For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | more bcjordan's commentsregister

This is really exciting, one of those projects I've been tempted to build myself over the last decade+. There's a massive unmet market need for an LMS that plays well with other open source web software (integration with the existing OSS LMSes is a startup MVP's worth of effort itself).

Are there samples of dynamic web activities one could look at / a template format? It would be amazing if there were a way to provide interactive web activities hosted as open source (e.g. a repo that provides a ThreeJS activity with block-based coding, or e.g. a writing activity that measures language grade level while the student is writing).

Also curious if there are plans for localization support? (This can be tough to add on later with heavily dynamic/interactive blocks and activities)


Thanks for your comment Jordan!

We're experimenting with headless usage, as you said it would be possible to embed or add a "Dynamic Page Player" or "Canva" to your custom website, the format would be a JSON file that can be passed to that element

Localization support is definitely on the roadmap !


interesting Q of the schelling point for such a scenario. maybe blockchain / stenography in wikipedia / his original paper/post / usenet

if he kicked off a treasure hunt puzzle through some time-released clue in the future he'd basically be Ready Player One's James Halliday :D


This does seem like where composable fine-tuning / memory-encoded knowledge graphs will end up.

Couple related things in this direction that may be leveragable:

- WikiData: https://m.wikidata.org/wiki/

- Knowledge Futures' Underlay: https://docs.underlay.org/history


Freedom of expressions


Can one write installable apps for this OS that Llama can call out to?

We need to go deeper!


We will go the depth. In the coming versions.


Still feels like they're laser-focused on achieving AGI/aligned ASI. Improving chips and evolving the UX feel like cohesive (possibly requisite) intermediate steps


Been on the secure knot for nearly two decades. Looks great, perfect amount of grip (never unties) and easy pull to open.

Make sure you tie it balanced!


You know I'm a bit surprised Stripe has not put out more boilerplates that include integration with their platform. It's often a feature not added / coming soon in the OSS SaaS boilerplates I've seen.


Agreed. What do you think the reason for not doing it would be? Liability? Are they responsible if someone takes it and modifies code? I've gotta assume they could cover their butts with a terms of use.

This could be a very solid best practices utilizing product if they did put it out.


Pipedream is very good for a sort of medium-code Zapier like. Great for point and click hooking up web services but also being able to eject out into JS/Python/Docker with all the authentication done, debug/replay steps and production traffic errors, and generally nice magic support for npm dependency inclusion.

They also have nice repository integration and subdomain support now

Pricing is also super reasonable for anything other than eg high high volume analytics use cases.


Could you have it write code and run it on the machine too?


I was experimenting with this just last week. The TRS-80 CoCo was my first computer and I still have one. A year or two ago I was able to read and write data to a modern digital audio recorder.

I think a program could be built to write the audio file that the TRS-80 would understand. Then you could translate a code file to audio and LOAD it. I wrote such a program with the help of ChatGPT last week but the wav file didn’t quite sound right. After more research, I think it might be right and I just don’t remember the sound quite right.

This post made me think you might be able to go the other way too. I vaguely remember a command to forward the audio cassette (maybe in seconds). The host computer could listen for that forwarding command and respond with its translated wav. Forward 5 seconds could be for API call #5.

This would require no extra hardware on the TRS-80 side. You would just connect the audio jacks into a sound card headphone/mic port.

Edit: As another commenter posted, serial would probably be much easier. I didn’t even realize it had serial IO.


That would be a really cool addition. GPT seems less good at writing BASIC code, than other modern languages though. I think since GPT mostly crawls online sources there was less training material put online overall. :)


With 3.5-turbo-16k you could include quite a lot of example code or extra BASIC documentation if you are concise.

Targeting some retro platform for ChatGPT code generation is something I have been thinking about. Especially now that we have fine tuning. Because the domain of a retro system is relatively limited compared to the scope of modern platforms.

Maybe someone could train it with like 300 type-in BASIC programs along with a good paragraph-long description for each.

Then we could just give it a paragraph describing what we want and if we are lucky get a tailor-made program.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search:

HN For You