The explosion of open-source AI frameworks has given developers unprecedented flexibility in deploying AI models. Portkey, an open-source AI gateway, simplifies AI model orchestration by providing a ...

LiteLLM allows developers to integrate a diverse range of LLM models as if they were calling OpenAI’s API, with support for fallbacks, budgets, rate limits, and real-time monitoring of API calls. The ...

The development of DeepSeek v2.5 involved the fusion of two highly capable models: DeepSeek version 2 0628 and DeepSeek Coder version 2 0724. By combining the strengths of these models, DeepSeek v2.5 ...

On January 20, 2025, Chinese AI startup DeepSeek unveiled R1, an open-source large language model (LLM) that is redefining industry expectations. Designed to offer performance on par with proprietary ...

ETH Zurich and EPFL’s open-weight LLM offers a transparent alternative to black-box AI built on green compute and set for public release. Large language models (LLMs), which are neural networks that ...

While the shortest distance between two points is a straight line, a straight-line attack on a large language model isn't always the most efficient — and least noisy — way to get the LLM to do bad ...

The release of Deepseek v3.1 signifies a major advancement in the realm of large language models (LLMs). This open source AI model, licensed under MIT, introduces a powerful 700GB mixture of experts ...

AI frameworks, including Meta’s Llama, are prone to automatic Python deserialization by pickle that could lead to remote code execution. Meta’s large language model (LLM) framework, Llama, suffers a ...

Xiaomi has quietly stepped into the large language model space with MiMo-7B, its first publicly available open-source AI system. Built by the newly assembled Big Model Core Team, MiMo-7B focuses ...

According to Microsoft, the decision to open source GitHub Copilot Chat stems from a growing demand for transparency in how AI-assisted developer tools work -- particularly around prompt engineering, ...

Researchers at the University of Science and Technology of China have developed a new reinforcement learning (RL) framework that helps train large language models (LLMs) for complex agentic tasks ...

The vibe coding tool Cursor, from startup Anysphere, has introduced Composer, its first in-house, proprietary coding large language model (LLM) as part of its Cursor 2.0 platform update. Composer is ...