diff --git a/content/_index.md b/content/_index.md index db2a880d694ab..c9a97943a63ed 100644 --- a/content/_index.md +++ b/content/_index.md @@ -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. @@ -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) diff --git a/content/assets/honcho logo and text.png b/content/assets/honcho logo and text.png new file mode 100644 index 0000000000000..40d1a7c1a3ccf Binary files /dev/null and b/content/assets/honcho logo and text.png differ diff --git a/content/assets/honcho thumbnail.png b/content/assets/honcho thumbnail.png new file mode 100644 index 0000000000000..6e7e630335e40 Binary files /dev/null and b/content/assets/honcho thumbnail.png differ diff --git a/content/extrusions/Extrusion 01.24.md b/content/extrusions/Extrusion 01.24.md new file mode 100644 index 0000000000000..e3cb0c87d3923 --- /dev/null +++ b/content/extrusions/Extrusion 01.24.md @@ -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): + + + +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 + +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) 🫡. \ No newline at end of file diff --git a/content/notes/The machine learning industry is too focused on general task performance.md b/content/notes/The machine learning industry is too focused on general task performance.md index 6b00d111d1072..8965fa30889be 100644 --- a/content/notes/The machine learning industry is too focused on general task performance.md +++ b/content/notes/The machine learning industry is too focused on general task performance.md @@ -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. diff --git a/package-lock.json b/package-lock.json index f1d8657b102ae..7c12e7146da5d 100644 --- a/package-lock.json +++ b/package-lock.json @@ -1,20 +1,12 @@ { "name": "@jackyzha0/quartz", -<<<<<<< HEAD "version": "4.1.2", -======= - "version": "4.1.0", ->>>>>>> f8d1298d (fix: missing field in config) "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "@jackyzha0/quartz", -<<<<<<< HEAD "version": "4.1.2", -======= - "version": "4.1.0", ->>>>>>> f8d1298d (fix: missing field in config) "license": "MIT", "dependencies": { "@clack/prompts": "^0.6.3", diff --git a/quartz/styles/custom.scss b/quartz/styles/custom.scss index c642fb892cb45..983310eb0fed9 100644 --- a/quartz/styles/custom.scss +++ b/quartz/styles/custom.scss @@ -20,3 +20,9 @@ img { display: flex; justify-content: center; } + +iframe { + display: block; + margin-left: auto; + margin-right: auto; +}