Daegwon Nacyot Kim

한국어, English, 日本語. Claude Code Max, OpenAI Pro, M3 Ultra 512GB. Aspiring value investor. A member of @fortyfourbits. A software engineer at Karrot. 京釜高速道路.

[Daegwon Nacyot Kim @nacyotKim]

그러고 보니 이 반도체 대란에 앤스로픽은 한국에 안 오고 일본에 간다고? 너 차단… #아님 #틀려

[seb @hiiinternet]

https://t.co/Gpmb2JENiX

[Mikhail Parakhin @MParakhin]

Fable 5 is in the league of its own. Both in quality and price - already on Toloka Arena:

[Google DeepMind @GoogleDeepMind]

We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video.

It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵

[Figma @figma]

Imagine a world where you could copy/paste websites into editable Figma layers (jk you don’t have to imagine you can do this now with our Chrome extension)

[Daegwon Nacyot Kim @nacyotKim]

@Multi_Serio_Ai 저건 API 비용으로 계산했을 때라서요... 😅

[Daegwon Nacyot Kim @nacyotKim]

20개 정도 이슈 엮여있는 클라이언트 퍼포먼스/네트워크 메타 이슈를 fable에 던져봄... 자러 갑니다.

[Daegwon Nacyot Kim @nacyotKim]

이슈는 잘 해결함. 적어도 표면적 문제는 은 보임. 모델/비용 봐서는 fable도 많이 돌긴 했는데, $2,000 정도 나옴.

[Daegwon Nacyot Kim @nacyotKim]

아침에 일어나니 전부 Opus로 바껴있는 것 같은데... :think:

[Hugues 👨🏼‍💻 @huguesdelamure]

Aujourd'hui, j'ai réalisé le rêve de tout geek qui voyage beaucoup : Remplacer l'intégralité de mon setup réseau mobile par un seul appareil qui fait tout 🥰

Le Avant/Après parle pour lui même 😂

[朱雀 | SUZACQUE @Suzacque]

Fable 5を2日間使った感想
・IQは最強でGPT-5.5 pro の比ではない
・EQは高いのにKYで、真実を追求する
・ビジネスなど人間世界の理解が半端ない
・現実世界に適用できる提案力も半端ない
・なのに回答スピードは比較的速い
・主力LLMの座はGPT-5.5 proから交代
・そのためにMaxプランにアップグレード済
・常時稼働なしならMax5倍でトークン量は十分
・Codex派だったがClaude Codeに乗り換え済
・GPT-5.6 proでも超えられない可能性が高い
・結論：このモデル、ヤバすぎ。非エンジニアもみんな使うべき

[OpenAI @OpenAI]

We heard you wanted to use Codex rate limit resets on your own time.

Starting today, we’re rolling out the ability to save rate limit resets to use later.

We’re starting Go, Plus, Pro, and Business users with one free reset:

[Kyle Hessling @KyleHessling1]

Qwopus 3.6 27b-Coder is now live!

Scores a 67% on a full run of SWE bench verified with thinking completely disabled! Q5_K_M

This model is lightning fast for dense class! With a natively finetuned MTP head, it achieves 100 tps on a single 5090! The biggest upgrade here, though, is its stability in programming and tool calling within @NousResearch Hermes agent, with thinking off!

Wall time is crazy fast this way, which makes Hermes feel "native" and snappy, like they were meant for each other. The freedom of running without thinking at all makes you part of the thinking process, and you never get caught waiting 15 minutes for it to finish a thought string, like with the base models.

Thinking on and temp high, .9-1 seems to produce really incredible design and svg results. I reran the Boat survival prompt through a few turns, thinking on, and it seemed to render more fancy models in HTML canvas, but it was much more of a start-a-prompt and wait experience vs the snappy and active iteration with it disabled. It may be worth turning it off and on throughout the build process if you want to get really creative with design.

Really looking forward to seeing how this one performs for y'all! Please post comments with your opinions and use cases below! As always with our fine-tunes, mess with the temperature setting, and run them much hotter than the base!

Please check out the Boat Survival game I posted yesterday, made in 12 turns using Hermes and this model, with thinking off. Link below!

Full swe bench repo-specific breakdown also posted in the comments for those interested!

Happy building, everyone! We're looking forward to your thoughts! Quants uploading now!

https://t.co/kxJE3C39ZZ

[Daegwon Nacyot Kim @nacyotKim]

클로드 말하는 게 고도로 추상화된 GPT(Coedx) 같아지는데, 한국어로 설명해주세요. 😂

[Daegwon Nacyot Kim @nacyotKim]

마크다운 렌더링 70점, 아내가 클로드한테 이상한(?) 걸 물어보고 있음...
https://t.co/OgXK24ZOnr

[Daegwon Nacyot Kim @nacyotKim]

GPT, 마크다운 렌더링도 해주나요?

[Daegwon Nacyot Kim @nacyotKim]

GPT, 마크다운 렌더링도 해주나요?

[Justin Schroeder @jpschroeder]

In 👏 no 👏 universe 👏 is Opus 4.8 low better than GPT-5.5 xhigh

[0xSero @0xSero]

Holy moly man, Mythos speeds up Nex-N2-Pro decode speeds by 70% & reduce ttft by 29%

[Daegwon Nacyot Kim @nacyotKim]

프롬프트 다 쳐놨는데... UI 작업이 있어서 차마 Codex에게 못 보내겠다...

[Mitchell Hashimoto @mitchellh]

Fable is a good model. As with all new models, it is simultaneously excellent and entirely unremarkable (relative to other models). It is slow and expensive, and the "loops are all you need" discourse they are pushing is obvious in the context of someone using Fable-class models

What I've found so far is that for broad scope design (code architecture) tasks, Fable is unremarkable. Or, not better enough to justify its cost and speed.

But in highly targeted goal-oriented loops, it is another beast entirely. It is very slow but produces very good results.

I let it churn on optimizing a SwiftUI-layout resolver in Go I wrote and it was able to bring it down to an order of magnitude I could not reach myself (micro => nanosecond scale). But it took 2 hours and $40 to do it and I had to claw back some changes it overfit to Apple Silicon. Still, very worth it.

In comparison, for "implement this feature/change" iterative work, I ran head-to-head Fable vs GPT5.5 vs. GLM-5.1. They all produced equally acceptable final results, but GPT5/GLM did it in a couple minutes and Fable was churning away for 40 minutes. And GLM cost me less than a dollar, GPT5.5 ~$1.50, and Fable cost $9.

You can see that in this context, interactively working with an agent is nonsense. Its too slow. You need to write loops to keep the agent working and you probably want to highly parallelize the work being done. As with all things, I think a balance makes sense...

My sense is that I'd reserve Fable for targeted, surgical analysis and work. Not for daily driving everyday tasks.

I'm going to keep spending a shitload of money (relatively) and maining Fable for the rest of the week to continue to judge, will report if anything changes. I'll continue to head-to-head as well.