組込おじさん

自動車部品(ASIL-D)の元組込SWエンジニア。アセンブラ・C言語が好物です。
今はなぜかクラウドのお仕事をやっています。

[組込おじさん @embcpp]

確かにこれは一理あるんだよなー。

[Kun Chen @kunchenguid]

sigh.. i have to say something here

imagine you hired a new developer to your company, and on day one he did some terrible work, over-engineering your codebase, speaking jargons all day without context, making all kinds of “genuine mistakes”, lost trust with everyone around him

and then he goes on and tell you - in order for me to do a better job, you need to delete your entire company’s culture and workflow, and have everyone bend over to do things his way, only then can he do reasonable work

oh - and no one tells him how to do his job, NO ONE. he’s always the smartest one in the room and despite doing a terrible job on day one, despite the only results on his resume were vibe coded demos of games that already existed, he demands that you give him a big charter and let him go dark with no communication, taking no feedback

would you have hired a teammate like this?

when humans feel frustrated after using a model, let’s figure out how to RL the model better so they become a better teammate

don’t let a bad model RL _you_

[Kun Chen @kunchenguid]

sigh.. i have to say something here

imagine you hired a new developer to your company, and on day one he did some terrible work, over-engineering your codebase, speaking jargons all day without context, making all kinds of “genuine mistakes”, lost trust with everyone around him

and then he goes on and tell you - in order for me to do a better job, you need to delete your entire company’s culture and workflow, and have everyone bend over to do things his way, only then can he do reasonable work

oh - and no one tells him how to do his job, NO ONE. he��s always the smartest one in the room and despite doing a terrible job on day one, despite the only results on his resume were vibe coded demos of games that already existed, he demands that you give him a big charter and let him go dark with no communication, taking no feedback

would you have hired a teammate like this?

when humans feel frustrated after using a model, let’s figure out how to RL the model better so they become a better teammate

don’t let a bad model RL _you_

[組込おじさん @embcpp]

手動承認で実行してみた感じ、そこまで消費量が減るわけで��ないみたいだから、消費量への影響は軽微なのだろうか。

[組込おじさん @embcpp]

Codex の Usage の比率ってどうなっているんだろうな、と思って見てみたら、なんだこれ、、、、
主として使っているLunaの割合はほとんどなくて、ほぼ codex-auto-review だ。これはたしか自動承認の昨日だったかな・・・

[組込おじさん @embcpp]

あくまで Turn(実行回数?) ということなので消費量とは関係ないらしい。では消費量は如何程なのだろうか。

[組込おじさん @embcpp]

試しに承認を手動にしてやってみるかー。それでもだめそうなら別のエージェントツールへ繋げて使ってみよう

[組込おじさん @embcpp]

codex-auto-review のコストが下がった状態でこのザマなのか・・・？うーん

[OpenAI @OpenAI]

We’re also upgrading Auto-review in the ChatGPT app and Codex CLI from GPT-5.4 to GPT-5.6 Luna.

Combined with Luna’s new price, we expect Auto-review to cost about 10x less, making your agentic workflows more cost-efficient.

[OpenAI @OpenAI]

We’re also upgrading Auto-review in the ChatGPT app and Codex CLI from GPT-5.4 to GPT-5.6 Luna.

Combined with Luna’s new price, we expect Auto-review to cost about 10x less, making your agentic workflows more cost-efficient.

[Chris Banes @chrisbanes]

Been seeing my @ChatGPT Codex quota reduce way too fast lately. After looking at analytics, ~95% of my turns are for `codex-auto-review` (aka Approve for Me)

Just got Codex to look at my transcripts and it's used 1.74B tokens across 23.5k tool reviews over the past 6 weeks 🫨

[組込おじさん @embcpp]

Kimi K3 がGithub Copilotに！

[GitHub @github]

📣 @Kimi_Moonshot's Kimi K3, an open-weight model, is now generally available and rolling out in GitHub Copilot.

The model shows frontier-level abilities on agentic coding with highly cost-effective pricing. It is hosted by @FireworksAI_HQ. Learn more. 👇
https://t.co/lI3GgiZJ5M

[GitHub @github]

📣 @Kimi_Moonshot's Kimi K3, an open-weight model, is now generally available and rolling out in GitHub Copilot.

The model shows frontier-level abilities on agentic coding with highly cost-effective pricing. It is hosted by @FireworksAI_HQ. Learn more. 👇
https://t.co/lI3GgiZJ5M

[OpenAI Developers @OpenAIDevs]

Build a plugin once and use it across compatible agent clients.

Introducing Agent Plugins, an open standard developed with @awsdevelopers, @cursor_ai, @github, @code, and @vercel that packages Agent Skills and supports MCP server configurations in a shared format.

[組込おじさん @embcpp]

Claude Desktop、今日のアップデート後から新規のモデル選択が中(Medium)から超高(xHigh)へ勝手に変わるときがあるんだけど、なんだろうこれ。どこかの設定に影響されて���るのかな。

[Masao Kanamori @masaosaan]

AI-DLC v2 の説明記事が出ましたよー

AI-DLC Workflow V1からV2へ：人間のボトルネックを解消する設計の進化 by Satsuki https://t.co/UatCReVzD8

[Kazunori Sato @kazunori_279]

確かによくAIに「これはあなたにしかできない作業です」って頼まれて、半田付けとかテスターで確認とかUSB抜き差しと永遠にやらされてる。フィジカルAIってそういうこと？（違う）

[NVIDIA DRIVE @NVIDIADRIVE]

Introducing Alpamayo 2 Super: the frontier open reasoning VLA for autonomous vehicles and robotaxis.

34B parameters. Full-surround awareness. Available for commercial use under under OpenMDW-1.1.

Download now on @huggingface → https://t.co/pyyW2NP4BW

[組込おじさん @embcpp]

Claude App (Windows) がめっちゃ��くなった気がする。アップデートの影響かな？

[erukiti @erukiti]

定期的に出てくるAIによるエンジニア不要論について、記事を書いてみました

プロダクトを作ったことがある人なら、Fable5があってすら、素人が「顧客が存在するプロダクト」を作れるとは到底思えないよね、���いうのを記事としてまとめたものです https://t.co/NkGfRAxYNG