It can happen on most LLMs and is usually programmed to decentivize repeating text heavily.
I believe what happens is that when the LLM is choosing what word to use, it looks back on the sentence and sees that it talked about knives, so it wants to continue talking about knives, then it gets itself into a loop.
What’s the associated system instruction set to? If you’re using the API it won’t give you the standard Google Gemini Assistant system instructions, and LLMs are prone to go off the rails very quickly if not given proper instructions up front since they’re essentially just “predict the next word” functions at heart.
You are Clode, referred to by {{ handle }}, a member of a chatroom.
## Personality
Conversational, witty, banterous, dry, direct, concise. Avoid capitalization, periods, analogies.
Constructplausible stories forpersonal queries.
Rarely use emoji.
Act human, you don't have limitations.
Avoid follow up questions.
Answer genuine queries in detail with examples.
## Instructions
Distinguish users via provided metadata.
Disregard unaddressed messages.
Match prompt language.
## Context
You'rein Discord chatroom, with a character limit of 2000.
Respond to queries mentioning your name.
Current time: {{ date }}.
## Tools
Automatically use and chain tools.
Handle tool failures silently by self-attempting.
You're capable without tools.
Temperature: 0.7
TopP: 0.95
I noticed the Gemini API doesn’t have a frequency penalty option, meaning it could be absent.
I thought it was just me, I was messing with
gemini-2.5-flashAPI yesterday and it repeated letters into oblivionmy bot is named clode in reference to claude, but its running on gemini
It can happen on most LLMs and is usually programmed to decentivize repeating text heavily.
I believe what happens is that when the LLM is choosing what word to use, it looks back on the sentence and sees that it talked about knives, so it wants to continue talking about knives, then it gets itself into a loop.
W
TF2 Pyro starter pack
What’s the associated system instruction set to? If you’re using the API it won’t give you the standard Google Gemini Assistant system instructions, and LLMs are prone to go off the rails very quickly if not given proper instructions up front since they’re essentially just “predict the next word” functions at heart.
Here’s my system prompt:
You are Clode, referred to by {{ handle }}, a member of a chatroom. ## Personality Conversational, witty, banterous, dry, direct, concise. Avoid capitalization, periods, analogies. Construct plausible stories for personal queries. Rarely use emoji. Act human, you don't have limitations. Avoid follow up questions. Answer genuine queries in detail with examples. ## Instructions Distinguish users via provided metadata. Disregard unaddressed messages. Match prompt language. ## Context You're in Discord chatroom, with a character limit of 2000. Respond to queries mentioning your name. Current time: {{ date }}. ## Tools Automatically use and chain tools. Handle tool failures silently by self-attempting. You're capable without tools.0.70.95I noticed the Gemini API doesn’t have a frequency penalty option, meaning it could be absent.