Live data from Hacker News

Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

unihiker.com

21–30 of 241 posts

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#21
post #9

Earlier quoted context omitted.

I'm incredibly curious what the experience of trying to write code with ChatGPT is like, if you have no prior knowledge. Obviously, it's impossible for me (and most others reading this) to un-know everything and approach it with fresh eyes. Are there any good real-time videos of non-programmers using ChatGPT to write code? (seems like the best way to understand what it's like)

I suspect that people would fail at the first hurdle and not even be able to run the code. I also wonder if they'd even know what to ask.

I've got a colleague who's been doing it with some success. Nothing fancy, just a bit of doodling around in Python for fun.

He's been leaning heavily on the repl.it Copilot thingy, so it's more autocomplete than code blocks. He uses ChatGPT for working out error messages.

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#22
post #9

Earlier quoted context omitted.

I'm incredibly curious what the experience of trying to write code with ChatGPT is like, if you have no prior knowledge. Obviously, it's impossible for me (and most others reading this) to un-know everything and approach it with fresh eyes. Are there any good real-time videos of non-programmers using ChatGPT to write code? (seems like the best way to understand what it's like)

I suspect that people would fail at the first hurdle and not even be able to run the code. I also wonder if they'd even know what to ask.

Reminds me of a (perhaps fake) screenshot of a conversation I saw that went:

Person A: I just used AI to make my own website, you're gonna be out of a job soon.

Person B: Oh? Let me see it.

Person A: Here it is C:\Users\Bob\Desktop\index.html

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#23

Unrelated but trying the HN wisdom here: any suggestion for a cheap touchscreen with a CPU attached and a battery that can be used as a control panel for Home Assistant? Yeah, probably some Android tablet but something that actually works well for this job and costs as less as possible? I cannot power it properly where I want to put it so it needs battery and then I can charge it as needed. Suggestions?

Kindle tablets with fully Kiosk browser.

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#24

Link to the pin out of the bottom connector: https://www.unihiker.com/wiki/board-overview Looks like a neat board, I could see making expansion modules that plug into the bottom and running like a IR blaster or other stuff off the SPI/UART bus.

> The UNIHIKER's pins are compatible with micro:bit They really bury the lede here, awesome that there is already an ecosystem that exists for the edge connector.

It's the same connector as on the BBC Micro:bit, right?

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#25
post #9
post #3

The video says "No coding skills? No worries. Just write your code with ChatGPT."

I'm incredibly curious what the experience of trying to write code with ChatGPT is like, if you have no prior knowledge. Obviously, it's impossible for me (and most others reading this) to un-know everything and approach it with fresh eyes. Are there any good real-time videos of non-programmers using ChatGPT to write code? (seems like the best way to understand what it's like)

I'm helping another fella who's new to coding, he's using GPT to make some code. Most of what it produces won't even compile. Building for sensors on an ESP32 platform. BUT! GPT will get a good way there, a main with some sub-routines, stuff like that. I don't think it's good enough to teach.

If you can already code, then GPT can ramp you up on a new project faster, or accelerate and existing project

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#26
post #9
post #3

The video says "No coding skills? No worries. Just write your code with ChatGPT."

I'm incredibly curious what the experience of trying to write code with ChatGPT is like, if you have no prior knowledge. Obviously, it's impossible for me (and most others reading this) to un-know everything and approach it with fresh eyes. Are there any good real-time videos of non-programmers using ChatGPT to write code? (seems like the best way to understand what it's like)

It’s pretty good depending on what you are doing. With Python and JS/TS, the last checkpoint for training datasets really matters. These api’s for no reason at all to me, rot incredibly fast, so the code it generates was valid in September 2020, but now it is almost completely incompatible.

I was raised with (80s/90s); never break the public api unless you have to and make a migration path if you do; now it is ‘let’s definitely break the public api, with any minor version change and just waste everyone’s life fixing it, we don’t care’. And gpt doesn’t know this. It usually does make up code that’s close to correct and relatively easy to fix though, but you need to know how to read the docs and not panic that actually everything is spitting errors.

If you ask it for C, Java or vanilla js it fares better but there you suffer from the memory window; now with 16k tokens, we are seeing massive improvements. The api deprecation (read; we just throw away or change without warning) issue remains and is a huge issue; I cannot even see how they would properly fix that in LLMs. They are going to have outdated versions in their search space; how do they know to ignore them? And next to that there are the hallucinations.

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#27
post #20

This device is similar to many hacker festival badges from the recent years. Just a bit more expensive. For example: - the Camp 2023 flow3r badge https://events.ccc.de/2023/06/05/camp23-the-flow3r-badge/ - the MCH2022 badge https://wiki.mch2022.org/Badge - the SHA2017 badge with E-Ink https://wiki.sha2017.org/w/Projects:Badge - the Camp 2011 badge R0ket https://events.ccc.de/camp/2011/wiki/R0ket The first three have…

This thing runs full linux and requires 3.3V, 2000mA (max). A badge is probably not the best use case.

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#28
post #9
post #3

The video says "No coding skills? No worries. Just write your code with ChatGPT."

I'm incredibly curious what the experience of trying to write code with ChatGPT is like, if you have no prior knowledge. Obviously, it's impossible for me (and most others reading this) to un-know everything and approach it with fresh eyes. Are there any good real-time videos of non-programmers using ChatGPT to write code? (seems like the best way to understand what it's like)

I am wondering why people seem to think it's so great for this. It's fine for I guess boiler plate code construction but totally falls over when I give it e.g. complicated Rust borrow checker problems. And if you tell it a mistake it's made, it just buries itself deeper branching off into spirals of more and more incorrent solutions.

To me, it's like a junior developer I have to coach constantly.

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#29

Link to the pin out of the bottom connector: https://www.unihiker.com/wiki/board-overview Looks like a neat board, I could see making expansion modules that plug into the bottom and running like a IR blaster or other stuff off the SPI/UART bus.

> The UNIHIKER's pins are compatible with micro:bit They really bury the lede here, awesome that there is already an ecosystem that exists for the edge connector.

Hey, that's really cool!

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#30

So, like all other "raspberry pi killers" this is running a patched kernel released by some company in Shenzhen with no plan to upstream changes or get them into the main kernel tree. E-Waste in less than three years!

Looks like it's based around the Rockchip RK3308 so it's likely not that bad. I'm sure this ships with some old patched vendor kernel but the SoC is already supported in mainline.

I've not gone through the other components but this probably doesn't take too much time to get to full mainline linux support.

Post reply on HN