Yoshua Bengio, one of the pioneers of artificial intelligence, Turing Award laureate, and scientist whose research laid the foundation for modern AI systems, raised alarm.…
💻 Using Nginx for load balancing LLM chat sessions. There are many examples of connecting LLM models to a Telegram bot, but with a large number of users, there are no…
This article discusses AI integration packages from Effect—a set of tools designed to simplify working with large language models in modern applications. It describes…
We at MWS have launched a language model aggregator, where you can work with multiple LLMs through a single interface. In MWS GPT, the following models are available:…
Yet again, someone on LinkedIn decided to have some fun. They say Elon Musk has decided to rework the US Social Security software in a new way. Oh dear, what a blockheaded…
Agents are super buggy. In our company projects, we noticed that Langchain started to perform worse. In multi-agent systems, agents often loop because they don’t understand…
This article about the new extension of the transformer architecture – Titan from Google – that allows expanding the limits of LLM to 2 million tokens, prompted me to…
Hello, this is Yulia Rogozina, a business process analyst at Sherpa Robotics. Today I translated an article for you, the topic of which concerns the use of Large Language…
There is a classic problem on any marketplace related to how to categorize and understand product descriptions. It is especially exacerbated by the fact that users create…
There is a classic problem on any e-commerce platform related to how to categorize and understand product descriptions. It is especially exacerbated by the fact that…
When LLMs first appeared, they were a bit like children - they said the first thing that came to their mind and didn't care much about logic. They needed to be reminded:…
Generation with augmented sampling is a method that connects external data sources to improve the output of large language models. This method is ideal for LLM to access…
In recent years, the quality of LLM models has significantly improved, quantization methods have become better, and graphics cards more powerful. Nevertheless, the quality…
In this post, we will talk in detail about RAG at each of its stages, its modifications, and its promising directions of development at the time of writing.
Should we trust something that cannot understand the consequences of its actions? The answer seems obvious, but as the niche of linguistic models develops, we increasingly…
Colleagues, don't argue and don't be afraid - I'm not going to prove the existence or absence of a soul in either robots or humans :) After all, a definition of the soul…
I asked the following question to the most popular LLMs.
For most developers, tests are the least favorite part of the job. Recently, we confirmed this by surveying more than 400 developers at the Joker and Heisenbug conferences…