開発スタッフがアプリ関連の最新技術やニュースをご紹介します。

GitHub has released a private beta version of the GitHub Copilot code browsing feature to give developers this option. When code referencing is enabled, Copilot will not automatically block the matching code it generates, but instead will show it to the developer in the sidebar and let the developer decide what to do with it. Over time, this feature will also be implemented in the Copilot chat.

GitHub previewed this feature last November, but it has clearly taken a long time to release.

GitHub CEO Thomas Dohmke told that Microsoft, GitHub, and most of his Copilot enterprise customers used the original locking feature, which he also said was a bit of a dull tool. said. “It gives you little control to decide for yourself whether you actually want to take that code and attribute it back to an open source license. It doesn’t actually let you discover that there might be a library that you could use instead of synthesizing code,” he told me. “It prevents you from exploring these libraries and submitting pull requests. You might be reproducing everything that already exists in some open source repo.”

Also, the code browsing feature tends to trigger more often when Copilot doesn’t have much context to operate. If Copilot can see a lot of context from the existing code you’re working with, it’s unlikely to generate hints that match public code. However, if you’re just starting out, your chances of generating matching code are greatly increased. You can read more detail about this topic from Github blog.

Yuuma

Tweet

text-generation-webui というアプリケーションを使用することで
一般家庭用のPCでもグラフィックカードを使って
Chat GPTのような大規模言語AIを比較的簡単に動かせるようです。

モデルのダウンロードやAIのキャラクラー性の設定も簡単にできるようです。

使用するモデルにもよるようですが、vramは16GBほど必要なようです。

グラフィックカードは最新世代のnvidia製のvramが12GBの物と、
1世代前のamd製のvramが16GBの物を所有しているのですが、
Windowsではamd製のグラフィックボードはサポートしていないようなので、
少ないvramでも動作するモデルを見つけられたら
Windows上で試してみたいなと思っています。

水曜担当：Tanaka

Tweet

Netflix hires a product manager to strengthen the internal use of artificial intelligence. In the first joblist discovered by the intercept, Netflix will manage to a successful applicant of $ 300,000 to $ 900,000.

In their tasks, Netflix develops a “strategic vision” for using AI through machine learning platforms, evaluates the use, execute a program for “user education” in the platform, and maintains new technology. Includes to do.

The important thing is that it is not clear whether this role is directly involved in content creation or influence. Netflix has already selected a thumbnail art that uses artificial intelligence to customize user recommendations and appeal to a specific preference of individuals. The company was parody with Netflix’s own black mirror. The streaming site will also use AI to analyze which content is successful and notify future production.

However, Netflix has previously demonstrated that it does not oppose the idea of using AI to generate content. The company was scrutinized in February after the Japanese division using AI to generate the background art of Anime Short THE DOG and THE BOY.

All of these are all invested in AI, are ready to invest a large amount of investment, and are willing to invest.

Yuuma

Tweet

今回はOpenAI APIをWebアプリケーションに組み込んで活用する方法を説明します。
PythonのWebアプリケーションフレームワークといえばDjangoが有名ですが、
今回はテスト用途なので、軽量でシンプルなフレームワークである
Flaskを試してみたいと思います。

Tweet

Unitreeという中国のロボットメーカーがGPTを搭載した
犬型ロボットUnitree Go2の販売を開始しているようです。

Tweet