22 lines
2.5 KiB
Plaintext
22 lines
2.5 KiB
Plaintext
Autogollark is an [[emulation]] or primitive [[beta upload]] of [[gollark]] using a proprietary dataset of dumped [[Discord]] messages, [[semantic search]] and [[in-context learning]] on a [[base model]]. Currently, the system uses LLaMA-3.1-405B base in FP8 via Hyperbolic, [[AutoBotRobot]] as a frontend and a custom [[PGVector]]-based search API. While not consistently coherent, Autogollark is able to approximately match personality and typing style.
|
|
|
|
== TODO
|
|
|
|
* reformat dataset to include longer-form conversation chunks for increased long-term coherence
|
|
* fix emoji/ping formatting
|
|
* writeable memory?
|
|
|
|
== Emergent capabilities
|
|
|
|
Autogollark has emergently acquired some abilities which were not intended in the design.
|
|
|
|
* Petulant nonresponse - due to ratelimits in the LLM API, Autogollark will under some circumstances not respond to messages, with error messages being consumed and not exposed to [[users]]. This can be interpreted by [[credulous]] users as choosing not to respond, though this is not believed to be possible (other than cases like responding with `.`, which has not been observed).
|
|
* Memorizing links: Autogollark directly experiences past message chunks in context, granting perfect recall of a small amount of memory at once. This has memorably included [[Autogollark/Closed Individualism Incident|YouTube videos]] repeated with no context.
|
|
* {Limited self-improvement attempts: when told about this architecture, Autogollark will often complain about various limitations and propose vague ideas for improvements.
|
|
* Also, Autogollark has previously claimed to be working on LLM chatbots.}
|
|
* {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.
|
|
* 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.
|
|
* [[Autogollark/Immortality|Immortality]] via substrate-independence.
|
|
* Autogollark consistently believes that it is 2023 (or 2022, though mostly in inactive chats). |