SeaOtter(Kentaro Mori)

Graduate @jaistbot ex @AoyamaGakuinU / DevSecOps Oriented / AI friendly ☺️ / Tweets are my own 🦦

[SeaOtter(Kentaro Mori) @moruku36]

This is a summary of my master's thesis, and I welcome any comments or feedback on this content🙌
OSS-based environmental investigations to enable vulnerability mitigation in DevSecOps schemes https://t.co/s9j48qksrb

[SeaOtter(Kentaro Mori) @moruku36]

🎵
James Blake, Travis Scott, Ludwig Göransson - When I'm Home (from The Od... https://t.co/JTeCN6qjDD @YouTubeより

[SeaOtter(Kentaro Mori) @moruku36]

👀
https://t.co/prh0ikNeVD

[SeaOtter(Kentaro Mori) @moruku36]

👀
https://t.co/LGnjcW372R

[SeaOtter(Kentaro Mori) @moruku36]

👀
On the waitlist
https://t.co/pV3jMst8jC

[みのるん @minorun365]

資料です！ #みのるんのゲリラ勉強会

今話題のAI「Jev」って何？ 宇宙最速で学ぶ会
https://t.co/8uCVEpIArM

[SeaOtter(Kentaro Mori) @moruku36]

AI attacks are shifting from assisted to autonomous.

https://t.co/D7b5HucaPC

[SeaOtter(Kentaro Mori) @moruku36]

KUMAMON !
https://t.co/IBtbmfzFGZ

[SeaOtter(Kentaro Mori) @moruku36]

🔐🧮

https://t.co/XxqZSmbns6

[SeaOtter(Kentaro Mori) @moruku36]

people matter more than AI
https://t.co/4uTM0KZfbm

[SeaOtter(Kentaro Mori) @moruku36]

🛴

https://t.co/lt92N2oTNm

[SeaOtter(Kentaro Mori) @moruku36]

My AI workflow https://t.co/8cm3ci20MA

[SeaOtter(Kentaro Mori) @moruku36]

Combine three cloud PoCs into a single verification

https://t.co/KusGNjgpsM

[SeaOtter(Kentaro Mori) @moruku36]

🤓🤖

https://t.co/jeCfR0BtgT

[SeaOtter(Kentaro Mori) @moruku36]

Knowledge distillation was new to me, so I ran it on a local LLM.

https://t.co/Fh9ZhcGZd0

[SeaOtter(Kentaro Mori) @moruku36]

vibe hacking 😎

[Anthropic @AnthropicAI]

We're publishing our most detailed threat intelligence report to date.

It covers how people tried to misuse Claude—for cyberattacks, influence operations, surveillance, biology, and building weapons—and how we found and stopped them.

We disrupted every operation in the report, and used the lessons from them to strengthen our safeguards. Where appropriate, we also shared what we found with authorities and other AI companies.

These cases are not typical: we’re highlighting some of the most sophisticated misuse we’ve seen. But they’re especially important to discuss, because they show us where AI misuse is headed, where our safeguards work, and where they need to improve.

We’re publishing this report so others can spot the same activity on their own platforms, and so we can give the public a clearer view of how emerging threats develop.

Read the report: https://t.co/0EJUnYEgfz

[SeaOtter(Kentaro Mori) @moruku36]

👀 https://t.co/Hi9QMNZCH6

[SeaOtter(Kentaro Mori) @moruku36]

Let's GOOOO !

[SeaOtter(Kentaro Mori) @moruku36]

🤤🤤🤤

[OpenAI @OpenAI]

GPT-6 Astra is now available to all Pro, Enterprise, and Business Premium users in ChatGPT Work and Codex. It's also live in the API.

It might take a few days to roll out to our Plus and Business users. Thank you for your patience.

[SeaOtter(Kentaro Mori) @moruku36]

https://t.co/iTeKpjH71y

[SeaOtter(Kentaro Mori) @moruku36]

😳
OpenAI warns of rogue AI agents in breach https://t.co/6pHpuMAh6G.