diff --git a/content/_index.md b/content/_index.md index bb28c3700603f..3a834ecc07a0c 100644 --- a/content/_index.md +++ b/content/_index.md @@ -4,7 +4,7 @@ enableToc: false --- Welcome to our collaborative second brain. -Here you'll find our blog, public notes, and research. [You can also engage with the ideas directly](https://github.com/plastic-labs/blog) on GitHub. +Here you'll find our blog, research, and public notes. You can also [engage with the ideas directly](https://github.com/plastic-labs/blog) on GitHub. [Plastic](https://plasticlabs.ai) is a research-driven company building at the intersection of human and machine learning. We believe re-centering LLM app development around the user will unlock a rich landscape of deeply personalized, autonomous agents. @@ -14,18 +14,12 @@ It’s our mission to realize this future. We post a few different types of content here: -- [[blog | Blog]] -- Deep dives into the philosophy, cognitive science, & machine learning underpinning our work - +- [[blog | Blog]] -- Deep dives into the philosophy, cognitive science, & machine learning underpinning our projects - [[notes | Evergreen Notes]] -- Short form working notes on Plastic theses - - [[extrusions | Extrusions]] -- Brief, densely-linked reflections synthesizing last month's conceptual work - - [[releases | Release Notes]] -- Weekly changelogs & details on new product features - - [[research | Research]] -- Formal published, preprint, or blog-style company research we've made public - - *Extrusions and Release Notes are also available as email newsletters:* - [Subscribe to Extrusions](https://plasticlabs.typeform.com/extrusions) - [Subscribe to Release Notes](https://plasticlabs.typeform.com/honchoupdates) @@ -35,5 +29,4 @@ We post a few different types of content here: If you find the content here compelling, explore our active projects: - [Honcho](https://honcho.dev) — A personalization platform for AI-powered applications, currently in [private beta](https://plasticlabs.typeform.com/honchobeta) - - [Bloom](https://bloombot.ai) — A theory of mind-powered AI learning companion, open sourced as [Tutor-GPT](https://github.com/plastic-labs/tutor-gpt) (slated for relaunch soon...) diff --git a/content/research/Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models.md b/content/research/Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models.md index 53b6730044a6b..8558a135e363d 100644 --- a/content/research/Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models.md +++ b/content/research/Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models.md @@ -1,6 +1,14 @@ +--- +title: Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models +date: 10.12.23 +tags: + - research + - ml + - philosophy +--- [Read on Arxiv](https://arxiv.org/abs/2310.06983). -Download here: +Or download here: ![[Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models.pdf]]