I've been enjoying toast to help click through a project. I still mostly use Zed to handwrite code, but it's nice to open a pane and fire up toast from the terminal. paradise-runner.github.io/toast/
Any conversation
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.
Spotted this Royal Air Force A400 over the lake yesterday, it was so different from civil planes www.planespotters.net/โฆ/zm420-royal-air-force-โฆatlas-c1-a400m-180
Hi ha dies que em demano si no hauria d'escriure en catalร aquรญ, per tal que hi hagi mรฉs diversitat lingรผรญstica visible. Al cap i a la fi, avui en dia les traduccions sรณn econรฒmiques. La traducciรณ automร tica pot ajudar a preservar la diversitat lingรผรญstica del mรณn.
There are days when I wonder if I shouldn't write in Catalan here, so that there is more visible linguistic diversity. After all, translations are cheap these days. Machine translation can help preserve the world's linguistic diversity.
ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so iโm happy to settle into predictable models for a while.
recently, I have fallen in love with the artwork of takato yamamoto.
WARNING FOR NSFW ARTWORK
ibb.co/dJrZjr6C



