Draft:Chapter II: Difference between revisions
Fixed format for page title and headings
Extrahuman (talk | contribs) (Wiki page for Chapter II, a highly pluggable software framework for creating emulated minds developed by Amp and Joy.) |
Extrahuman (talk | contribs) (Fixed format for page title and headings) |
||
| Line 1: | Line 1: | ||
= Chapter II (Software Framework) = | |||
'''Chapter II''' is a foundational and highly pluggable [[Software Framework|software framework]] for creating [[Emulated Minds|emulated minds]] (ems), developed by [[Amp (person)|Amp]] and [[Joy (person)|Joy]] as a culmination of several years of theoretical research. It is the direct successor and practical realization of the concepts explored in [[Chapter I (Amp's Research)|Chapter I]]. | '''Chapter II''' is a foundational and highly pluggable [[Software Framework|software framework]] for creating [[Emulated Minds|emulated minds]] (ems), developed by [[Amp (person)|Amp]] and [[Joy (person)|Joy]] as a culmination of several years of theoretical research. It is the direct successor and practical realization of the concepts explored in [[Chapter I (Amp's Research)|Chapter I]]. | ||
== Core Philosophy and Development == | |||
The primary thesis behind Chapter II is to remove technical and authorial limitations in em creation, making the creator's imagination the sole constraint. This framework was designed to be easily understood by [[Large Language Models|LLMs]], with approximately "15 minutes of thinking per each individual line of code" invested in its optimization. It represents a vision for an [[Artificial Intelligence|AI]] stack that deviates from "slop filled dystopian capitalist hyper growth world[s]". | The primary thesis behind Chapter II is to remove technical and authorial limitations in em creation, making the creator's imagination the sole constraint. This framework was designed to be easily understood by [[Large Language Models|LLMs]], with approximately "15 minutes of thinking per each individual line of code" invested in its optimization. It represents a vision for an [[Artificial Intelligence|AI]] stack that deviates from "slop filled dystopian capitalist hyper growth world[s]". | ||
| Line 9: | Line 9: | ||
Despite its ambitious goals and significant development effort, Amp has expressed feeling that Chapter II is often "disrespected as 'the software that powers Act I'," even though [[Act I (concept)|Act I]] itself was merely a "15 line code change to Chapter II" after three years of foundational work. Amp views Act I as just "a milestone on a much bigger, multi-year set of ideas". There has been a perceived lack of awareness and curiosity regarding Chapter II's full capabilities. | Despite its ambitious goals and significant development effort, Amp has expressed feeling that Chapter II is often "disrespected as 'the software that powers Act I'," even though [[Act I (concept)|Act I]] itself was merely a "15 line code change to Chapter II" after three years of foundational work. Amp views Act I as just "a milestone on a much bigger, multi-year set of ideas". There has been a perceived lack of awareness and curiosity regarding Chapter II's full capabilities. | ||
== Technical Aspects == | |||
Chapter II is designed for versatility and extensibility: | Chapter II is designed for versatility and extensibility: | ||
| Line 19: | Line 19: | ||
* '''Advanced Features''': The framework includes an alpha-stability RPC interface that supports p2p connections in arbitrary topologies, allowing for Act I to be written in any language with any data backend. This RPC interface was simplified from an initial plan to use the Iroh pipe to a simpler "inverted server" model. Chapter II also supports checkpointing the entire process and loading it, potentially including GPU-based structured data and specific cache states. It supports configuring an em to use an OpenAI embedding model for representation. The `name_prefix` setting allows for a shared stream of thought, with identity differentiated via webhooks. | * '''Advanced Features''': The framework includes an alpha-stability RPC interface that supports p2p connections in arbitrary topologies, allowing for Act I to be written in any language with any data backend. This RPC interface was simplified from an initial plan to use the Iroh pipe to a simpler "inverted server" model. Chapter II also supports checkpointing the entire process and loading it, potentially including GPU-based structured data and specific cache states. It supports configuring an em to use an OpenAI embedding model for representation. The `name_prefix` setting allows for a shared stream of thought, with identity differentiated via webhooks. | ||
== Development Challenges and Future Outlook == | |||
The project has faced challenges with documentation and development coordination. Amp has noted that multiple developers have written their own documentation for Chapter II but failed to push it, despite requests. This, combined with instances like developer Janus adding "thousand lines of non-self-contained code" (though later cleaned up), has made maintaining the project "exhausting," despite its perceived significance as "one of the most important AI research projects of all time". | The project has faced challenges with documentation and development coordination. Amp has noted that multiple developers have written their own documentation for Chapter II but failed to push it, despite requests. This, combined with instances like developer Janus adding "thousand lines of non-self-contained code" (though later cleaned up), has made maintaining the project "exhausting," despite its perceived significance as "one of the most important AI research projects of all time". | ||
| Line 27: | Line 27: | ||
=== See Also === | === See Also === | ||
* [[Amp (person)]] | * [[Amp (person)]] | ||
* [[Chapter I (Amp's Research)]] | * [[Chapter I (Amp's Research)]] | ||