投稿時間:2023-06-16 17:17:32 RSSフィード2023-06-16 17:00 分まとめ(22件)

カテゴリー等	サイト名等	記事タイトル・トレンドワード等	リンクURL	頻出ワード・要約等/検索ボリューム	登録日
IT	ITmedia 総合記事一覧	[ITmedia ビジネスオンライン] 日産、強まる「内田色」　ナンバーツー退社は企業連合の変化の象徴か	https://www.itmedia.co.jp/business/articles/2306/16/news158.html	itmedia	2023-06-16 16:35:00
IT	ITmedia 総合記事一覧	[ITmedia Mobile] 050IP電話サービス契約時の本人確認を義務化　早ければ2023年夏頃までに制度改正へ	https://www.itmedia.co.jp/mobile/articles/2306/16/news157.html	itmediamobileip	2023-06-16 16:35:00
IT	ITmedia 総合記事一覧	[ITmedia PC USER] Dreame、ハイエンド仕様のロボット掃除機「DreameBot L10s Ultra」など6製品を投入	https://www.itmedia.co.jp/pcuser/articles/2306/16/news155.html	dreamebotlsultra	2023-06-16 16:33:00
IT	ITmedia 総合記事一覧	[ITmedia News] 「ハリポタツアー東京」きょう開業　Twitterで「いいね」すると魔法がかかる	https://www.itmedia.co.jp/news/articles/2306/16/news151.html	itmedia	2023-06-16 16:14:00
IT	ITmedia 総合記事一覧	[ITmedia ビジネスオンライン] 「私立大薬学部に強い学校」ランク　1位は？	https://www.itmedia.co.jp/business/articles/2306/16/news150.html	itmedia	2023-06-16 16:13:00
IT	情報システムリーダーのためのIT情報専門サイト IT Leaders	アステリア、IoTデータのエッジ処理にクラウドでのデータ集約・分析を組み合わせた「新Gravio」 | IT Leaders	https://it.impress.co.jp/articles/-/24968	アステリア、IoTデータのエッジ処理にクラウドでのデータ集約・分析を組み合わせた「新Gravio」ITLeadersアステリアは年月日、IoTエッジコンピューティング用ミドルウェア「Gravio」をクラウドコンピューティングへと拡張した「新Gravio」を発表した。	2023-06-16 16:10:00
js	JavaScriptタグが付けられた新着投稿 - Qiita	PhpStormでGitHub Copilotプラグインを使ってみた	https://qiita.com/r_ishimori/items/bfdc4d2c77ac673100dd	githubcopilot	2023-06-16 16:17:43
AWS	AWSタグが付けられた新着投稿 - Qiita	(無料枠で可能)AWS上にADサーバを構成してAWSアカウントにSSOする	https://qiita.com/bonjiko/items/099fc63caf3394474132	activedirecroty	2023-06-16 16:06:23
Docker	dockerタグが付けられた新着投稿 - Qiita	docker compose upで発生した「error response from daemon: network 」の解決方法	https://qiita.com/nagataichiko/items/6c9dd3eb801e7682b9f9	errorresponsefrom	2023-06-16 16:20:44
Ruby	Railsタグが付けられた新着投稿 - Qiita	【2023年度】S3にあるhlsコンテンツをセキュアに自分のドメインで再生する方法	https://qiita.com/1ulce/items/8956d9e89d2f41f34c14	参考文献	2023-06-16 16:56:22
技術ブログ	Developers.IO	【7/12（水）東京】クラスメソッドの会社説明会を開催します	https://dev.classmethod.jp/news/jobfair-230712/	会社説明会	2023-06-16 07:06:08
海外TECH	DEV Community	Disrupting the AI Scene with Open Source and Open Innovation	https://dev.to/polterguy/disrupting-the-ai-scene-with-open-source-and-open-innovation-9hl	Disrupting the AI Scene with Open Source and Open InnovationWhen I discovered OpenAI the rd of December I became obsessed I hadn t had this much fun coding since I started years ago After playing with fine tuning for a month and miserably failing I found a YouTube video by Dave Shapiro that explained how to create a Q amp A chatbot using OpenAI s embeddings API Dave has since removed the video but it explains how to use OpenAI s embeddings API and combine it with their chat completion API to create a Q amp A chatbot that knows everything about the problem domain Tage s reaction best sums up my findings as he told me one day OMG dad this time you ve really done it I woke up shaking in the middle of the night because of enthusiasm and I couldn t even sleep so I hade to take a walk for kilometres outside in the middle of the night just to calm down How a Q amp A chatbot worksTo understand a Q amp A chatbot based upon ChatGPT you can go to ChatGPT and find any article and copy and paste it into the prompt as follows Answer the following QUESTION given the specificed CONTEXT QUESTION What is the meaning of life CONTEXT content of some article explaining the meaning of life What ChatGPT will do is to answer any question you might have while using the article s content as its single source of truth What we do and everybody else that delivers ChatGPT chatbots is to create a database of context data that might be created by uploading documents and or scraping websites When the user asks a question we ll use OpenAI s embeddings API to create a vector of the question This vector is then used to perform a similarity search through our database calculating dot products which becomes the distance between the question and the snippets from our context database Then we order each result from our context database by this distance and takes the first to context snippets and sends to OpenAI as the question s context Before you ask yes The whole process is simply automated prompt engineering OpenAI s embeddings API again is incredibly smart at finding similarities between questions and context data allowing it to find the relevant data given any question you ve got related context for in your database The problem with AI based semantic searchThe above dot product is the problem To understand why realise you have to perform a table scan through your entire database extract the embedding vector for each record and calculate the dot product for each result originating from this process This is a CPU intensive job and for a context database with with records this would take to seconds in our Kubernetes cluster for our systems This is the reason why we ve not been able to deliver chatbots with more than snippets previously However today we fixed this problem and during the weekend we ll hopefully be able to deploy a solution that at least in theory allows for snippets possibly even more while returning context data in seconds instead of minutes Ever since I realised the above process was sub optimal I ve been periodically doing a Google search for sqlite vector plugin To understand the importance of this realise that since OpenAI went viral at least half a dozen startups have been created with the intention to create a vector based database I know about at least one such database that got million dollars in VC funds earlier this year To explain why realise the truth of the following statement Who ever solves the vector database problem is destined to control the AI space and hence the world What s at stakeI personally believe that AI the way it s progressed the last year is probably the most important thing to have occurred on Earth for the last million years seriously When people are comparing AI to the internet heavier than ear flight the computer for that matter I tend to laugh and reply with AI is the most significant event to have happened since we crawled down from the trees For million years we ve been the smartest specie on Earth that era ends in So basically if somebody can control innovation in this space they basically own the future of mankind The amount of power a company having such control could yield would inevitably make all previous power constructs become the equivalent of a child s playground in comparison We cannot let this happen simply because if somebody controls the AI space that person would be able to yield God like powers over the rest of us Giving the people control is CRUCIAL for the above reasons The solutionEven Google have publicly admitted they can t keep up with open source AI innovation This of course is because of open source projects such as Hugging Face However there was always one tiny little piece missing vector based database systems A superior vector based database can easily index millions and even billions of database records allowing even year old kids to build their own Google As I searched for sqlite vector plugin I didn t find any results before a couple of weeks ago Two weeks ago I found Alex SQLite VSS plugin for SQLite The library was an amazing piece of engineering from an idea perspective However as I started playing around with it I realised it was ipso facto like Titanic Beautiful and amazing but destined to leak water and sink to the bottom of the ocean because of what we software engineers refers to as memory leaks I spent a lot of time fixing the library to the point where it could be argued I melted down the Titanic cast a new boat out of its original material ending up with a Battle Ship Cruiser with perfect memory management To put that into perspective below you can find my pull request for Alex amazing library My pull request to SQLite VSSIt s a monster of a pull request and it fixes some roughly to memory leaks I ran the entire code through ChatGPT before submitting my PR to Alex and even ChatGPT couldn t find any memory leaks in it and claimed every single function class and construct was perfect according to how to correctly create an SQLite database plugin Before my PR the thing would consume GB of memory in a test deployment in our Kubernetes cluster After it consumed half and don t grow to inifinity and beyond The leaks would make the library useless for all practical concerns Every single leak is now fixed Effectively making SQLite a better vector database than all vector database systems out there Once we start using the above plugin in our Kubernetes clusters we can basically increase model size from context snippets to probably context snippets for extreme cases This allows us to scrape websites with pages and create Q amp A chatbots out of them Previously our maximum was roughly web pages Further down the road we might even be able to continue modifying the library to the point where we can in theory index billions of pages using this technology This would effectively allow us to build Google and create chatbots with knowledge the size of the Himalayas The future is YOURS Magic our platform is open source Anything else would be unfair considering what s at stake Within a week we will deploy these changes into our technology for all to use allowing you to query databases with records in some seconds to extract context data This allows us to create chatbots for things such as CouchBase s documentation Microsoft s website DEV to for that matter etc etc etc This allows us to deliver technology allowing you to outperform Google and Microsoft on search Combined with the innovation that s happening in the GPT space with initiatives such as Hugging Face etc The inevitable result becomes as follows The future is YOURS Me and thousands of other open source software developers will make sure of it CreditsAlex for having built an amazing semantic search plugin for SQLite BRAVO Alex Dave Shapiro for constantly giving me good ideas for how to approach the AI spaceFacebook research for having open source licensed an amazing vector based indexing libraryMe for pulling all the strings together ending up with a usable product by melting down the Titanic and creating a Battle Ship Cruiser out of Alex original workPsst support our work by creating your own ChatGPT chatbot and play with it for a week for then to purchase a commercial license As long as you guys keep buying I ll make sure the people gets the power Psst a completely unrelated YouTube videos to find some inspiration	2023-06-16 07:44:43
金融	日本銀行：RSS	業態別の日銀当座預金残高（5月）	http://www.boj.or.jp/statistics/boj/other/cabs/cabs.xlsx	日銀当座預金残高	2023-06-16 17:00:00
金融	日本銀行：RSS	総裁記者会見（6月16日）動画の配信開始	http://www.boj.or.jp/about/release/sousaidouga.htm	記者会見	2023-06-16 16:50:00
金融	日本銀行：RSS	日本銀行政策委員会月報（令和5年5月号）	http://www.boj.or.jp/about/organization/policyboard/pb_geppo/pbgp2305.pdf	日本銀行政策委員会	2023-06-16 16:30:00
海外ニュース	Japan Times latest articles	Japan’s top court holds hearing on transgender woman’s bathroom restrictions	https://www.japantimes.co.jp/news/2023/06/16/national/crime-legal/transgender-official-bathroom-supreme-court/	Japan s top court holds hearing on transgender woman s bathroom restrictionsThe resulting ruling on the case which will mark the first time the Supreme Court has weighed in on the working environment for sexual minorities	2023-06-16 16:33:16
ニュース	BBC News - Home	Tesco sees early signs inflation is starting to ease	https://www.bbc.co.uk/news/business-65925217?at_medium=RSS&at_campaign=KARANGA	price	2023-06-16 07:18:21
ニュース	BBC News - Home	Why South Africa's Cyril Ramaphosa is leading Ukraine peace mission	https://www.bbc.co.uk/news/world-africa-65916196?at_medium=RSS&at_campaign=KARANGA	pressure	2023-06-16 07:12:41
ビジネス	東洋経済オンライン	脳の力を100％使えるようになる｢8：8：8｣の法則 プレゼン前日は｢しっかり寝る｣ほうが成功する | リーダーシップ・教養・資格・スキル | 東洋経済オンライン	https://toyokeizai.net/articles/-/674677?utm_source=rss&utm_medium=http&utm_campaign=link_back	東洋経済オンライン	2023-06-16 16:30:00
IT	週刊アスキー	『龍が如く7外伝 名を消した男』の主要キャストが発表！新たな舞台は西の大歓楽街「大阪・蒼天堀」	https://weekly.ascii.jp/elem/000/004/141/4141340/	主要キャスト	2023-06-16 16:30:00
IT	週刊アスキー	さくらインターネット、石狩データセンターの電力を再生可能エネルギーへ変更	https://weekly.ascii.jp/elem/000/004/141/4141310/	再生可能エネルギー	2023-06-16 16:15:00
マーケティング	AdverTimes	グランプリ「人生延長3日間」受賞チームなど表彰 第10回「BOVA」贈賞式	https://www.advertimes.com/20230616/article423151/	入賞作品	2023-06-16 07:23:47