Skip to content

Commit

Permalink
Merge pull request #43 from plastic-labs/extrusions
Browse files Browse the repository at this point in the history
Extrusions 01.24
  • Loading branch information
courtlandleer authored Jan 25, 2024
2 parents 14074ed + 749c3c3 commit 9dc58b6
Show file tree
Hide file tree
Showing 7 changed files with 65 additions and 11 deletions.
13 changes: 11 additions & 2 deletions content/_index.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,9 @@ title: Home
enableToc: false
---

Welcome to our collaborative second brain. We're a research and development company working at the intersection of human and machine learning.
Welcome to our collaborative second brain. Here you'll find our blog posts, "Extrusions" newsletter, evergreen notes, and public research. And if you like, [you can engage with the ideas directly](https://github.com/plastic-labs/blog) on GitHub.

Our first product was [Bloom](https://bloombot.ai) -- a *subversive learning companion*. On this journey, we realized AI tools need a framework for securely and privately handling the intimate data required to unlock deeply personalized, autonomous agents.
Plastic Labs is a research-driven company working at the intersection of human and machine learning. Our current project is [Honcho](https://github.com/plastic-labs/honcho), a user context management solution for AI-powered applications. We believe that by re-centering LLM app development around the user we can unlock a rich landscape of deeply personalized, autonomous agents.

It’s our mission to realize this future.

Expand All @@ -15,6 +15,15 @@ It’s our mission to realize this future.
[[blog/Theory-of-Mind Is All You Need]]
[[blog/Open-Sourcing Tutor-GPT]]

## Extrusions

[[extrusions/Extrusion 01.24|Extrusion 01.24]]
## Notes

[[Honcho name lore]]
[[Metacognition in LLMs is inference about inference]]
[[The machine learning industry is too focused on general task performance]]

## Research

[Violation of Expectation Reduces Theory-of-Mind Prediction Error in Large Language Models](https://arxiv.org/pdf/2310.06983.pdf)
Binary file added content/assets/honcho logo and text.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added content/assets/honcho thumbnail.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
47 changes: 47 additions & 0 deletions content/extrusions/Extrusion 01.24.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
Welcome to the inaugural edition of Plastic Labs' "Extrusions," a monthly prose-form synthesis of what we've been chewing on.

This first one will be a standard new year recap/roadmap to get everyone up to speed, but after that, we'll try to eschew traditional formats.

No one needs another newsletter, so we'll work to make these worthwhile. Expect them to be densely linked glimpses into the thought-space of our organization. And if you like, [you can engage with the ideas directly](https://github.com/plastic-labs/blog) on GitHub.

## 2023 Recap

Last year was wild. We started as an edtech company and ended as anything but. There's a deep dive on some of the conceptual lore in last week's "[[Honcho; User Context Management for LLM Apps|Honcho: User Context Management for LLM Apps]]:"

>[Plastic Labs](https://plasticlabs.ai) was conceived as a research group exploring the intersection of education and emerging technology...with the advent of ChatGPT...we shifted our focus to large language models...we set out to build a non-skeuomorphic, AI-native tutor that put users first...our [[Open-Sourcing Tutor-GPT|experimental tutor]], Bloom, [[Theory-of-Mind Is All You Need|was remarkably effective]]--for thousands of users during the 9 months we hosted it for free...
Building a production-grade, user-centric AI application, then giving it nascent [theory of mind](https://arxiv.org/pdf/2304.11490.pdf) and [[Metacognition in LLMs is inference about inference|metacognition]], made it glaringly obvious to us that social cognition in LLMs was both under-explored and under-leveraged.

We pivoted to address this hole in the stack and build the user context management solution agent developers need to truly give their users superpowers. Plastic applied and was accepted to [Betaworks](https://www.betaworks.com/)' [AI Camp: Augment](https://techcrunch.com/2023/08/30/betaworks-goes-all-in-on-augmentative-ai-in-latest-camp-cohort-were-rabidly-interested/?guccounter=1):

<iframe src="https://player.vimeo.com/video/868985592?h=deff771ffe&color=F6F5F2&title=0&byline=0&portrait=0" width="640" height="360" frameborder="0" allow="autoplay; fullscreen; picture-in-picture" allowfullscreen></iframe>

We spent camp in a research cycle, then [published pre-print](https://arxiv.org/abs/2310.06983) showing it's possible to enhance LLM theory of mind ability with [predictive coding-inspired](https://js.langchain.com/docs/use_cases/agent_simulations/violation_of_expectations_chain) [metaprompting](https://arxiv.org/abs/2102.07350).

<iframe width="560" height="315" src="https://www.youtube.com/embed/PbuzqCdY0hg?si=OSujtqg44AK3y_W-" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>

Then it was back to building.

## 2024 Roadmap

This is the year of Honcho.

![[honcho logo and text.png]]

Last week [[Honcho; User Context Management for LLM Apps|we released]] the...

>...first iteration of [[Honcho name lore|Honcho]], our project to re-define LLM application development through user context management. At this nascent stage, you can think of it as an open-source version of the OpenAI Assistants API. Honcho is a REST API that defines a storage schema to seamlessly manage your application's data on a per-user basis. It ships with a Python SDK which [you can read more about how to use here](https://github.com/plastic-labs/honcho/blob/main/README.md).
And coming up, you can expect a lot more:

- Next we'll drop a fresh paradigm for constructing agent cognitive architectures with users at the center, replete with cookbooks, integrations, and examples

- After that, we've got some dev viz tooling in the works to allow quick grokking of all the inferences and context at play in a conversation, and visualization and manipulation of entire agent architectures--as well as swap and compare the performance of custom cognition across the landscape of models

- Finally, we'll bundle the most useful of all this into an opinionated offering of managed, hosted services

## Keep in Touch

Thanks for reading.

You can find is on [X/Twitter](https://twitter.com/plastic_labs), but we'd really like to see you in our [Discord](https://discord.gg/plasticlabs) 🫡.
Original file line number Diff line number Diff line change
Expand Up @@ -4,4 +4,4 @@ However, general capability doesn't necessarily translate to completing tasks as

Take summarization. It’s a popular machine learning task at which models have become quite proficient, at least from a benchmark perspective. However, when models summarize for users with a pulse, they fall short. The reason is simple: the models don’t know this individual. The key takeaways for a specific user differ dramatically from the takeaways _any possible_ internet user _would probably_ note.

So a shift in focus toward user-specific task performance would provide a much more dynamic & realistic approach. Catering to individual needs & paving she way for more personalized & effective ML applications.
So a shift in focus toward user-specific task performance would provide a much more dynamic & realistic approach. Catering to individual needs & paving the way for more personalized & effective ML applications.
8 changes: 0 additions & 8 deletions package-lock.json

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

6 changes: 6 additions & 0 deletions quartz/styles/custom.scss
Original file line number Diff line number Diff line change
Expand Up @@ -20,3 +20,9 @@ img {
display: flex;
justify-content: center;
}

iframe {
display: block;
margin-left: auto;
margin-right: auto;
}

0 comments on commit 9dc58b6

Please sign in to comment.