[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/g/ - Technology


Thread archived.
You cannot reply anymore.


[Advertise on 4chan]


File: E78nr3hX0AczNEg.jpg (96 KB, 588x521)
96 KB JPG
>ask Claude to recreate an illustration as a SVG I can import into adobe and work with
>40 mins later usage runs out, buy extra because I need it today
>20 mins later it keeps second guessing itself and writing shit ass long paragraphs about how to do it

I'm so fucking tired, why is this so called breakthrough model so shitty and interpreting images and translating them to vector using simple shapes?
>>
>fell for the 1-900 "please hold" scam that's been around since the 80s
>>
File: Untitled.png (255 KB, 1557x563)
255 KB PNG
One hour, over 1M context (it had to compact the fucking conversation) + 6 euros spent in extra usage, and this is the result.

Fuck your "AGI"
>>
>>108965264
Current AI has fake vision.
>>
inkscape has a perfectly usable bitmap tracing tool. adobe almost certainly does too (and probably better)
you're the retard that decided to offload your last few remaining brain cells to a glorified autocomplete engine.
learn to use your tools. a language model does not see images, it sees a weighted token distribution that describes them
you deserve everything you fucking get
>>
>>108965388
Good enough for you goy. Now pay up and dont forget the tax+tip.
>>
>>108965264
Extremely low-efficiency way to go about it.
You could have just asked it what the best existing tool is to do that.



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.