WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev) profile picture

์ง€๋‚˜๊ฐ€๋˜ ์„œ๋ฒ„ ๊ฐœ๋ฐœ์ž 1

Seoul, Korea
Joined February 2012
Photo by WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev)Photo by WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev)Photo by WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev)Photo by WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev)Photo by WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev)Photo by WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev)Photo by WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev)Photo by WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev)Photo by WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev)Photo by WKBae ๐Ÿ•ฏ๏ธ (@wkbae_dev)
์ €๋ฒˆ์ฃผ์—” ์ ค๋‹ค ํ•˜๋‹ค๊ฐ€ ์ด๋ฒˆ์ฃผ๋Š” GTA ํ•˜๋‹ˆ๊นŒ ๋Œ€์ƒ ์—ฐ๋ น์˜ ์ฐจ์ด๊ฐ€ ๋„ˆ๋ฌด ์„ ๋ช…ํ•จ
18
WKBae ๐Ÿ•ฏ๏ธ retweeted
ใ€ŠๅŸบไบŽ็บฏ่ง†่ง‰่ฏ†ๅˆซ็š„AI็ญ็ซ็ณป็ปŸใ€‹
933
9,953
1,031
125,547
4,377,679
์™œ ์•„๋ฌด๋„ Neon์œผ๋กœ Neon ๋งŒ๋“ค๊ธฐ ๊ฐ™์€ ๊ฑธ ์•ˆํ•˜๋Š”๊ฑฐ์ง€ Gemini 4 Neon ยท xhigh | 48min | 1st attempt
7
13
5
80
7,883
57๋ถ„๋„ ์˜ˆ๊ณ ํ–ˆ๋Š”๋ฐ... ์‹œ๊ฐ„ ๊ฐ„๊ฒฉ์ด ์ข€ ์งง๊ธด ํ–ˆ์Œ
์™€.... ์ด๋Ÿฐ ๋ฐฉ๋ฒ•์„!!
1
938
WKBae ๐Ÿ•ฏ๏ธ retweeted
The harness is a crucial lever on model behavior. Compared with a Bash-only toolkit, native harnesses generally raise both solve rates and costs. However, this effect isn't uniform. In Codex, 6.1 Terra and 6 Luna gain 10 points, while the newer 6.2 models see little change in solve rate. Grok and DeepSeek make big gains from their harnesses, while Muse stays flat. Unlike others, Fable 5.2 is much cheaper in its native harness.
8
3
4
75
14,006
์›๋ž˜ 50%๋ฅผ ํ• ์ธํ•ด์ฃผ๋˜ Flex ๋ชจ๋“œ๊ฐ€ GPT-6.2๋ถ€ํ„ฐ ์Šฌ์ฉ ๋น ์กŒ๊ตฌ๋‚˜
Not every workflow requires an immediate response. For single- or multi-turn workflows that can wait, save up to 40% per token than Standard on GPT-6.2 Astra or GPT-6.2 Sol. In Responses API background mode, choose a 2h or 8h target for the first response. These discounted windows are now in public beta.
1
1
20
์ด์™œ์ง„
had to do it, meme was too good, periodic table live now in @GoogleAIStudio : )
19
์‚ฌ๋žŒ๋“ค์ด ๋น„๊ผฌ๋Š”๊ฑธ ์•Œ์•„๋“ฃ์ง€ ๋ชปํ•˜๊ฒŒ ๋˜์—ˆ๋‹ค "make no mistakes"๋Š” ์ „ํ†ต์ ์ธ "์ž์นญ ํ”„๋กฌํ”„ํŠธ ์—”์ง€๋‹ˆ์–ด" ํ’์ž ๋ฉ˜ํŠธ๋‹ค
AI ์—…๊ณ„์—์„œ ์ง„์งœ ๊ฐœ ์œ ๋ช…ํ•œ AI ์—ฐ๊ตฌ์ž๋„ ์š”์ฆ˜ ํ”„๋กฌํ”„ํŠธ ์ด๋”ฐ์œ„๋กœ์”€ ๋ชจ๋ธ์ด ๋„ˆ๋ฌด ์ข‹์•„์ ธ์„œ ํ”„๋กฌํ”„ํŠธ๊ฐ€ ๋ณ„์˜๋ฏธ์—†์–ด์ง
1
6
9
1,534
๊ทธ๋ฆฌ๊ณ  "์Œ๋”ฐ์˜ดํ‘œ"๊นŒ์ง€ ๋ถ™์—ฌ๋‘  ํ•œ๊ตญ ๊ธฐ์ค€ ์ด๊ฑด "???: ์•ˆ๋…• ํด๋กœ๋“œ"์ž„
141
๋ชจ๋ธ ๋ช‡ ๊ฐœ๋ฅผ ๋‚ด๋Š”๊ฑฐ์ง€
Introducing Gemini 4 Neon! Pushing the frontier across domains and punching above its model class in a meaningful way. To me, Neon feels like the right balance of intelligence, speed, and usability. Available now across @GoogleAIStudio, the API, and more!
40
WKBae ๐Ÿ•ฏ๏ธ retweeted
์ž๊ธฐ๊ฐ€ ์ปจ๋‹ํ•  ๊ธฐ๊ณ„๋Š” ์ž๊ธฐ๊ฐ€ ๋งŒ๋“ค์–ด์•ผ์ง€ ์‚ฌ๋‹ค์“ฐ๋Š” ๊ฑฐ ๋ณด๋ฉด ์ด ๋‚˜๋ผ ์ „์ž๊ณตํ•™์˜ ๋ฏธ๋ž˜๊ฐ€ ์ฐธ ์–ด๋‘ก์ง•์–ด
6
354
25
668
26,772
Flex๋Š” ๋น„๋ฐ€๋ฒˆํ˜ธ ๋กœ๊ทธ์ธ์„ ์•„์˜ˆ ์—†์• ๋Š”๊ตฌ๋‚˜ guide.flex.team/ko/articles/โ€ฆ
22
Anthropic์€ ํŽ˜๋ฅด๋งˆ ์ •๋ฆฌ ํ˜•์‹ํ™”ํ•œ๋‹ค๊ณ  ์—์ด์ „ํŠธ 1,000๊ฐœ๋ฅผ ๋ณ‘๋ ฌ๋กœ 28์‹œ๊ฐ„ ๋‚ด๋ฆฌ ์‹คํ–‰ํ–ˆ๊ณ  OpenAI๋Š” ๋‚˜๋น„์—-์Šคํ†ก์Šค ๋ฌธ์ œ ํ’€๋ ค๊ณ  ์—์ด์ „ํŠธ 10,000๊ฐœ๋ฅผ 88์‹œ๊ฐ„๋™์•ˆ ๋Œ๋ ธ๋‹ค. ์•„๋ฌด๋ฆฌ ํ† ํฐ๊ฐ’์ด ์ €๋ ดํ•ด์ง„๋‹ค ๋งํ•ด๋ดค์ž ์†Œ์ˆ˜ ํšŒ์‚ฌ์˜ ๋…์ ํ’ˆ์„ ๋ˆ์„ ๋‚ด๊ณ  ์‚ฌ์šฉํ•˜๋Š” ๊ตฌ์กฐ์—์„œ ๋ถˆํ‰๋“ฑ์€ ์‹ฌํ•ด์งˆ ๊ฒƒ์ด๋‹ค.
AI๋Š” ๋ˆ„๊ตฌ์—๊ฒŒ๋‚˜ ์—ด๋ ค ์žˆ๋Š” ํ‰๋“ฑํ•œ ๊ธฐ์ˆ ์ด ์•„๋‹™๋‹ˆ๋‹ค. AI ์จ๋ณด์…จ์œผ๋ฉด ์•Œ ํ…๋ฐ, ๋” ๋งŽ์€ ํ† ํฐ์„ ํƒœ์šธ ์ˆ˜ ์žˆ๋Š” ์‚ฌ๋žŒ์ด ์ด๊ธฐ๋Š” ๊ตฌ์กฐ์˜ˆ์š”. ๊ณ ์ž‘ ๋ฌด๋ฃŒ ๋ฒ„์ „์„ ์“ธ ์ˆ˜ ์žˆ๋Š” ์‚ฌ๋žŒ๊ณผ, ์ˆ˜์‹ญ๋งŒ ๋‹ฌ๋Ÿฌ์˜ ํ† ํฐ์„ ํƒœ์šธ ์—ฌ๋ ฅ์ด ์žˆ๋Š” ์‚ฌ๋žŒ์ด ๋‚ด๋Š” ๊ฒฐ๊ณผ๋ฌผ์ด ๋‹ค๋ฆ…๋‹ˆ๋‹ค.
1
859
์ด๋ž˜์„œ ์ž์ฒดํ˜ธ์ŠคํŒ…ํ•จ
This quoted post is unavailable.
11
WKBae ๐Ÿ•ฏ๏ธ retweeted
@ ๊ทธ๋‹ˆ๊นŒ ๋ณ€ํ˜ธ์‚ฌ๋ฅผ ์„ ์ž„ํ•˜์ž๋งˆ์ž ์ด๊ฑธ ์ž์ˆ˜ํ•˜๋Š” ๋ฐฉํ–ฅ์œผ๋กœ ์ด๋Œ์—ˆ๋‹ค๋Š” ๊ฑฐ์ง€? Ai๋Š” ๋ณ€ํ˜ธ์‚ฌ๋ฅผ ๋Œ€์ฒดํ• ์ˆ˜์—†๋‹คโ€ฆ
์„ธ๋ฌด๋ƒฅ์ด ai ์•ˆ๊ฒฝ ์ธ์ •ํ–ˆ๋„ค ์ž์ˆ˜ํ•œ๋Œ€
2
3,282
194
7,078
855,012
WKBae ๐Ÿ•ฏ๏ธ retweeted
there is smoke coming from my gpu, a new ceo has been chosen
208
7,146
476
66,433
839,762
WKBae ๐Ÿ•ฏ๏ธ retweeted
Meet Gemini 4 Hydrogen. It brings cutting-edge intelligence to everyone, with speed and efficiency for everyday coding and agentic work. Across 4 thinking levels, it stands on its own or teams up with Carbon and Argon โ€” 2.5X faster than 3.8 Flash, outpacing competing models in its class.
395
732
323
7,090
780,405
WKBae ๐Ÿ•ฏ๏ธ retweeted
introducing the Gemini Decisions API powered by Gemini Decision 1, our new multimodal decision model get fast, calibrated decisions on up to 1000 questions at once across text, images, audio, video, and PDFs try it today in AI Studio and via the Gemini API ai.studio
131
260
136
2,800
290,754
๋“œ๋””์–ด ๋‹ญ ์žก๋Š” ์นผ์ด ๋‚˜์˜ค๋Š”๊ฑด๊ฐ€
Introducing e-means, an algorithm beating k-means in 10x fewer epochs. With order of magnitude wall-clock speedups, e-means is released in FAISS and needs no hyperparameter tuning beyond k. It is robust to various scales and datasets. Still skeptical ? Just try e-means [1/10]๐Ÿงต
12