291–300 of 332 posts
I'm confused, do people actually watch their agents code like it was a screen share? Why does the AI even mess with that, just send a diff over text? Is it getting a keyboard next? This is the definition of over-engineering. I don't usually criticize ideas but this is so stupid my head hurts.
You spent 3 months on this hacked together garbage when you probably could’ve just configured a pre-existing solution off the shelf with like 10 minutes of reading and understanding documentation. This blog post reeks of “you can just do things” type of engineering. This is the quality of engineering I would expect from “TPOT” (that part of Twitter) where people talk about working 12 hour days. It’s cause they’re wor…
what about av1?
Or maybe self-write the code to not create this hell of bullshit code that lead to the issues the article writes about?
Which you a Merry Christmas! :D
Earlier quoted context omitted.
Why would you do that? Nearly-static content is where you want even fewer keyframes than usual. In a situation like this you need them when the connection is interrupted and you reset things, and not much of anywhere else.
1 FPS with GOP 60 might just simply not play in some players.
I remember 12 years ago, while the Flash vs Html war was still raging on (pre-html5), I created a framework to create web video playback using CSS and JPEGs. It would expect a set of big JPEGs, each containing the frames of the video in a grid (a "reel"), and play it by changing the css background position (and swap out the background with the next jpeg once a "reel" was complete). It worked really well, and I also c…
"By the time you see a bug, the AI has already committed it to main" Beside of that the Author has no plan at all about encoding, mjpeg, vnc,.... Really, THIS is the product that they sell?! This sounds like a horrible work. Observing a coding agent that does my job, but faster and crappier than me and stopping it when it does totally bullshit to prevent it from commiting to main?
If I understand correctly, the clients of the video stream are web browsers and perhaps mobile devices, and the servers are Helix's. Would SVT-AV1 with low-latency mode not be an option?
Earlier quoted context omitted.
>Don’t assume something you cannot prove. Well it's an inherently unprovable accusation, so assumption will have to do. It reeks of LLM-ese in certain word choices, phrases, and structure, though. I thought it was quite clear. >It was great writing Err... no accounting for taste, I suppose.
Just saying but LLM-ese as the common dominator of how people wrote, it is likely the writing style of a lot of people
40mbps for video of an LLM typing text didn't immediately fire off alarm bells in anyone's head that their approach was horribly wrong? That's an insane amount of bandwidth for what they're trying to do.
Wait what? 40Mbps for a remote desktop? Event 10Mbps is insane. I remember deploying sunrays over dialup and the image wasn't that bad, yes it was low resolution and I think it was UDP, but the desktop was usable with a surprisingly low latency. To monitor an IA you can lower the bit depth considerably and not lose that much details on what is happening. If you control the web rendered, disable text anti aliasing, an…
Young engineers are bad.