diff --git a/content/_index.md b/content/_index.md index 0e469b51b109c..48f84273b0564 100644 --- a/content/_index.md +++ b/content/_index.md @@ -4,9 +4,9 @@ enableToc: false --- 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. +Here you'll find our blog posts, ["Extrusions" newsletter](https://plasticlabs.typeform.com/extrusions), [Honcho release notes](https://plasticlabs.typeform.com/honchoupdates), evergreen notes, and public research. And if you like, [you can engage with the ideas directly](https://github.com/plastic-labs/blog) on GitHub. -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. +Plastic Labs is a research-driven company working at the intersection of human and machine learning. Our current project is [Honcho](https://honcho.dev), 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. @@ -18,15 +18,24 @@ It’s our mission to realize this future. [[Theory-of-Mind Is All You Need]] [[Open-Sourcing Tutor-GPT]] -## Extrusions +## Research -[[extrusions/Extrusion 01.24|Extrusion 01.24]] -## Notes +[Violation of Expectation Reduces Theory-of-Mind Prediction Error in Large Language Models](https://arxiv.org/abs/2310.06983) + +## Evergreen Notes [[Honcho name lore]] [[Metacognition in LLMs is inference about inference]] [[The machine learning industry is too focused on general task performance]] -## Research +## Extrusions -[Violation of Expectation Reduces Theory-of-Mind Prediction Error in Large Language Models](https://arxiv.org/abs/2310.06983) +[[extrusions/Extrusion 01.24|Extrusion 01.24]] + +([Subscribe](https://plasticlabs.typeform.com/extrusions)) + +## Release Notes + +[[Release Notes 02.01.24]] + +([Subscribe](https://plasticlabs.typeform.com/honchoupdates)) diff --git a/content/releases/Release Notes 02.01.24.md b/content/releases/Release Notes 02.01.24.md new file mode 100644 index 0000000000000..4132e4974c58f --- /dev/null +++ b/content/releases/Release Notes 02.01.24.md @@ -0,0 +1,34 @@ +Today we're shipping a new site, docs, & lots of improvements.  + +We talked to a ton of agent developers beginning to build with Honcho over the past two weeks.   + +[We'd love to hear what you're building](https://discord.gg/plasticlabs). + +## Announcements + +- [Honcho website](https://honcho.dev) drop! + +- And we've [launched docs](https://docs.honcho.dev): + - Learn how to get started with Honcho + - Using our hosted version + - Running it locally + - Deploying your own instance with [Fly.io](https://fly.io/) (in <5 mins) + +- Learn how to use Honcho with + - An interface like Discord + - A LLM framework like [LangChain](https://www.langchain.com/) + +## Honcho v0.0.1 + +- A more stable version of the SDK  + +- An object-oriented client to make DevEx easier + +- A public demo server + - Use Honcho out of the box with no setup + +- App-level scoping + - One dev can run multiple apps from the same instance + +- Added rate limiting to server + - Protects from spam & improves reliability