Last year’s MOVEit and 3CX vulnerabilities offered a stark reminder of the risk software supply chain attacks pose today.

Threat actors exploit vulnerabilities to infiltrate a software provider’s network and modify the software’s original functionality with malicious code. Once the infected software is passed on to customers, typically through software updates or application installers, the breach opens the door to unauthorized tasks, such as exfiltrating sensitive information or hijacking data.

To read this article in full, please click here

Značky: #Devops, #Devsecops, #Security, #Rozne

I’ve been asked if generative AI systems are always slow. Of course, I reply, “Slow, as compared to what?” The response I always get is funny. “Slower than we thought it would be.” And the circle continues.

Performance is often an afterthought with generative AI development and deployment. Most deploying generative AI systems on the cloud, and even not the cloud, have yet to learn what the performance of their generative AI systems should be, take no steps to determine performance, and end up complaining about the performance after deployment. Or, more often, the users complain, and then generative AI designers and developers complain to me.

To read this article in full, please click here

Značky: #Rozne

In an effort to streamline code, Java would be enhanced with derived record creation, via a proposal that would provide a means to create record instances from existing records through a block of transformation code.

The OpenJDK proposal authored by Oracle technical staff, titled “Derived Record Creation,” would streamlinescode by deriving a new record from an existing record, updating only components that need to change. The proposal notes that because records are immutable values, developers frequently build new records to reflect new data. The feature would enter Java in a preview state.

To read this article in full, please click here

Značky: #Rozne, #Java

As important as code is, documentation of that code is arguably more important . No developer, and no software, exists in a vacuum; unless other developers can understand the code you’ve written, it loses much of its potential impact.

But what about machines? Do they also need good docs?

The answer is yes, and points to a future of “tiered documentation,” a term I first saw described by Vlad Ionescu. As he details , tiered documentation means “having one set of documentation for human users and having another set of documentation specifically for LLM [large language model] training.” The former needs to be easily consumed by people; the latter needs to be detailed so that tools such as Amazon CodeWhisperer or GitHub Copilot will yield ever-improving code. It’s a fascinating concept with the ultimate aim of improving developer productivity. So, what do we need to get there?

To read this article in full, please click here

Značky: #Developer, #Rozne

As the momentous first year of ChatGPT comes to a close, it’s clear that generative AI (genAI) and large language models (LLMs) are exciting technologies. But are they ready for prime-time enterprise use?

There are well-understood challenges with ChatGPT , where its responses have poor accuracy. Despite being based on sophisticated computer models of human knowledge like GPT-4 , ChatGPT rarely wants to admit ignorance, a phenomenon referred to as AI hallucinations , and it often struggles with logical reasoning. Of course, this is because ChatGPT doesn’t reason —it operates like an advanced text auto-complete system.

To read this article in full, please click here

Značky: #Rozne

On November 15, Microsoft announced Azure AI Studio , a new platform for generative AI application development, using OpenAI models such as GPT-4, as well as models from Microsoft Research, Meta, Hugging Face, and others. The motivation for the product, Microsoft said, is that “navigating the complexities of prompt engineering, vector search engines, the retrieval-augmented generation (RAG) pattern, and integration with Azure OpenAI Service can be daunting.”

It turns out that Azure AI Studio is a nice system for picking generative AI models, for grounding them with RAG using vector embeddings, vector search , and data, and for fine-tuning those models, all to create AI-powered copilots, or agents. It’s the “basement-level” tool for creating copilots, aimed at experienced developers and data scientists, while Microsoft’s Copilot Studio is a “2nd-floor level” low-code tool for customizing chatbots.

To read this article in full, please click here

Značky: #Microsoft, #Rozne

Following fast in the footsteps of the Astro 4.1 release , Astro 4.2 has arrived, bringing improvements to accessibility rules and the ability for remark plugins to customize image optimization.

The Astro 4.2 release also introduces prerendering using the Speculation Rules API and reworked routing priority for injected routes, both experimental features.

Launched January 19 , Astro 4.2 marks the first release of the framework of almost all community-built features. Installation instructions for Astro can be found on GitHub .

To read this article in full, please click here

Značky: #JavaScript, #Rozne

In an exercise in dogfooding, I asked the GPT-4 large language model “What is retrieval-augmented generation?” using its Browse plug-in, which is one implementation of retrieval-augmented generation.

This is what GPT-4 eventually told me, after I asked it to regenerate its answer:

-----------------

Retrieval-Augmented Generation (RAG) is an AI framework that significantly impacts the field of Natural Language Processing (NLP). It is designed to improve the accuracy and richness of content produced by language models. Here’s a synthesis of the key points regarding RAG from various sources:

To read this article in full, please click here

Značky: #Rozne

With the just-released Preview 3 of the planned Visual Studio 2022 17.9 upgrade, Microsoft has enhanced Code Search, also known as the All-In-One Search experience.

The third preview of Visual Studio 2022 17.9 was launched January 17 and can be downloaded at the Visual Studio website .

The improvements to Code Search allow Visual Studio users to search for any word or string of characters across their solution, supplementing file and symbol results from their codebase. Users also now can search for words in comments, names of variables and parameters, or any other string of characters across a codebase. For more specialized text search, Find in Files (Ctrl+Shift+F) and Quick Find (Ctrl+) offer more options.

To read this article in full, please click here

Značky: #Rozne