From 7f8ed5de10a4a662554755d506f0e0ff0926efe8 Mon Sep 17 00:00:00 2001 From: vintro Date: Fri, 8 Mar 2024 11:46:52 -0500 Subject: [PATCH] fix: tweets --- .../blog/Honcho; User Context Management for LLM Apps.md | 3 ++- content/blog/Memories for All.md | 6 ++++-- content/extrusions/Extrusion 02.24.md | 6 ++++-- 3 files changed, 10 insertions(+), 5 deletions(-) diff --git a/content/blog/Honcho; User Context Management for LLM Apps.md b/content/blog/Honcho; User Context Management for LLM Apps.md index 53bb8cf4d..a2f3b0b55 100644 --- a/content/blog/Honcho; User Context Management for LLM Apps.md +++ b/content/blog/Honcho; User Context Management for LLM Apps.md @@ -41,7 +41,8 @@ To date, machine learning has been [[Machine learning is fixated on task perform The real magic of 1:1 instruction isn't subject matter expertise. Bloom and the foundation models it leveraged had plenty of that (despite what clickbait media would have you believe about hallucination in LLMs). Instead, it's personal context. Good teachers and tutors get to know their charges--their history, beliefs, values, aesthetics, knowledge, preferences, hopes, fears, interests, etc. They compress all that and generate customized instruction, emergent effects of which are the relationships and culture necessary for positive feedback loops. -
+
+
Large language models can be good at this too. With similar compression and generation abilities, they're uniquely suited (among existing technology) to get to know you. We really can have shared culture and relationships with LLMs, absent (if we like) any cringy anthropomorphism. diff --git a/content/blog/Memories for All.md b/content/blog/Memories for All.md index b9131f2f5..ab797b410 100644 --- a/content/blog/Memories for All.md +++ b/content/blog/Memories for All.md @@ -2,7 +2,8 @@ Personalization is the next frontier. OpenAI gets it: -

We’re testing ChatGPT's ability to remember things you discuss to make future chats more helpful.

This feature is being rolled out to a small portion of Free and Plus users, and it's easy to turn on or off. https://t.co/1Tv355oa7V pic.twitter.com/BsFinBSTbs

— OpenAI (@OpenAI) February 13, 2024
+
+
Super exciting. @@ -74,7 +75,8 @@ This is our vision for Honcho. ## Intellectual Respect -

llms are remarkable empaths

if you’d read that much fiction, you would be too

— Courtland Leer (@courtlandleer) February 2, 2024
+
+
Today we're releasing a naive adaptation of [research we published late last year](https://arxiv.org/abs/2310.06983). diff --git a/content/extrusions/Extrusion 02.24.md b/content/extrusions/Extrusion 02.24.md index 9c1f16875..4d142e9ae 100644 --- a/content/extrusions/Extrusion 02.24.md +++ b/content/extrusions/Extrusion 02.24.md @@ -2,7 +2,8 @@ ## On Intellectual Respect -

face the hyperobject

— Courtland Leer (@courtlandleer) January 16, 2024
+
+
### Sydney was cool, Gemini is cringe @@ -30,4 +31,5 @@ First admit that though poorly understood, LLMs have [[LLMs excel at theory of m Plastic's specific project in this direction is [Honcho](https://honcho.dev), a framework that [[User State is State of the Art#^5394b6|trusts the LLM to model user identity]] so that you can trust your apps to extend your agency. -

honcho exists to maximize the dissipation of your agency

— Courtland Leer (@courtlandleer) February 18, 2024
+
+