Definitely agree! I spent so many hours reading BYTE and Computer World and OMNI - and learned so much along the way. If y'all are interested in visualizing and exploring older computer magazines: https://thestacks.dev :)
I’ve always been obsessed with the "Depths of Wikipedia" -- those weird connections you find between totally unrelated topics. I built https://on-the-same.page to gamify that experience, and to help spark new serendipitous discoveries + learn new facts.
It’s a web app that lets a player race from Topic A to Topic B, embedded in the browser (and gamified with a global leaderboard).
Technical details:
- Built using AI Studio and Antigravity.
- Uses Firestore to handle state management.
- Deployed via Cloud Run.
It’s currently live at https://on-the-same.page. Let me know if you find any dead ends or if you have feature requests! And please suggest new topics for the explorations; will turn this into a model eval for computer use after getting enough examples. :)
Reimagined NASA’s Space Math curriculum (https://spacemath.gsfc.nasa.gov/) as an immersive game, instead of static PDFs. Students solve the same problems real scientists face daily -- calculating orbits and trajectories, dealing with space weather, etc. -- in an interactive way that goes beyond worksheets (or just sending PDFs to an LLM).
Powered by Gemini for storytelling and text-to-speech (TTS). Links to the GitHub repo and live link that you can play above, thanks to Google Cloud Run. Please file feature requests, if there's enough interest will add more missions and a leaderboard.
"While we built next-generation experiences for developers, our business failed in two important ways.
First, we failed to deliver our vision of AI-assisted programming because we were 10+ years too early to market, i.e. the tech is not ready yet.
We built the most-advanced AI for helping developers, but it fell short of the 10× improvement required to break through because today’s state of the art for ML on code is not good enough. You can see this in Github Copilot, which is built by Github in collaboration with Open AI. As of late 2022, Copilot has a number of issues preventing it from being widely adopted.
The largest issue is that state-of-the-art models don’t understand the structure of code, such as non-local context. We made some progress towards better models for code, but the problem is very engineering intensive. It may cost over $100 million to build a production-quality tool capable of synthesizing code reliably, and nobody has tried that quite yet.
Nonetheless, we could have built a successful business without 10×’ing developer productivity using AI, and we did not do that.
We failed to build a business because our product did not monetize, and it took too long to figure that out."
> _I'm thinking of a built in voice chat as well as multi-author editing within the same Codespace._
You should try Live Share! VS Code Live Share enables you to collaboratively edit and debug with others in real time, regardless what programming languages you're using or app types you're building. It also supports voice chat:
:( Former student from Rice, and can definitely attest to this.
I received full a full tuition scholarship when I matriculated in 2008; the number of students in a similar situation was in the dozens.
Potential attendees are accepted based on SAT scores; class rank; extracurricular activities; etc.; and if the applicants make it through all of those bandpass filters, they're awarded full-tuition scholarships.
Getting data into a reasonable format is (unfortunately!) a huge part of the machine learning process; that was the motivation for tools like pandas (in Python) and dplyr (for R). Joseph is describing a machine-learning-enabled way to automate some of that data cleaning, which is pretty cool.