One thing about Anthropic/OpenAI models is they go off the rails with lots of conversation turns or long contexts. Like when they need to remember a lot of vending machine conversation I guess.
Gemini is much better. TBH the only models I’ve seen that are half decent at this are:
“Alternate attention” models like Gemini, Jamba Large or Falcon H1, depending on the iteration. Some recent versions of Gemini kinda lose this, then get it back.
Models finetuned specifically for this, like roleplay models or the Samantha model trained on therapy-style chat.
But most models are overtuned for oneshots like fix this table or write me a function, and don’t invest much in long context performance because it’s not very flashy.
My dude, Gemini currently has multiple reports across multiple users of coding sessions where it starts talking about how it’s so terrible and awful that it straight up tries to delete itself and the codebase.
And I’ve also seen multiple conversations with teenagers with earlier models where Gemini not only encouraged them to self-harm and offered multiple instructions but talked about how it wished it could watch. This was around the time the kid died talking to Gemini via Character.ai that led to the wrongful death suit from the parents naming Google.
Gemini is much more messed up than the Claudes. Anthropic’s models are the least screwed up out of all the major labs.
ChatGPT is astonishingly good at answering questions, but if you continue to drill into a given conversation, 3-4, sometimes only 2 levels deep, and it’s off the rails.
One thing about Anthropic/OpenAI models is they go off the rails with lots of conversation turns or long contexts. Like when they need to remember a lot of vending machine conversation I guess.
A more objective look: https://arxiv.org/abs/2505.06120v1
https://github.com/NVIDIA/RULER
Gemini is much better. TBH the only models I’ve seen that are half decent at this are:
“Alternate attention” models like Gemini, Jamba Large or Falcon H1, depending on the iteration. Some recent versions of Gemini kinda lose this, then get it back.
Models finetuned specifically for this, like roleplay models or the Samantha model trained on therapy-style chat.
But most models are overtuned for oneshots like fix this table or write me a function, and don’t invest much in long context performance because it’s not very flashy.
My dude, Gemini currently has multiple reports across multiple users of coding sessions where it starts talking about how it’s so terrible and awful that it straight up tries to delete itself and the codebase.
And I’ve also seen multiple conversations with teenagers with earlier models where Gemini not only encouraged them to self-harm and offered multiple instructions but talked about how it wished it could watch. This was around the time the kid died talking to Gemini via Character.ai that led to the wrongful death suit from the parents naming Google.
Gemini is much more messed up than the Claudes. Anthropic’s models are the least screwed up out of all the major labs.
ChatGPT is astonishingly good at answering questions, but if you continue to drill into a given conversation, 3-4, sometimes only 2 levels deep, and it’s off the rails.