GitHub Copilot now supports multiple LLMs

Picture of a person with a digital brain with multiple coloured waves illustrating the GitHub Copilot AI software development assistant gaining accessing to multiple new LLMs (large language models)

GitHub is bringing more flexibility and choice to Copilot through the integration of multiple large language models (LLMs).

Since its inception, GitHub Copilot has utilised different LLMs for varied uses. The journey began with the deployment of Codex, an early iteration of OpenAI's GPT-3, that was fine-tuned specifically for coding tasks. The evolution continued with the launch of Copilot Chat in 2023, initially using GPT-3.5 and subsequently transitioning to GPT-4. As demands...

30 October 2024 | Artificial Intelligence

GitHub Copilot users gain access to Stack Overflow knowledge

Smartphone with glasses and a book illustrating the launch of a Stack Overflow extension for the GitHub Copilot AI assistant for developers, enabling users to access the vast knowledge platform to find solutions for software development problems.

Stack Overflow has launched an extension for GitHub Copilot that promises to improve how developers find solutions. The extension allows users to pose questions directly within the AI-driven coding assistant and receive summarised responses informed by Stack Overflow's extensive knowledge base.

GitHub and Stack Overflow’s partnership aims to aid developers in tackling their most challenging coding queries. The latest Stack Overflow Developer Survey reveals that 61% of developers...

29 October 2024 | Artificial Intelligence

JetBrains launches AI model for software development tasks

Image of a brain illustrating the launch of the new Mellum LLM by JetBrains that enhances its AI assistant for developers that specialises in software development tasks.

JetBrains has announced the launch of Mellum, its own AI model specifically engineered for software development tasks.

Mellum has been integrated exclusively into JetBrains’ AI Assistant, reporting dramatic improvements in both speed and accuracy of code completions compared to previous implementations.

Unlike more extensive language models, Mellum has been purposefully designed with a smaller footprint to deliver near-instantaneous coding suggestions. The model...

23 October 2024 | Artificial Intelligence

Holistic’s open-source tools counter AI development risks

Woman punching illustrating the launch of Holistic AI open-source tools to counter artificial intelligence software development risks and algorithmic bias.

Holistic has unveiled an open-source library to help counter AI development risks and build fairer and more responsible systems.

The library – dubbed Holistic AI OSL – arrives at a crucial moment when organisations are increasingly deploying AI systems across sensitive domains including recruitment, healthcare, and financial services. Recent studies suggest that 65% of AI researchers and developers still consider bias a significant challenge in their work.

Holistic...

23 October 2024 | Artificial Intelligence

Anthropic launches Message Batches API for Claude

Illustration by Anthropic AI depicting their Message Batches API for developers to take full advantage of the Claude large language model.

Anthropic has launched its Message Batches API, which offers developers a cost-effective solution for processing large volumes of Claude queries asynchronously. 

Through the Message Batches API, developers can now send batches of up to 10,000 queries. These batches are processed in less than 24 hours and come at a 50% reduction in cost compared to standard API calls—representing a significant advancement in handling non-time-sensitive tasks more efficiently.

The...

9 October 2024 | API

GitHub’s Copilot Autofix triples vulnerability remediation speed

Shipping software quickly often comes at the cost of security, with vulnerabilities inadvertently making their way into production code. This poses a significant challenge, as many developers find security requirements complex and difficult to implement.

"Developers are shipping software faster than previously imaginable, releasing new features early and often. Yet, despite their best efforts to code securely, software vulnerabilities inadvertently make their way into production...

14 August 2024 | Artificial Intelligence

Sterling Chin, Postman: Transforming API testing and documentation with AI

In an interview ahead of AI & Big Data Expo Europe, Sterling Chin, Senior Developer Advocate at Postman, shed light on the company's AI-powered tool Postbot and its impact on API development.

Postbot is Postman's intelligent assistant designed to tackle two perennial pain points in API development: testing and documentation.

"The major pain points that Postbot solves is allowing you to – by click of a button – generate tests for your APIs, generate...

12 August 2024 | API

OpenAI cures structured data headache for developers

OpenAI has unveiled "Structured Outputs", a new API feature designed to address the long-standing challenge of reliably generating structured data from large language models (LLMs). The feature, available now, guarantees that model-generated outputs will adhere to developer-defined JSON Schemas.

Generating structured data from unstructured input is a cornerstone of many AI applications today. Developers leverage the OpenAI API to build sophisticated assistants capable of fetching...

7 August 2024 | Artificial Intelligence

Hugging Face partners with NVIDIA to democratise AI inference

Hugging Face has joined forces with NVIDIA to bring inference-as-a-service capabilities to one of the world's largest AI communities. This collaboration, announced at the SIGGRAPH conference, will provide Hugging Face's four million developers with streamlined access to NVIDIA-accelerated inference on popular AI models.

The new service enables developers to swiftly deploy leading large language models, including the Llama 3 family and Mistral AI models, with optimisation from...

30 July 2024 | Artificial Intelligence

OpenAI slashes AI costs with high-performance GPT-4o mini

OpenAI has announced GPT-4o mini, a small model designed to make AI more accessible and affordable for developers. This new addition to the GPT family promises superior performance at a fraction of the cost of previous models, including the regular GPT-4o .

GPT-4o mini still boasts impressive capabilities, scoring 82% on the MMLU benchmark and outperforming GPT-4 on chat preferences in the LMSYS leaderboard. The model is priced at just 15 cents per million input tokens and 60...

19 July 2024 | API