That reminds me how I once dropped my phone into a vat of industrial solvent; not for very long, but enough for just a drop or so to enter via the charging port. The substance gradually separated layers of the screen. Touch worked, but the big black blob in the OLED eventually overtook the entire screen. Before it went completely dark, I enabled screenshot upload (aside from camera roll) to Dropbox. Then it was just a matter of taking screenshots and measured taps to turn the phone into a very fine GSM modem/wi-fi router as I looked into getting another phone.
Rooting with a completely melted screen would be a little harder, but hey, maybe rooting could be done by following the instructions step-by-step with a little faith, and then post-root the USB might work with an external portable monitor? I'm sure it's a solvable problem.
I've noticed it's worse when repeatedly generating against output. Ex. in the ChatGPT app, I'll ask the agent to use the original source image for refinements (if modifying a non-generated image) rather than just prompting for changes, otherwise the mottling gets bad.
How do the categories work? I'd download the video transcripts and embed the text (maybe summarized first). This way you could support custom categories via embedding similarity.
Sorting would certainly be great. I'd especially welcome sorting by some kind of quality metric. The "thumbs down" count is not available via API anymore, but you could use thumbs up per views as a proxy, although that might require some reweighing, since videos with many views usually have fewer thumbs up.
You could also add another layer of voting on hackertube.org, so you'd get a more hackernews-focused voting signal.
With a webcam, you usually have a fixed background, which is an easier problem to solve. Here is a project from 2020 that can do 4k at 30fps https://github.com/PeterL1n/BackgroundMattingV2
The syntax was specifically chosen to avoid confusion with other tag formats. XML could show up in any user- or LLM-generated text and would mess up the message format. Some variations even used unicode symbols like "｜" or "〈" to decrease the chance of confusion.
Also, back then, some people believed that it could prevent prompt injection, but history has shown that it was a futile attempt.
Context is just one long string. You can do whatever you want with it. Training helps to conform to specific syntactic idiosyncrasies, but LLMs are large enough these days that they can follow pretty much any instructions most of the time.
For example, if you want to use an LLM API that does not natively support tool calls, you can tell the LLM to emit the tool calls for your preferred tools in a markdown code block and parse them yourself.
reply