๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___) header
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___) profile picture

์—ฌ์ž Only / ํ•˜๊ณ  ์‹ถ์€ ๊ฒŒ ๋„ˆ๋ฌด ๋งŽ์€ ํ˜ธ์ฃผ ์›Œํ™€ ์˜ˆ์ • ๊ฐœ๋ฐœ์ž ! / ํˆฌ์ž / ์ˆ˜์ œํŠธ์œ— ํ•˜์ด๋ผ์ดํŠธ์— ๋ชจ์•„๋†จ์–ด์š” ๐Ÿค™ / ๋ฐด๋•Œ๋ฌธ์— ๋งžํŒ”์ด ์กฐ๊ธˆ ๋А๋ ค์š” ใ… ใ… 

Joined June 2025
Photo by ๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___)Photo by ๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___)Photo by ๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___)Photo by ๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___)Photo by ๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___)Photo by ๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___)Photo by ๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___)Photo by ๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___)Photo by ๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___)Photo by ๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค (@nkhla___)
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
๋‚˜๊ฐ™๊ฒฝ ํ•˜๋ฃจ๋ฅผ 3์‹œ๊ฐ„ ๋‹จ์œ„๋กœ ๋Š์–ด์„œ ์ƒ๊ฐํ•˜๋Š” ๊ฒŒ ์ง„์งœ ๋„์›€ ๋์Œ. ์˜ค์ „์— ๊ธฐ๋ถ„ ๋‚˜์œ ์ผ ์ƒ๊ฒจ๋„ '์˜ค๋Š˜ ๋งํ–ˆ๋‹ค'๊ฐ€ ์•„๋‹ˆ๋ผ '์˜ค์ „ ํƒ€์ž„ ๋งํ–ˆ๋„ค.' ํ•˜๊ณ  ์ ์‹ฌ๋จน๊ณ  ๋ฆฌ์…‹ํ•˜๋Š” ๊ฑฐ์ž„. ํ•˜๋ฃจ๋ฅผ 24์‹œ๊ฐ„์งœ๋ฆฌ๋กœ ์ƒ๊ฐํ•˜์ง€๋ง๊ตฌ 3์‹œ๊ฐ„์งœ๋ฆฌ ํ•˜๋ฃจ๋ฅผ 6๋ฒˆ ์‚ฐ๋‹ค๊ณ  ์ƒ๊ฐํ•˜๋ฉด (์ž˜๋•Œ ์ œ์™ธ) ๋‹ค์‹œ ์‹œ์ž‘ํ•  ๊ธฐํšŒ๋„ 6๋ฒˆ ์ƒ๊น€.
This Post is from an account that no longer exists. Learn more
27
11,385
798
34,852
1,365,649
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
๋‹น์žฅ ์นด์žํ์Šคํƒ„ ํ’๊ฒฝ๋งŒ ๋ด๋„ ์ด๋ ‡๊ฒŒ ๊ด‘ํ™œํ•˜๊ณ  ๋„“์„ ์ˆ˜๊ฐ€ ์—†๋Š”๋ฐ ์šฐ๋ฆฌ๊ฐ€ ๋งจ๋‚  ์ง‘ ํšŒ์‚ฌ ํ•™๊ต ํ‡ด๊ทผํ•˜๋ฉด ๋ฐฉ์— ๊ฐ‡ํ˜€์„œ ํŠธ์œ„ํ„ฐ ์œ ํŠœ๋ธŒ๋งŒ ๋ณด๋‹ˆ๊นŒ ์ •์‹ ๋ณ‘์ด ์˜ค๋Š” ๋“ฏ
์ด๊ฑฐ ์ „์— ๋ณธ ๊ฑด๋ฐ ์š”์ฆ˜ ๋งŽ์ด ๊ณต๊ฐ๋จ ๋จผ๊ฐ€ ์ด ์ผ์ƒ๋“ค์— ๊ฐ‡ํ˜€์„œ ์‚ฌ๋Š” ๋А๋‚Œ์ด ์ž์ฃผ ๋“ค์–ด์„œ ๋” ๊ทธ๋Ÿฐ๊ฐ€๋ด„
20
12,533
1,939
41,361
1,795,894
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
ๅ‘Š่ฏ‰ไฝ ไธ€ไธช่ฎฉไบบ็”Ÿๅ˜้กบ็š„็ง˜ๅฏ†๏ผŒๅฐฑๆ˜ฏๅชๅ…ณๆณจ่‡ชๅทฑใ€‚ไธๅŽปๅ…ณๆณจไปปไฝ•ไบบ็š„ๅŠจๆ€๏ผŒไธๅŽปๆฃๆต‹ไปปไฝ•ไบบ็š„ๆƒณๆณ•๏ผŒไธๅŽป่ฎพๆƒณไธ€ไบ›ๆฒกๆœ‰ๅ‘็”Ÿ็š„ไบ‹ๆƒ…๏ผŒไนŸไธ่ฆๅฆ„ๆƒณ็”จ่‡ชๅทฒ็š„ไธป่ง‚ๆ„ๅฟ—ๅŽปๆ”นๅ˜ไปปไฝ•ไบบใ€‚ไฟๆŒไธ“ๆณจ๏ผŒๆๅ‡่‡ชๅทฑ๏ผŒไฟๆŒๆˆ้•ฟใ€‚่ฎฉ่‡ชๅทฑ็ฎ€ๅ•ไธ€็‚น๏ผŒ็ณŠๅพไธ€็‚น๏ผŒ่ฟŸ้’ไธ€็‚นใ€‚ๆœ€็ปˆไฝ ๅฐฑๅ‘็Žฐ๏ผŒไฝ ๅฐ‘ไบ†็š„ๅพˆๅคš็ƒฆๆผ๏ผŒๅคšไบ†ๅพˆๅคš่‡ชๅœจใ€‚
191
3,599
84
18,301
367,642
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
์•„๋‹ˆ ๊ทผ๋ฐ ์ด๊ฑฐ ๊ดœํžˆ ํ•„์ˆ˜ํ…œ์ด๋ผ๊ณ  ์˜ค๋ฐ” ๋– ๋Š” ๊ฑฐ ์•„๋‹ˆ๊ณ  ๋‚˜์ค‘์— ์‹ค์—์„œ ๊ณฐํŒก์ด or ๊ฐ์ข… ๋ฒŒ๋ ˆ์™€ ๋งˆ์ฃผํ•˜๊ณ  ์‹ถ์œผ์‹ ๊ฑฐ ์•„๋‹ˆ๋ฉด ์ฒœ์› ์ฃผ๊ณ  ์‚ฌ์„ธ์š”... ์ด๊ฑด ๋งŽ์€ ๋œจ๊ฐœ์ธ๋“ค์˜ ํ”ผ๋กœ ์“ฐ์—ฌ์ง„ ํŠธ์œ—์ž…๋‹ˆ๋‹ค
์†”์งํžˆ ๋‹ค์ด์†Œ ๋œจ๊ฐœ์ธ ํ•„์ˆ˜ํ’ˆ ๋ญ ๊ทธ๋Ÿฐ ๋ฆด์Šค์—์„œ ๋‚˜์˜ค๋Š” ๊ฒƒ๋“ค ์ค‘์— ์ง„์งœ ํ•„์ˆ˜๋Š” ์—†๋‹ค๊ณ  ์ƒ๊ฐํ•จ ์ง„์งœ ํ•„์ˆ˜ํ’ˆ์€ ๋ฐ”๋กœ ์ด๊ฒƒ์ž„ ๋œจ๊ฐœ๋ฅผ ํ•˜๊ณ  ์‹ค์ด ์ง‘์— ์žˆ๋‹ค๋ฉด ๋ฌด์กฐ๊ฑด ์žˆ์–ด์•ผ๋งŒ ํ•œ๋‹ค ์ž˜๋ผ์„œ๋„ ์“ธ ์ˆ˜ ์žˆ์–ด์„œ ์•„์ฃผ ๊ตฟ
2
1,342
75
2,070
123,736
๋‚˜ ๋ฌดํ†ค๋˜...
This quoted post is unavailable.
1
2
487
๋ถ€์—…์œผ๋กœ ์˜จ๋ผ์ธ ๋ฌผ๊ฑดํŒ”์ด ํ•ด๋ดค๋Š”๋ฐ ์ง„์ƒ๋ฉ์ฒญ์ด๋“ค ๋„ˆ~~~~~~๋ฌด๋งŽ์•„์„œ์ ‘์Œ ์•„๋ฌด๋‚˜ํ•˜๋Š”๊ฑฐ์•„๋‹˜....
๋™์˜ํ•ฉ๋‹ˆ๋‹ค ๋ˆ๋ฒŒ๊ณ ์‹ถ์œผ๋ฉด ๊ทธ๋ƒฅ ์žฅ์‚ฌ๋ฅผ ํ•˜์„ธ์š” ์™ธ๊ตญ ํ”Œ๋žซํผ์— ๋‹ค์ด์†Œ ํ™”์žฅํ’ˆ ์˜ฌ๋ ค๋„ ํŒ”๋ฆฌ๋Š” ์‹œ๋Œ€๊ณ  ์ธ์Šคํƒ€ ๊ณ„์ •ํŒŒ์„œ ํ™”์žฅํ’ˆ ํŒ”์•„๋„ ํŒ”๋ฆฝ๋‹ˆ๋‹ค ๋ญ˜ ํ•ด๋„ ๋™์ธ์ง€๋ณด๋‹ค๋Š” ๋งŽ์ด ๋ฒŒ ๊ฒƒ์ž„
3
7
1,347
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
ๆˆ‘ๆœ€่ฟ‘ๆฏๅคฉๅœจ่ขซ้Ÿฉๅ›ฝไบบ็ง่‰ๆท˜ๅฎ่ดงโ€ฆ้Ÿฉๅ›ฝๅฅณๅญฉไปฌไฝ ไปฌ็œŸไผšๆญ้…ๅฎก็พŽ็œŸๅฅฝๅ•Šโ€ฆๆ„Ÿ่ฐขไฝ ไปฌโ€ฆ
818
5,792
511
31,749
1,704,362
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
์•ผ์ƒ ์š”๊ฑฐ ํƒ€์˜ค๋ฐ”์˜ค๊บผ์ž…๋‹ˆ๋‹ค ์ง„์งœ๊ฐ•์ถ” ๋”ฐ๋œปํ•˜๊ณ  ์žฌ์งˆ์ด ๋„ˆ๋ฌด์ข‹์Œ ๊ทผ๋ฐ 2๋งŒ์›์ž„
75
833
225
9,829
1,025,181
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
์„ธ์ƒ์—... Etsy ํ•œ๊ตญ์…€๋Ÿฌ ๊ฐ€์ž… ๋‹ค์‹œ ์—ด๋ฆฐ๊ฑธ.. 1๋…„ ๋ฐ˜ ๋งŒ์— ์•Œ๊ณ  ์ด์ œ ๊ฐ€์ž…. ์„ธํŒ…๋น„ 19๋‹ฌ๋Ÿฌ. ํ”Œ๋žซํผ/๊ฒฐ์ œ/์ถœ๊ธˆ ๋“ฑ์˜ ์ˆ˜์ˆ˜๋ฃŒ ๋ชจ๋‘ ํ•ฉ์น˜๋ฉด ๋Œ€์ถฉ 16~17% ์ˆ˜์ค€. ์ฝ”๋กœ๋‚˜ ๋•Œ.. ์•„์ด๋””์–ด์Šค๋กœ ์ปค์Šคํ…€ ํ‹ฐ์…”์ธ  ํŒ๋งค๊ฐ€ ๋˜๊ธฐ ์‹œ์ž‘ํ•˜๋ฉฐ.. ํ•ด์™ธ๋Š” ์—ฃ์‹œ๋กœ ๊ฐ€๋ณด๋ คํ–ˆ๋Š”๋ฐ ํ•˜ํ•„ ํ•œ๊ตญ์…€๋Ÿฌ ๊ฐ€์ž…์ด ๊ฐ‘์ž๊ธฐ ๋ง‰ํ˜”์—ˆ๋‹ค. ๋‹น์‹œ ์บ”๋ฐ”๋‚˜ ๋…ธ์…˜ ๋””์ง€ํ„ธํŒŒ์ผ์„ ์—ฃ์‹œ์— ์˜ฌ๋ ค๋†“๊ณ  ๋™๋‚จ์•„ ํ•ด๋ณ€์—์„œ ๋…ธํŠธ๋ถ๋งŒ ๋“ค๊ณ  ๋””์ง€ํ„ธ๋…ธ๋งˆ๋“œ๋กœ ์‚ด ์ˆ˜ ์žˆ๋‹ค๋Š” ๊ฐ•์˜ํŒ”์ด๋“ค์ด ๋„˜์ณ ๋‚ฌ์Œ. ๊ฒฝ์ œ์  ์ž์œ ๋ฅผ ์ด๋ฏธ ์ด๋ค—๋‹ค๋ฉด์„œ ๋ฐค๋‚ฎ์œผ๋กœ ๊ฒฝ์ œํ™œ๋™ ๊ฐœ์—ด์‹ฌํžˆํ•˜๋Š”.. ๊ทธ๋Ÿฐ ์นœ๊ตฌ๋“ค. ์•”ํŠผ ๊ฒฐ๊ตญ ํ•œ๊ตญ์˜ ์ €ํ’ˆ์งˆ ์…€๋Ÿฌ/์ƒํ’ˆ์ด ๊ฐ‘์ž๊ธฐ ๋Œ€๋Ÿ‰์œ ์ž…. ์—ฃ์‹œ๊ฐ€ ๋ฐํžŒ ๊ณต์‹์ ์ธ ์ด์œ ๋Š” ์—ฃ์ง€ํŽ˜์ด ๋„์ž…๋ฏธ์ง€์› ๊ตญ๊ฐ€๋ผ๋Š” ๊ฑด๋ฐ ๊ทธ๊ฒŒ ์˜จ๋ผ์ธ๊ฐ•๊ตญ ์‚ฌ์šฐ์Šค์ฝ”๋ฆฌ์•„๋ฅผ ๋ฌด๋ ค 4๋…„์ด๋‚˜ ๋ง‰์•„๋‘˜ ์ผ์ด๊ฒ ๋‚จ. ๋‹น์‹œ ๋ง‰ํžŒ ๋‚˜๋ผ๋Š” ์ด์ง‘ํŠธ, ํŒŒํ‚ค์Šคํƒ„, ์นด์žํ์Šคํƒ„, ์กฐ์ง€์•„. ํ•œ๊ตญ ์…€๋Ÿฌ๋“ค์ด ์กฐ์ง€์–ด ๋†“์•˜๊ธฐ์— ๋ง‰ํ˜”๋‹ค๋Š”๊ฒŒ ์ค‘๋ก . ์•”ํŠผ ๊ทธ๋žฌ๋˜ ๊ฒƒ์ด ๋‹ค์‹œ ๋šซ๋ฆฐ ๊ฒƒ์ด๋‹ค... ๋ผ๋Š” ๊ฑธ 18๊ฐœ์›” ์ „์— ์•Œ์•˜์–ด์•ผํ–ˆ๋Š”๋ฐ.. ์œผํžˆํžˆ ๋‚˜๋„์ฐธ.
1
183
12
534
56,648
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
46
1,225
1,259
7,709
3,350,377
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
์‚ผ์ „ ํ•˜๋‹‰ ๋งŽ์ด ์˜ฌ๋ผ์„œ ํƒ€๋ ค๊ณ  ํ•˜๋Š” ์‚ฌ๋žŒ๋“ค์•„ ๊ตญ์žฅ์€ ์šฐ๋ฆฌ์—๊ฒŒ ๊ธฐํšŒ ํ•œ ๋ฒˆ ์ค€๋‹ค ๊ทธ๋•Œ ํƒ€๋ผ
25
363
227
2,593
1,367,974
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
Tรผrbanlฤฑ kฤฑz dyson airwrapโ€™i napacak amk
Sรถzlenen bir รงiftin birbirlerine aldฤฑฤŸฤฑ hediyeler:
627
2,533
595
68,724
7,010,858
Pc๋กœ ์‚ด๊ป„๊ฑธ๊ฑธ๊ฑธโ€ขโ€ขโ€ขโ€ข
์นœ๋ชจ์•„ ์ฟจํƒ€์ž„ ๋Œ๋™์•ˆ ํ•  pc์ƒŒ๋“œ๋ก ์ƒ€๋Š”๋ฐ ์—ญ์‹œ ๊ฐœ๋˜ฅ์ปด์ด์–ด๋„ pc๊ฐ€ ๋‚ซ๊ตฌ๋‚˜...์Šค์œ„์น˜๋ณด๋‹ค ํ™”์งˆ์ด ํ›จ์”ฌ ์ข‹์Œ...
1
1
141
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
small room approved: multifunctional furniture that still looks aesthetic
3
444
35
5,415
210,750
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
Si usas Obsidian y tienes TDAH, esto puede ser oro. reADHD es un plugin para Obsidian hecho especialmente para personas con TDAH. Mejora el modo de lectura, aรฑade segmentaciรณn inteligente de texto y hace que leer y tomar notas sea mucho mรกs llevadero para cerebros neurodivergentes. (Estรก en chino, ya sabes lo que toca hacer) REPOOO๐Ÿ‘‡
5
49
3
726
39,402
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
Wow, this tweet went very viral! I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person's agent customizes & builds it for your specific needs. So here's the idea in a gist format: gist.github.com/karpathy/442โ€ฆ You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It's intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool.
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
1,121
2,825
685
26,768
7,354,480
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
ใฝใ“ใ‚ ใ‚ฏใƒฉใ‚ฆใƒ‰ๅณถใ€Žใ‚ใ‚‹ใฎใ‚„ใคใ€ ๆŸ“่‰ฒๅฏ่ƒฝใชๅ…จใฆใฎๅปบๆใƒ–ใƒญใƒƒใ‚ฏใ‚’ๆŸ“่‰ฒใ—ใฆไธฆในใฆใฟใพใ—ใŸใ€‚ ่‰ฒ่ฆ‹ๆœฌใซไฝฟใฃใŸใ‚Š ใ‚ชใƒ–ใ‚ธใ‚งใ‚ฏใƒˆๆ’ฎๅฝฑใ—ใŸใ‚Šใ”่‡ช็”ฑใซใฉใ†ใž ใ˜ใ‚…ใ†ใ—ใ‚‡ใ€6DXLPD6Fใ€‘ Every block. Every color. All here. #ใฝใ“ใ‚ใƒใ‚ฑใƒขใƒณ #ใฝใ“ใƒใ‚ฑ #Pokopia
ใฝใ“ใ‚ ใƒใ‚ฑใƒขใƒณ ใ‚ฏใƒฉใ‚ฆใƒ‰ๅณถใ€Žใ‚ใ‚‹ใฎใ‚„ใคใ€ ๅฟ…่ฆใช็‰ฉๅ…จ้ƒจ้›†ใ‚ใกใ‚ƒใ„ใพใ—ใŸใ€‚ ใ˜ใ‚…ใ†ใ—ใ‚‡ใ€6DXLPD6Fใ€‘ ใ‚ฒใƒผใƒ ๅ†…ใ€ใชใžใฎใ‚ดใƒผใ‚ฐใƒซใ‚’ไฝฟใฃใฆใ‚ขใ‚ฏใ‚ปใ‚นใŒๅฏ่ƒฝใงใ™ใ€‚ Everything You Need โ€“ Pokopia Treasure Island #ใฝใ“ใ‚ใƒใ‚ฑใƒขใƒณ #pokopia
21
836
58
5,529
891,646
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
ElevenLabs just lost its moat ๐Ÿคฏ Someone just dropped Voicebox, and it clones any voice from just a 3-second audio clip, running 100% locally on your machine. 100% Open Source
8
51
1
346
21,981
๋ฌผ๊ฐœ ๐Ÿฃ๐Ÿฅ๐Ÿค retweeted
ํŠธ๋ ˆ์ด๋„ˆ ์—ฌ๋Ÿฌ๋ถ„! ์„œ์šธ ์„ฑ์ˆ˜ ์ผ๋Œ€์—์„œํฌ์ผ“๋ชฌ ๋ฉ”๊ฐ€ํŽ˜์Šคํƒ€ 2026 "Pokรฉmon GO" ์„œ์šธ ์Šคํƒฌํ”„๋ž ๋ฆฌ๊ฐ€ ์ง„ํ–‰๋ฉ๋‹ˆ๋‹ค! ๐ŸŽ‰ ํฌ์ผ“์Šคํ†ฑ์„ ๋ฐฉ๋ฌธํ•˜๊ณ , ํฌํ† ๋””์Šคํฌ๋ฅผ ๋Œ๋ ค ์Šคํƒฌํ”„๋ฅผ ๋ชจ์œผ๋ฉฐ ์„ฑ์ˆ˜ ๊ณณ๊ณณ์„ ํƒํ—˜ํ•ด ๋ณด์„ธ์š”! ๐Ÿ—บ๏ธ โ€œPokรฉmon GOโ€์™€ ํ•จ๊ป˜ ์„ฑ์ˆ˜์—์„œ๋งŒ ์ฆ๊ธธ ์ˆ˜ ์žˆ๋Š” ํŠน๋ณ„ํ•œ ๋ชจํ—˜์ด ์—ฌ๋Ÿฌ๋ถ„์„ ๊ธฐ๋‹ค๋ฆฝ๋‹ˆ๋‹ค. โœ… ํ•œ๊ตญ์‹œ๊ฐ„ 2026๋…„ 5์›” 1์ผ 10:00 ~ 5์›” 31์ผ 20:00 ๐Ÿ“ ์„œ์šธ ์„ฑ์ˆ˜ ์Šคํƒฌํ”„๋ž ๋ฆฌ ์žฅ์†Œ ์ผ๋Œ€ #ํฌ์ผ“๋ชฌGO #PokemonGO pokemongo.com/news/mega-festโ€ฆ
7
276
142
873
215,113