GitHub's UI doesn't show repo size anywhere obvious.
The API does — barely. You have to know to ask
Reposizer is a one-line wrapper around it that prints the answer in your terminal in under a second.
```
npx reposizer owner/repo
```
Size, stars, file count, languages — before you clone.
Works on private repos too, if you set GITHUB_TOKEN.
Docs: https://t.co/FRfsx3OJhr
NPM: https://t.co/XkTFNixsNv
Introducing the Open Knowledge Format (OKF), an open specification that formalizes the LLM-wiki pattern into a portable, interoperable format.
AI is only as smart as the context we give it. As we build more advanced, agentic AI systems, they need accurate metadata and context to be useful. But in most organizations, that context is locked inside fragmented data catalogs, isolated wikis, scattered code comments, or the minds of senior engineers. Every time a new AI agent is built, teams are forced to solve the exact same context-assembly problem from scratch.
To solve this, we've announced OKF, a vendor-neutral, open specification that formalizes the "LLM-wiki pattern" into a portable, interoperable format. It provides a standardized way to represent the enterprise knowledge that modern AI systems rely on.
— Just markdown: readable in any editor, renderable on GitHub, indexable by any search tool
— Just files: shippable as a tarball, hostable in any git repo, mountable on any filesystem
— Just YAML frontmatter: for the small set of structured fields that need to be queryable: type, title, description, resource, tags, and timestamp
We’ve also shipped reference implementations to help you hit the ground running, including an enrichment agent for BigQuery, a static HTML visualizer, and live sample bundles on @github → https://t.co/ilhAMCrcTc
➕ Knowledge Catalog can now natively ingest OKF!
Stop reinventing data models and building bespoke integrations for every new AI tool. Here's more about how OKF works → https://t.co/FR4kJRsgEH
We built an AI that can draw on your screen.
It's a true personal tutor.
Using Claude Opus we're able to draw polygons, point with pixel perfect accuracy, and walk users through complex steps directly on their screen.
Here's me learning Pythagorean Theorem + FL Studio.
Demo:
Quick update: Slack is now live on Brief. Mentions, requests, and follow-ups, from selected channels land in your daily briefing.
Initial version should be rolling out in a couple of days, just waiting on verification from providers.
Yeah, exactly there are similarities when interacting with common objects, sometimes even language agnostic, during the data gathering stage at Neurosync, people respond to “Left” the same way in different languages
Neuralink’s current BCI systems rely primarily on per-patient training and calibration to decode intentions from neural signals, they have not yet deployed a large population-scale pre-trained model for cross-user generalization.
There is definitely heavy use of ML
Well, that’s why most of the data generated to train a model is stimulus driven, and what that shows is that we do usually react to generic things in a similar pattern, case in point a red shoe shown to a random set of people would often generate a similar pattern in specific frequency bands in the brain.
Although that’s one of the major blockers in the space rn, the accuracy of a model trained on a few set of similar people would not perform well without tweaking to different set of people.
The solution to this in my opinion is more training data (in comparison to frontier models today) and deep learning instead of ML
I keep shouting this from the high heavens ..but our people just want to buy shares/tbills/houses/ and brag about their returns ...while leaving the actual full course industrial production meal on the table. Industrial and production business is not sexy....but that is how Dangote became a Billionaire. We can do this like the Chinese, Lebanese and Indians. Pool resources together...then go in big!!