LLaMator: Red Teaming framework for testing LLM vulnerabilities
Hello, tekkix! In this material, we, the LLaMasters team — 1st year master's students of ITMO AI Talent Hub, present the LLaMator framework, which won the AI Product…
Introduction to Large Language Models (LLM)
Applications and Benefits of LLM in IT
IQ distribution: how a programmer can survive in a world designed for fools?
You have probably often caught yourself thinking that many things in our world are arranged as illogically as possible, and, ideally, should have been arranged completely…
Using ChatGPT for automating code generation in a JS project
In my previous articles on developing Telegram bots, I shared my experience of creating basic functionality and working with commands through arguments. While preparing…
From context to jurisdiction: 7 key parameters when choosing an LLM for your project
A year ago, it seemed that simply choosing GPT-4 was enough to solve all AI problems. Today, the language model market resembles a zoo, with new exotic species appearing…
AI without illusions. Debunking myths
In my podcast, I threatened to read the article GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models by Apple scientists and…
How to teach LLM to understand video? Overview of approaches
Hello everyone! Today we will talk about the task of understanding video and the evolution of approaches to training multimodal large language models for this task.
How to Win Kaggle Competitions: LLM Analysis of Winning Solutions
About a year ago, a Kaggle enthusiast named Darek Kłeczek conducted an interesting experiment: he collected all available descriptions of winning solutions on Kaggle…
Comparison of five LLM models: ChatGPT-4, GigaChat Pro, GigaChat Lite, YaGPT Pro, and Llama 3 7B
Hello, friends! Today we would like to discuss five popular LLM models that our team had the opportunity to work with: ChatGPT-4, GigaChat Pro, GigaChat Lite, YaGPT Pro,…
Models Gemini 1.5 from Google: main about Gemini 1.5 Pro
One of the main models of the Gemini 1.5 series is the Gemini 1.5 Pro. This is the latest version of large language models from Google, which has attracted significant…
What can gorilla Koko teach us
On July 4, 1971, the 50th gorilla born in captivity was born at the San Francisco Zoo. Since the birth date of this gorilla coincides with the US Independence Day, which…
AI from the startup Mercor conducted interviews with 300,000 applicants, and now it is valued at $250 million
Under the leadership of three 21-year-old Thiel Fellows, the AI startup Mercor attracted $32 million from Benchmark, Peter Thiel, and other investors. The startup's revenue…
Sam Altman: "Next-generation AI will be able to invent breakthrough technologies and cure diseases"
According to the company's CEO, Sam Altman, the next generation of artificial intelligence systems will be able to perform tasks independently without human intervention,…
Creation of a code generation tool using Rust and local LLMs from Ollama
This is a reaction to the release of ChatGPT o-preview. An attempt to add logic to open-source LLMs that can be run at home on a modest GPU or even on a CPU
The trend towards AI has brought microchip manufacturing back to the forefront of computer technology
Author of The Economist magazine Shailesh Chitnis discusses in the Technology Quarterly special issue how increased attention to artificial intelligence is changing the…
Garak: Red-Team tool for finding vulnerabilities in LLM
«ChatGPT reveals personal data of real people!», «Side-channel attack on ChatGPT!», «ChatGPT chatbot caused a leak of confidential data!», «Hackers started using ChatGPT…
Application Security for Large Language Models
Discover OWASP Top 10 for LLM and GenAI and explore key strategies for securing your AI models and applications.
What does LLM think about the meaning of life of a programmer
Perhaps it is on Programmer's Day that it will be interesting to look at your life from an unexpected point of view, rising a little higher, so to speak, from a bird's…