Edit ‘autogollark’
This commit is contained in:
parent
e2a9384822
commit
027ab3689d
@ -43,7 +43,9 @@ Autogollark has emergently acquired some abilities which were not intended in th
|
||||
* {Inconsistent inference of own status as a language model chatbot, possibly based on seeing the name "autogollark". Often, Autogollark assumes use of GPT-3.
|
||||
* Autogollark will also sometimes alternately claim to be the "original" gollark, particularly when interacting with gollark.}
|
||||
* {"Self-reset" from attractor states (e.g. the [[As An AI Language Model Trained By OpenAI]] basin, all caps, etc) after some time passes, because of messages having `HH:MM` timestamps.
|
||||
* This is mostly specific to the 405B model; Autogollark in failover to the 8B internal model usually does not do this.
|
||||
* {This is mostly specific to the 405B model; Autogollark in failover to the 8B internal model usually does not do this.
|
||||
* DeepSeek-V3-Base is somehow //worse// at this than LLaMA-3.1-8B and can get locked in sillier states such as generating garbage.
|
||||
}
|
||||
}
|
||||
* {For somewhat [[Waluigi Effect]]-related reasons (past context is strong evidence of capability but weak evidence of incapability), Autogollark has some knowledge [[gollark]] does not, and can speak in a much wider range of languages.
|
||||
* "I, being more than just myself, actually can talk about both Galois theory and obscure poetry by Yeats."}
|
||||
|
Loading…
x
Reference in New Issue
Block a user