Welcome to the inaugural edition of Plastic Labs' "Extrusions," a monthly prose-form synthesis of what we've been chewing on. No one needs another curation newsletter, so expect these 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). ## 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]]": >[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): 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). Then it was back to building. ## 2024 Roadmap 2024 will be the year of Honcho. Check out the new site we're launching today. ![[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 that allows anyone to quickly grok all the inferences and context at play in a conversation, compare sessions, and visualize and manipulate entire architectures--as well as swap and compare the performance of custom architectures across the landscape of models - Finally, we'll bundle the most useful of all this into an 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) 🫡.