めんふぃむ

Robot vision engineer. Kaggle Expert. Signate Expert. atcoder Cyan.

[山田ハヤオ🧊 @Hayao0819]

最近自分の中でDocker嫌いが加速しているので代替技術を調査しているのだが、NVIDIAが非常に面白そうなものを出している。思想はかなり好き。
https://t.co/Uq0k1WxydC

[AI駆動塾 @L_go_mrk]

ClaudeCodeの無駄なトークン消費を「怠惰なシニアエンジニア」が80％抑えてくれる「Ponytail」が話題。

・生成コード量80〜94%減
・コスト47〜77%減
・タスク速度は3〜6倍に

コードが書かれる前に「これ標準ライブラリで足りない?」「本当に書く意味ある？」というのも確認してくれる親切シゴデキ設計。

https://t.co/W5fwm4rcbY

[爱丽丝呀！ @BTCqzy1]

Codex 5.6 这个 GitHub 插件一定要装，能让你省下90%的token！

90% 的人都把 Codex 用反了。
一上来就让它：
帮我写一个 App。

分享一条我在用的绝佳省token技巧，先给 Codex 连接 GitHub 插件，然后输入提示词：

我要开发一个 XXX。暂时不要创建文件，也不要输出代码。先在 GitHub 调研同类开源项目，筛选出最有参考价值的方案。分析它们解决了什么问题、采用什么架构、依赖哪些技术、目前是否活跃，以及有哪些设计值得复用或避开。最后结合我的需求，给出技术选型、系统架构、MVP 范围和开发顺序。得到我的确认后，再进入实现阶段。

这样 Codex 会先做三件事：

1️⃣ 找到经过真实项目验证的方案
2️⃣ 研究别人已经踩过的坑
3️⃣ 根据你的需求做出技术取舍

等方向确定后，再让它开始写代码。

[Vox @Voxyz_ai]

Codex tip: tell Sol to configure 𝗟𝘂𝗻𝗮 𝗠𝗮𝘅 𝗮𝘀 𝗮 𝘀𝘂𝗯𝗮𝗴𝗲𝗻𝘁.

𝗽𝗿𝗼𝗺𝗽𝘁:

create a custom agent named luna_worker at ~/.codex/agents/luna-worker.toml.

use these settings:

model = "gpt-5.6-luna"
model_reasoning_effort = "max"

give it a description and instructions for bounded delegated work. preserve the rest of my config. validate it against my installed Codex version, show me the diff, then use luna_worker for subagent tasks.

[Google Earth @googleearth]

Today we’re bringing AI image generation with Nano Banana to Google Earth, letting you virtually reimagine anywhere in the real world. 🍌 https://t.co/zsgvAnbYrl

For the first time, you can generate custom images using Google Earth’s satellite, aerial, and 3D imagery. 🌎

[Tibo @thsottiaux]

To celebrate a week of efficiency and let you run 100'000 Luna threads this weekend... that's right... wait for it... I have reset usage limits for Codex and ChatGPT Work.

Enjoy.

[むし @n_en_u]

同志社、刑事責任は難しそうだし、やっぱりここは一つ学校法人の認可取り消しあたりを落とし所にしてはどうか。罪のない大学生ら(事件に対して何のアクションも起こしてない構成員に罪がない？)はかわいそうだが、大きな大学が突然消滅するところ見てみたい。

[Yuichi Uemura @u1]

お名前.com がGMOグループ全体に与えてるネガティブ効果、凄まじいと思う

[めんふぃむ @menphim]

5時間制限復活してしまうのか…

[Tibo @thsottiaux]

Hello people of Sol! I've reset usage limits for all ChatGPT Work and Codex users. Together with that, a quick update on GPT-5.6 Sol usage limits.

Over the past few weeks, many of you have told us that Sol was using your Codex limits faster than expected. To be clear, we have not reduced usage on any subscription plans.

We’ve been digging into what was happening and have landed several improvements. As a result, we expect your usage to last around 18% longer during typical use of Sol. Some of you should already see significantly larger improvements from today. Tomorrow, we’ll also restore the five-hour limit that we temporarily paused while investigating.

Here’s what we found:
- GPT-5.6 Sol is much more willing to work for longer, make additional tool calls, and coordinate complex workflows across tools and subagents. That makes it better at solving hard problems, but some tasks were using far more than we intended.
- Sol also works harder at the same reasoning effort than previous models. High on Sol can use more tokens than High did on GPT-5.5.
- Programmatic tool calling, also referred to as code mode, gives Sol much more flexibility to run tool calls in parallel or continue working while waiting. But it also led to more responses per turn, more cached input tokens, and higher usage than expected.
- This was particularly noticeable when Sol was waiting for tool calls to finish or running many web searches. We’ve improved how we handle both cases and are continuing to make code mode more efficient.
- The impact was also very uneven. The median user actually found Sol quite token efficient, while some power users working on harder tasks saw their usage drain much faster. We were very focused on average and median usage before launch and missed some cases where the long tail could use significantly more usage.

Sol is a significant step forward in what Codex can do, but capability and efficiency do not always improve at the same pace, and some issues only become clear once people are using the model at real-world scale. We should have recognized this sooner and been more upfront about it.

You keep pushing the frontier and we’ll keep improving efficiency and sharing updates as we go.

[Tibo @thsottiaux]

More opensource goodness. We have just released a CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in your code. Scan repositories, review changes, track findings over time, and run security checks in CI.

https://t.co/nkfTbw8p7b

[XAIFURA • 個人開発 @xaifura]

@fuuba_ai https://t.co/n2NMXl9jMH
https://t.co/zxMXGhpaHZ

クロスチェックを！！！

[Holy_Moly @Holy_Molygr1]

People who criticized GR last time for “not respecting the safety of other drivers” have suddenly changed their narrative again? It really just seems like you simply don’t like GR.

It’s pretty obvious that Ant lifted off the throttle too late, and he was so close to Vstp that you could see it with the naked eye. If Ant had spun, there was a real possibility that he could have hit Vstp.

GR, on the other hand, lifted around 100 meters earlier, and he was much farther away from the incident—so far that he couldn’t even see the crashed car.

Please stop pretending these are the same situation. They aren’t.

[Yuichi Uemura @u1]

なにこれ､こんな糞system promptが入ったのかよ

これがOpus5の糞みたいな返答誘発してそう

[Pankaj Kumar @pankajkumar_dev]

Fable 5.1 Leaks

- Fable 5.1 is in preparation, with a target launch in August.
- Pricing is to be remain the same as Fable 5.
- If the current timeline holds, it could launch ahead of GPT-6 to compete directly with it.

[himako @himkt]

爆速トークナイザ gigatoken、マジで爆速っぽくてすごいけど何するとこんな速度変わるの
https://t.co/hLcjQ4lvN8

[Jun Watanabe＠rela @rela1470]

@FruitRiin えーんえんえん😭😭プライベート リポジトリを削除すると、リポジトリのすべてのフォークが削除されます。 >> リポジトリの削除 - GitHubドキュメント https://t.co/S1qSC56dRN

[Qwen @Alibaba_Qwen]

Qwen3.8 is launching and going open-weight soon!🌐

With a massive 2.4T parameters, this model is continuously evolving. We believe it’s one of the most powerful model available today, compatible to leading frontier AI models , second only to Fable 5.

You don't have to wait to test it. Just now, the Qwen3.8-Max-Preview made its debut on Alibaba’s Token Plan, Qoder, and QoderWork. Be among the very first to try it out.

Can't wait to hear what you build. Stay tuned! 🚀 

Token Plan
international：https://t.co/YRvcGdB9Bv
China：https://t.co/PKMUNwUuRp

[あるふ @alfredplpl]

.@kantocv 本日の発表資料です。ご査収ください。

生成AIの基盤モデルとしてのCVPR 2026とJust image Transformers | あるふ #cvsaisentan
https://t.co/vDseC3SCsT

[piqcy @icoxfog417]

これはあり得ない投稿なので社内でエスカレーションします。甚大な請求額に対し、アカウント情報の漏洩により第三者に利用された結果ではと心配された方も、また予算アラートを設定していたために意図しない対応をしなければならなかった方もいると認識してます。このような投稿はセキュリティが最優先のAWSとしてポリシーに沿わない発信です。不快な思いされた方に大変申し訳ないです。