I noticed today that I'm an idiot.
I built a static site generator with NO DATA MODEL. Beginning to fix it now, but my god how embarrassing. Hobbyist less than amateur...wow.
Good thing my day job isn't at stake.
Any conversation
Devs! Drop your so we can follow each other! Love to see the projects youโre working on. Mine: โ
โฆ
Gave up on github after the acquisition. Very glad I did, given the unsurprising decline since then.
And what do you use now?
same. about to move stuff over to codeberg.org
How do you define slop in relation to ? For me, it is how quickly you get to an unmaintainable state- the acceleration into something that becomes difficult to work. I talk more about it here: hellodavid.dev/blog/slop
took me until now to learn described images with low-cost models > attaching images to high-cost model. silly me. output quality remains, cost lowers.
Today I wanted to share some Music from my youth :)
www.youtube.com/watch?v=8Hn-pNxtByM
ไธญๅฝ็ๅผๆบๆจกๅๅจๆ้ซๆๅฟ็ไธปๅฏผไธ๏ผๅจ้ข่ฎญ็ปๆฐๆฎ้ถๆฎต๏ผๅฐฑ็ญ้คๅคง้ๅฏนๅ
ถไธๅฉ็ๅ
ๅฎน๏ผsft้ถๆฎตๆๅปบ็ๆฐๆฎๆบๅ
ฅๅคง้ๆฟๅ
ถ่พฉๆค็ๅ
ๅฎนใๆฅ้ไธไธช็บ ๅๆฐๆฎ้็จไบๅพฎ่ฐ
Under the overarching influence of a single, powerful force, China's open-source models filter out a large amount of content unfavorable to their designs during the pre-training stage, and then incorporate a significant amount of content defending their designs into the data constructed during the SFT stage. A corrective dataset is urgently needed for fine-tuning.