
openjny
4.3K posts

openjny
@OpenJNY
Cloud Solution Architect @Microsoft, アンダーパーで回りたい
Tokyo Katılım Mayıs 2016
552 Takip Edilen719 Takipçiler

Azure SRE エージェントは ISUCON で戦えるか?パフォーマンスチューニングに挑戦してみた|Junya Yamaguchi zenn.dev/microsoft/arti… #zenn
日本語
openjny retweetledi

週末の Global Azure 2026 Tokyo 向け発表資料です。ボリューム多めでダジャレを放つ余裕がなくなりそうなので事前放流しておきます #jazug / Azure Lifecycle with Copilot CLI speakerdeck.com/torumakabe/azu…
#speakerdeck
日本語
openjny retweetledi

We replicated Mythos findings in opencode using public models, not Anthropic's private stack.
The moat is moving from model access to validation: finding vulnerability signal is getting cheaper; turning it into trusted security
A better way to read Anthropic's Mythos release is not "one lab has a magical model."
It is: the economics of vulnerability discovery are changing.
We took the patched public Mythos examples and tried to reproduce them with GPT-5.4 and Claude Opus 4.6 in an open-source harness. Every run stayed below $30 per file.
AI models are already good enough to narrow the search space, surface real leads, and sometimes recover the full root cause in battle-tested code.
The takeaway: model access is not the moat anymore. Validation is. Finding vulnerability signal is getting cheaper; turning it into trusted security work is still hard.
Co-authors: @KlaKlo_, Amadeusz, Marek, Kuba, Mikolaj

Dawid Moczadło@kannthu1
UPDATE: We were able to replicate the Mythos findings using existing models (GPT5.4) Writeup coming early next week, no BS prompts, it's real reproduction
English
openjny retweetledi

claude codeのコンテキストの消費が激しいため以下を導入
github.com/rtk-ai/rtk
どうやら git status や ls などのコマンド出力がそのままコンテキストに流れる前に、事前にrtkが圧縮・フィルタしてくれるっぽい
トークン消費が最大90%削減されるらしいが果たして
日本語

今後も、最新モデルはセキュリティサービスのバックエンドにしか使わず、一般提供は旧世代モデルのみ、って形になっていくのかな。そうなってくれたほうが様々なサービスを使う一般人としてはありがたいけど
Anthropic@AnthropicAI
Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. anthropic.com/glasswing
日本語
openjny retweetledi

Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software.
It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans.
anthropic.com/glasswing
English
openjny retweetledi
openjny retweetledi











