たくど

Senior Tech Consultant. ex-AWS | BigData, MLOps, AgentOps, Physical AI とか好き。立体音響技術, 指向性/無指向性スピーカーとかも好き。その他: 極真空手黒帯, ケルト酒場の期間限定営業

[たくど @d01tkum]

"2025 Japan AWS Top Engineer" の1人に選ばれました！🎉👍
https://t.co/RhcWTGfICA

#2025Japan_AWS_Top_Engineers
#AWSパートナー
#AWSSummit
#awssummit2025

[Ichigo @iiiichigo_chan]

Google just released a free 2-hour course on Agent Harness Engineering.

How to go from one prompt to a self-improving agent harness:

0% → 10:16 — build your first AI agent
25% → 41:05 — master prompt engineering
50% → 54:45 — turn agents into graphs
75% → 1:20:10 — run loops inside an agent harness
100% → 1:43:33 — build a harness that improves itself

Most people build one agent and stop there.

Google is teaching everything that comes next:

Prompt → Agents → Graphs → Loops → Harness

Single agents are the old workflow.

Self-improving harnesses are the next one.

This free 2-hour course is worth more than most paid agent engineering programs.

Bookmark it and watch today.

Then read the full guide below to build your first self-improving agent harness ↓

[Google Antigravity @antigravity]

Introducing /boost in Google Antigravity.

The Antigravity harness can tackle a wide range of tasks right out of the box, but /boost helps if you are tackling particularly complex tasks and are willing to spend some more tokens to push the system to reason deeply about the challenge at hand.

Here is how it works ⬇️

[Google Antigravity @antigravity]

Google Research and Google DeepMind researchers just used Teamwork in Antigravity to achieve breakthroughs in theoretical computer science, research mathematics, and systems engineering. Teamwork is a multi-agent framework where agents propose, stress-test, and build solutions autonomously over hours or days. It uses a lot of tokens and is overkill for everyday tasks, but if you're tackling frontier, long-horizon challenges - give it a try!

[Hanako @hanakoxbt]

Anthropic engineer:

"At Anthropic we don't write prompts anymore. We build loops and graphs."

in 32 minutes she shows how the Claude team builds systems that prompt themselves

Prompts → Agents → Loops → Graphs

a loop finishes one unit of work without you

a graph decides which units exist and turns every accepted one into a rule the next run inherits

same model, same tokens, and the only thing that changes is the shape you run it in

watch it today, then save the full graph engineering guide below

[Google Antigravity @antigravity]

Remote Control is here!

Take Antigravity with you anywhere. Access your active sessions from any modern supported browser or mobile device across iOS and Android. Rolling out to all users starting today, beginning with Ultra subscribers.

[Google Antigravity @antigravity]

Google Antigravity in Gemini Enterprise is available today for eligible Gemini Enterprise Standard and Plus customers.

[Quant Science @quantscience_]

🚨BREAKING: A new open-source multi-agent LLM trading framework in Python

It's called TradingAgents.

Here's what it does (and how to get it for FREE): 🧵

[Quant Science @quantscience_]

🚨BREAKING: A new Python library for algorithmic trading.

Introducing TensorTrade: An open-source Python framework for trading using Reinforcement Learning (AI)

[Google Antigravity @antigravity]

The latest Antigravity 2.0 update includes a new built-in Antigravity Guide skill, audio file rendering, and improved substring file search.

Check the changelog for all the updates https://t.co/zcWx92BPr6

[たくど @d01tkum]

@Keisuke69 お互いに埋もれ合ってる感が年々強まってる印象です😇

[たくど @d01tkum]

同時選出！
🏅2026 Japan AWS Top Engineers (AI/ML Data Engineer)
🏅2026 Japan All AWS Certifications Engineers

このペア選出は全国で23名と見受けられます。また、トップエンジニアは 2025年（Services）に続き、異なるカテゴリで2年連続の選出です！

#2026Japan_AWS_Top_Engineers
#AWSSummit

[Takuro SASAKI / 佐々木拓郎 @dkfj]

エンタープライズAWSアカウント設計

実物を初めて目にしたが、メッチャ分厚い。自立して立つくらいw
今、私がAWSのアカウント管理で必要と思っていることを、全て詰め込みました。

欲しいと思った方！！
入力方法はこちらです
https://t.co/7X5lm5bLAr

[tatsuki | AI駆動ラボ @tatsuki_nowave]

OpenAI 共同創業者Karpathyの CLAUDE.md が、GitHub トレンドで1位独走中。
中身はライブラリでもアプリでもなく、たった65行のテキストファイル。Karpathy のコーディング観察を圧縮した1ファイルが、累計10万スター超え。
そこに書かれた4つの原則について解説します。

[Cursor @cursor_ai]

With the Cursor SDK, you can build your own agents with Composer 2.5. It's now available in Python and TypeScript.

This long weekend, Composer usage is 90% off in the SDK. We're excited to see what you build!

[たくど @d01tkum]

Google Antigravity 愛用者です！
今回の変更アツいですね

[Yahoo!ニュース @YahooNewsTopics]

【毛利蘭の声優 山崎和佳奈さん死去】
https://t.co/MSnzdqMomL

[Google for Developers @googledevs]

Gemma 4: Now up to 3x Faster. ⚡

Same quality, way more speed. Our new MTP drafters allow Gemma 4 to predict multiple tokens at once, effectively tripling your output speed without compromising intelligence.

[OpenAI Developers @OpenAIDevs]

You can build interactive applications with gpt-realtime-1.5, so users can control app state more naturally with voice.

Hi Chappy 👋

[たくど @d01tkum]

連載第二回が公開されました。
AgentCore Observability のゼロコード計装の仕組みを、CDK for TypeScript での実機検証とともに深掘りしています。

いつも技術評論社さんには丁寧にご対応いただき感謝です。

#AWS #AmazonBedrock #AgentCore #OpenTelemetry #Observability #gihyo #技術評論社

[gihyo.jp @gihyojp]

AgentCoreを運用する技術 ── 本番品質を支える3つの視点「CDK for TypeScriptで検証するAgentCore Observabilityゼロコード計装の仕組み」 by @d01tkum 公開 https://t.co/ZIsMYyUzwF

[たくど @d01tkum]

技術評論社さんの https://t.co/XN9nk9ADit にて、AI エージェント本番運用の連載（全3回）の第一回が公開されました。

日本を代表する技術系出版社である技術評論社さんに記事を掲載する機会をいただき、大変光栄に思います。

[gihyo.jp @gihyojp]

「AWSネイティブサービスで実現するDataOps × LLMOps統合アーキテクチャ」 by @d01tkum
公開 https://t.co/LKHKULt4J7