Recommended AI services lately This article introduces some famous and recommended AI services. Excluding ChatGPT and Gemini, services that improve work efficiency such as NotebookLM and Perplexity AI are listed. NotebookLM is a service provided by Google, which allows you to search f
GCP DB Instance Pricing ( Cloud SQL vs AlloyDB ) This guide compares the pricing and features of Google Cloud SQL and AlloyDB, helping you choose the optimal database for your service scale. Cloud SQL supports MySQL, PostgreSQL, and MS SQL, offering a wide range of features through HA configurations and
When JSON breaks in Gemini (or other LLMs) Learn how to use yaml to solve the problem of output breaking due to incorrect characters when generating JSON from LLMs such as Gemini Pro and Flash. Requesting output as yaml allows for stable output, which can then be converted back to json. However, o
Gemini 1.5 Flash, GPT-4o, and Pricing of Other LLMs Compare the performance and pricing of the latest AI models such as GPT-4o, Gemini 1.5 Pro, Claude 3 Haiku, and Gemini 1.5 Flash. We will guide you on how to choose the right model for you. Consider input token size, output ratio, task difficulty, etc. to
Apple's OpenELM / MS's Phi-3 / Meta's Llama 3 Released Major tech companies such as Apple, Microsoft, and Meta are injecting new energy into the AI industry by recently releasing their own large language models. These newly released models are evolving in various directions, including size reduction, data opt
Does writing on durumis really make it searchable globally and in other languages? durumis provides services to global users using multilingual generative AI, and can secure up to tens of times more traffic through global exposure than exposure in Korean only.
Claude 3 vs Gemini Price Comparison Anthropic's Claude 3 Haiku model is now available on GCP, and H2O.ai's evaluation using RAG shows that it outperforms Gemini in terms of price-to-performance. Claude 3 Haiku is the cheapest based on input and output costs per million tokens.
Google I/O (May 14), Apple WWDC (June 10) Schedule Announced Major technology event schedules: Google Next (April 9), Google I/O (May 14), Apple WWDC (June 10). These events are expected to showcase innovative technologies in various fields, including cloud computing, artificial intelligence, and operating systems.
Why is Naver's search engine so different? There are concerns that Naver's search engine prioritizes its own content, leading to poor search visibility for external content and potentially limiting users' access to diverse information. As the leading player in the domestic search market, Naver nee
Redis 7.4 - License Policy Changes Redis is a memory-based database that offers fast speeds and easy data processing. Recently, it has changed its license policy, requiring cloud service providers who host Redis products to enter into license agreements. General developers can use Redis Co
The End of 'Third-Party Cookies' and the Rise of New Login Technologies The blocking of third-party cookies is leading to changes in social login systems, and Google has developed a new technology called FedCM for secure logins. FedCM is implemented as a small window within the web browser itself, preventing phishing and allo
Email Sending Service Price Comparison We have compared and analyzed various email services such as Naver, NHN, AWS, and SendGrid. As a result of examining the free upper limit and the cost per unit, AWS SES is the cheapest at 0.1 won per unit. Currently, we are using NCP Outbound Mailer, but
ChatGPT vs Gemini Pricing Comparison This article compares two major LLM services currently available, ChatGPT and Gemini. ChatGPT, which is token-based, is charged $0.125 per 1 million tokens, while Gemini, which is character-based, is charged $0.125 per 1 million characters for input and $
durumis Development - Part 3: Gemini Pro durumis has developed various features using Google's next-generation LLM 'Gemini Pro'. By applying AI technology such as automatic URL generation, summarization, writing descriptions, generating topics, and automatic classification, we have efficientl
Durumis Development - Part 2: Infrastructure Durumis uses GCP for global service, and provides services in 7 regions worldwide, including Seoul, Singapore, Mumbai, Belgium, South Carolina, Sao Paulo, and Los Angeles. Users can view articles and images quickly from the nearest region. The technologie
Durumis Development Story - Part 1: The Beginning of Development Durumis is a global multilingual blog service developed using generative AI and GCP. Harrison, the developer, shares his experiences of the development process and multi-region service construction, and plans to cover infrastructure in more detail in the