iiinova — where your digital self keeps evolving

Context Lab @contextlab.bsky.social · 08/09/2026

Second, delayed recountings looked like smoothed/simplified versions of the immediate recountings. We used the RDP algorithm, originally developed for cartographic simplification, to ask how much each "event" in people's recountings contributed to the overall trajectory shape.

110

Context Lab @contextlab.bsky.social · 08/09/2026

We found two interesting things. First, people's second (delayed) recountings were more similar to their own first recountings than to the original episode! Distortions of the original experience (of watching the episode), as reflected in the initial recounting, carry forward to future recountings.

110

Context Lab @contextlab.bsky.social · 08/09/2026

We had participants watch a television episode, then recount it (immediately), and then recount it again after a week-long delay.

120

Context Lab @contextlab.bsky.social · 02/04/2026

We've also put together other tools for probing and visualizing these maps. Here is a fun project that uses Blender to create synthwave-style 3D renders of knowledge maps: github.com/ContextLab/k...

120

Context Lab @contextlab.bsky.social · 02/04/2026

We also found that each person has a unique knowledge map, which can be revealed by asking just a few multiple-choice questions. We're excited about what this unlocks: imagine matching up study partners, conversation partners, or even social relationships by studying how people's maps align!

110

Context Lab @contextlab.bsky.social · 02/04/2026

One finding is that knowledge is fundamentally *smooth*. Given that you've answered a question correctly, the probability of answering another question correctly falls off smoothly with distance. (Same with *incorrect* responses.)

110

Context Lab @contextlab.bsky.social · 02/04/2026

First, and most importantly: given that someone's knowledge map shows that they have X level of knowledge about some concept, does that correspond to their actual knowledge? We show that the predicted knowledge track closely with people's chances of correctly answering held-out quiz questions.

110

Context Lab @contextlab.bsky.social · 02/04/2026

We had our participants answer multiple-choice quiz questions before and after watching a series of @khanacademy.org lectures.

110

Context Lab @contextlab.bsky.social · 02/04/2026

We use text embeddings to define a coordinate system for human knowledge. Any text (video transcripts, quiz questions, etc.) can be localized in the embedding space, which lets us capture the idea that knowing about one concept also increases the chances that you know about other related concepts.

120

Context Lab @contextlab.bsky.social · 11/03/2026

And if you actually want to see the diagram, here you go-- there was some weird blurring in the previous message. More info: cdl-scheduler.readthedocs.io/en/latest/ar...

000

Context Lab @contextlab.bsky.social · 11/03/2026

Curious how it works? We use @github.com pages to host a static frontend site, along with @developers.google.com apps scripts as a serverless backend. GitHub actions do scheduled maintenance and Google Calendar, Gmail, and Sheets provide the scheduling, notification, and database infrastructure.

100

Context Lab @contextlab.bsky.social · 28/10/2025

🚨 New preprint alert! We use trained-from-scratch GPT-2 models to characterize & capture the unique writing styles of individual authors. We also develop a new LLM-based relative stylometric measure. Paper: arxiv.org/abs/2510.21958 Code/data: github.com/ContextLab/l... 🤗: huggingface.co/contextlab