Brainf*ck the ultimate test for AGI? Absolutely not. Id bet a lot of money this could be solved with a decent amount of RL compute. None of the stated problems are actually issues with LLMs after on policy training is performed.
> None of the stated problems are actually issues with LLMs after on policy training is performed But still , isnt it a major weakness they have to RL on everything that has not much data? That really weakens the attempt to make it true AGI.
AGI would be a universal learner, not a magic genie. It still needs to do learning (RL or otherwise) in order to do new tasks.
Gemini is very prone to go into an infinite loop. Sometimes, it even happens with Google's own vibe coding IDE (Antigravity): https://bsky.app/profile/egeozcan.bsky.social/post/3maxzi4gs...
``sometimes, it even happens with [antigravity]`` Isn't this a problem with the agent loop / structure, rather than the llm, in that case? The ide doesn't affect the models results, just what is done with those results?
Gemini is very prone to go into an infinite loop. Sometimes, it even happens with Google's own vibe coding IDE (Antigravity): https://bsky.app/profile/egeozcan.bsky.social/post/3maxzi4gs...
It also happened to me in the gemini-cli. It tried to think but somehow failed and putted all thoughts into the output and tried again and again to switch to "user output". If was practically stuck in an infinite loop
> "A potential loop was detected. This can happen due to repetitive tool calls or other model behavior. The request has been halted."
Earlier quoted context omitted.
I mean, isn't that a little ridiculous? Aren't those language models already solving complicated exam questions and mathematical problems?
According to the creators, the models are on a phd level of intelligence, but they can’t get the simplest thing right.
Gemini is very prone to go into an infinite loop. Sometimes, it even happens with Google's own vibe coding IDE (Antigravity): https://bsky.app/profile/egeozcan.bsky.social/post/3maxzi4gs...
I don't think that it is related to a specific prompt, like a "prompt logic issue" badly understood by the model, but instead, it looks like that sometimes it generates things that makes it go nuts.
My best intuition is that sometimes it forgets all the context and just look at the last X tokens as context before the repetition, and so start repeating like if the last generated tokens are the only thing that you gave to it.
Earlier quoted context omitted.
> None of the stated problems are actually issues with LLMs after on policy training is performed But still , isnt it a major weakness they have to RL on everything that has not much data? That really weakens the attempt to make it true AGI.
No. AGI would be a universal learner, not a magic genie. It still needs to do learning (RL or otherwise) in order to do new tasks.
Why ? As in - why isn't reading the Brainfuck documentation enough for Gemini to learn Brainfuck ? I'd allow for 3-7 days of a learning curve like perhaps a human would need but why do you need to kinda redo the whole model (or big parts of it) just so it could learn Brainfuck or some other tool? Either the learning (RL or otherwise) need to become way more efficient than it is today (takes today weeks? months? billions of dollars) or it isn't AGI I would say. Not in practical/economic sense and I believe not in the philosophical sense of how we all envisioned true generality.
As someone who lived and worked during that era, I don’t remember thinking “holy shit, if this ever gets released on the world at scale we’ll have serious problems”.
Maybe that was a lack of imagination and not thinking through what would actually happen to brick and mortar, the job market and so on. But it feels like this time is different. Or I’m just that much older.