From a6897fd536f8e0b00570d22586393b494c9b8528 Mon Sep 17 00:00:00 2001 From: Courtland Leer <93223786+courtlandleer@users.noreply.github.com> Date: Tue, 16 Apr 2024 15:03:50 -0400 Subject: [PATCH] primer draft --- content/blog/A Simple Honcho Primer.md | 86 +++++++++++++++++++ .../blog/Announcing Honcho's Private Beta.md | 16 +++- .../Introducing Honcho's Dialectic API.md | 4 + 3 files changed, 103 insertions(+), 3 deletions(-) create mode 100644 content/blog/A Simple Honcho Primer.md diff --git a/content/blog/A Simple Honcho Primer.md b/content/blog/A Simple Honcho Primer.md new file mode 100644 index 000000000..6dd487304 --- /dev/null +++ b/content/blog/A Simple Honcho Primer.md @@ -0,0 +1,86 @@ +--- +title: A Simple Honcho Primer +date: 04.16.24 +tags: + - blog + - honcho +--- +![[Honcho_Final-23.png]] + +Welcome to our quick, ELI5[^1] guide to [Honcho](https://honcho.dev). + +We'll cover [[A Simple Honcho Primer#^2f795f|what Honcho is]], [[A Simple Honcho Primer#^5125da|why we built it]], [[A Simple Honcho Primer#^1d2d3c|how to use it]], and [[A Simple Honcho Primer#^5a46d7|where the product is going]]. + +And throughout, we'll link to places you can dive deeper[^2]. + +## What is Honcho? +^2f795f + +Honcho is a personalization platform for large language model (LLM) applications built by [Plastic Labs](https://plasticlabs.ai). + +It's software infrastructure that lets AI apps to "get to know" their users, resulting in delightful experiences and optimized time to value. + +We'll have direct consumer experiences in the future, but today, the product is for application developers. It allows them to [[Introducing Honcho's Dialectic API#^a14c2f|reduce overhead]] and [[Introducing Honcho's Dialectic API#^07f7f8|enhance their machine learning pipeline]]. + +Right now, Honcho is in private beta, that means integrating our hosted version requires permission and onboarding[^3]. [You can sign-up here](https://plasticlabs.typeform.com/honchobeta). + +In its current form, Honcho has three core components: + +1. [[Announcing Honcho's Private Beta#^415f37|Storage]] - managing each user's data +2. [[Announcing Honcho's Private Beta#^453717|Inference]] - processing user data with our proprietary AI models +3. [[Announcing Honcho's Private Beta#^ee4516|Retrieval]] - surfacing user data to personalize user experience (UX) + +If you've heard of [Retrieval Augmented Generation](https://en.wikipedia.org/wiki/Prompt_engineering#Retrieval-augmented_generation) (RAG), this might sound familiar. But Honcho is doing *much* more than simple RAG. + +Behind the scenes, Honcho learns about users as people--[[User State is State of the Art|richly modeling identity]]. It seeks to understand their beliefs, hopes, dreams, history, interests, and preferences. + +It then acts as [[Introducing Honcho's Dialectic API|an oracle to each user]], allowing apps ask for any personal context they need to improve UX and giving them access to a social cognition layer. + +## Why We Built Honcho +^5125da + +We believe Honcho will be a key part of the AI application development stack. + +Why? Because [[Humans like personalization|users will want]] their AI experiences to be personalized and app developers shouldn't be redundantly solving that problem. + +But this might not be intuitive for a few reasons: + +- AI app builders are [[Machine learning is fixated on task performance|still focused on]] just getting general tasks to work +- LLMs' [[LLMs excel at theory of mind because they read|potential to personalize]] is still under-appreciated +- Historic examples of personalized apps just leverage our activity and engagement data +- Those examples tend target only base user needs and have poor privacy records + +Still, when interacting with an AI app, there's a sense that it *should* be getting to know us. In fact, we're often surprised when we realize it's not learning about us over time. And probably annoyed at having to start over. + +There's [[Announcing Honcho's Private Beta#^5b6ef1|enormous potenial]] for more positive-sum use of user data and for aligning AI applications more closely with user needs and preferences. + +## How to Use Honcho +^1d2d3c + + +## What's Next for Honcho +^5a46d7 + +Beyond improving our internal AI models so they can get to know users as richly as possible, we see three natural extensions in [[Announcing Honcho's Private Beta|Honcho's future]]: + +1. [[Announcing Honcho's Private Beta#^82dd3b|Monitoring & Evaluation]] - developer tools to understand & assess the impact of personalization + machine learning tools to build personalized datasets +2. [[Announcing Honcho's Private Beta#^a84f44|User-Facing Controls]] - chat with *your* Honcho to direct how it manages & shares data + authenticate with Honcho to sign-in to AI apps +3. [[Announcing Honcho's Private Beta#^ebf071|A Honcho Application Ecosystem]] - a network of apps contributing to & sharing Honcho data, user-owned & stored in confidential environments + +And in just a few weeks, we'll be launching a demo platform where anyone can interact with (& eventually build) Honcho powered apps. + +## Join the Beta + +[Sign-up for the private beta](https://plasticlabs.typeform.com/honchobeta) and start building personalized experiences. + +[Join Discord](https://discord.gg/plasticlabs), introduce yourself, and tell us what you're working on. + +[Visit our open-source repo](https://github.com/plastic-labs/honcho) and get your hands dirty. + +🫡 + +[^1]: "Explain it like I'm 5" + +[^2]: And if you want to get further into the weeds technically, head over to [our docs](https://docs.honcho.dev). If you want to go deeper on the philosophical or machine learning side, take some time to explore the [rest of the blog](https://blog.plasticlabs.ai). To sign up for the private beta waitlist, [click here](). + +[^3]: There's also [an open source repo for Honcho](https://github.com/plastic-labs/honcho), so you can self-host a basic version--[join our Discord](https://discord.gg/plasticlabs) for support. \ No newline at end of file diff --git a/content/blog/Announcing Honcho's Private Beta.md b/content/blog/Announcing Honcho's Private Beta.md index 17013477c..e15243fa8 100644 --- a/content/blog/Announcing Honcho's Private Beta.md +++ b/content/blog/Announcing Honcho's Private Beta.md @@ -46,12 +46,16 @@ Here's what the private beta currently includes, and what's on the way: #### User-Centric Storage +^415f37 + Honcho allows you to [store](https://docs.honcho.dev/getting-started/architecture) `users`, `messages`, `sessions`, & `metamessages`. That is, you can effortlessly record each user interaction with you application, organized on a per-user basis, and the product of any intermediate steps in between user message and application response. It also supports `documents` and `collections`. The former to store discrete user embeddings and the latter to organize them globally across sessions. These primitives are used by Honcho's personalization engine to begin modeling user identity based on each interaction. They can also be used to "bring you own" user data or context to be computed over and utilized by Honcho. #### Personalization Engine +^453717 + Here's where the magic happens. Honcho leverages everything in storage to run theory of mind inference and automatically learn about each user. The personalization engine both pulls out user desires, history, beliefs, emotions, etc from the data and surfaces it on demand. You can use it to answer queries, run prediction, build training sets, hydrate prompts, or cache for later. Deterministically inject specific types of context or let your LLM dynamically decide what's most useful in each moment. @@ -60,6 +64,8 @@ Honcho is always updating user identity, so it's ready when you need it. ##### Dialectic API +^ee4516 + Our [[Introducing Honcho's Dialectic API|Dialectic API]] is how your app-side LLM interfaces with the Honcho-side agent sitting on top of each user identity. This is done in natural language. It's an AI-native endpoint for direct LLM-to-LLM communication. It allows you to inject personal context and social cognition directly into your app's cognitive architecture wherever you need it, sync or async. Agent-to-agent chat over each user. @@ -68,11 +74,13 @@ It allows you to inject personal context and social cognition directly into your #### User-Specific Monitoring (coming soon...) +^82dd3b + Soon, Honcho will support a suite of tools to get the most out of our personalization platform. - **Visualization tools** - it's hard to grok and track everything going on within a session, we're building clean ways to visualize this an its relationship to all the background inference -- **Dialectic Playground** - take past sessions and run simulations predicting user behavior to see how things could have gone better or worse and how to optimize +- **Dialectic Playground** - take past sessions and run simulations predicting user behavior to see how things could have gone better or worse and how to optimize - **Evaluation & Benchmarking** - the state of theory of mind research is highly compelling, but [[Achieving SOTA on OpenToM with DSPy#^0b4f2e|we need practical, app & user specific evals]] @@ -93,13 +101,15 @@ All that guides a roadmap including, but not limited to: - **Per-user models** - understanding, representing, & updating the full breadth of user identity - **A *network* of Honcho-powered apps** - agents can share user data, reducing overhead & onboarding, just-in-time personalization - + ^ebf071 - **User owned data & confidential computing environments** - re-centralizing personal data around the person, then allowing approved applications to *compute-to* that data in a privacy preserving way -- **User-facing controls** - empower users to curate their Honcho identities, authenticate with Honcho, and define sensitive data sharing policies in natural language +- **User-facing controls** - empower users to curate their Honcho identities, authenticate with Honcho, and define sensitive data sharing policies in natural language ^a84f44 ### Who Is This For? +^5b6ef1 + We want to build with diverse projects at all stages of development--from ideation to production. We've already begun working with assistant, browsing, ecommerce, education, health, and productivity projects. Many more already on the waitlist are building in co-pilots, crypto, entertainment, finance, gaming, matchmaking, PKM, real estate, social media, & more. diff --git a/content/blog/Introducing Honcho's Dialectic API.md b/content/blog/Introducing Honcho's Dialectic API.md index f9a62acaf..abf704f21 100644 --- a/content/blog/Introducing Honcho's Dialectic API.md +++ b/content/blog/Introducing Honcho's Dialectic API.md @@ -52,6 +52,8 @@ Not only is it ideal from a development and design perspective, it's optimal for #### The DevEx Case +^a14c2f + Our Dialectic API is single endpoint for everything personalization. It reduces development overhead and allows you to get a personalized application running quickly and efficiently--speedrunning to production. @@ -64,6 +66,8 @@ However, this doesn't mean the developer now needs to be a prompting expert, flu #### The ML Case +^07f7f8 + Extra context improves user response generation, the more specific, the better. Focus on ML to crush your vertical, let Honcho personalize it by default. ##### Leverage Natural Language Plasticity