Best Programming Master

Google is enhancing its AI coding agent, Jules, with new functionality that reviews and critiques code while Jules is still working on it.  “In a world of rapid iteration, the critic moves the review to earlier in the process and into the act of generation itself. This means the code you review has already been interrogated, refined, and stress-tested … Great developers don’t just write code, they question it. And now, so does Jules,” Google wrote in a blog post .  According to the company, the coding critic is like a peer reviewer who is familiar with code quality principles and is “unafraid to point out when you’ve reinvented a risky wheel.” For instance, it might flag a patch that passed all tests but introduced a logic error, a change that compiles but drops a required field, or code that works but is inefficient.  This capability is different from a linter or test because it doesn’t follow specific rules or validate specific assertions. Rather, it understands th...

AI company bitHuman has announced a visual SDK for creating avatars for use as chat agents, instructors, virtual coaches, companions, and experts in different fields.  According to the company, the SDK allows avatars to be created on Arm-based and x86 systems without a GPU. The avatars have a small footprint and can be run online or offline on devices like Chromebooks, Mac Minis, and Raspberry Pis.  Because of their small footprint, these characters can be brought to a wide range of environments, including classrooms, kiosks, mobile apps, or edge devices.  “Running AI in the cloud can be a challenge in certain scenarios due to privacy, latency or cost,” said Parag Beeraka, senior director of consumer computing at Arm. “bitHuman’s SDK takes full advantage of Arm’s CPU performance and widespread adoption to deliver rich, responsive avatars, showing how on-device AI is unlocking new, immersive user experiences.” The SDK can also be used with the LiveKit plugin so that de...

GitHub’s CEO Thomas Dohmke has announced his plans to leave the company at the end of the year.  Dohmke says he will be staying with the company through the end of the year to help with the transition. When he leaves GitHub, he plans to build a new startup. “After all this time, my startup roots have begun tugging on me and I’ve decided to leave GitHub to become a founder again,” he wrote in a memo .  In the memo, he also said that Microsoft doesn’t plan to replace him; rather, GitHub and its leadership team will now operate under Microsoft’s CoreAI organization, a group within the company focused on developing AI-powered tools, including GitHub Copilot.  “Today, GitHub Copilot is the leader of the most successful and thriving market in the age of AI, with over 20 million users and counting,” he wrote. “We did this by innovating ahead of the curve and showing grit and determination when challenged by the disruptors in our space. In just the last year, GitHub Copilo...

Developer advocacy is a specialized role within developer relations focused on helping customers understand how the latest trends and products translate into value, Wade Wegner, chief ecosystem and growth officer at DigitalOcean, explained during a recent episode of our What the Dev? podcast.  Advocates work to drive adoption of products, but how they do it is what sets them apart from traditional sales and marketing teams.  “[Developer advocacy] is a growth tool, and it is an incredibly powerful way to close the distance between what it is that you want to highlight, and how it translates into real things when it comes to what it is developers are doing, the code that they’re writing, the workflows that they’re building, the communities they’re involved in. And so I think I tend to think about developer advocates way more as a function of growth versus marketing or sales or or anything else,” he said. In addition to driving growth, this work also leads to better products...

Whispers of “AI PCs” have been circulating for some time, promising a new era of on-device intelligence. Yet, for many, the reality has felt underwhelming, with a scarcity of compelling applications that truly leverage the dedicated Neural Processing Units (NPUs) within these machines. But what if the next leap in personal AI isn’t a desktop or laptop, but the device already glued to our palms? The coming AI smartphone is poised to learn from the AI PC’s early stumbles, offering a transformative user experience that could eventually see it dominate the smartphone, tablet and PC markets. Avoiding the AI PC’s App Problem The primary challenge for the AI PC has been the chicken-and-egg dilemma: developers are hesitant to build NPU-specific applications without a large installed base, and consumers see little reason to upgrade without compelling NPU-powered apps. Indeed, reports indicate that a lack of clear understanding of AI’s business value and security concerns have hindered AI PC a...

OpenAI launches GPT-5 OpenAI announced the availability of GPT-5, which it says is “smarter across the board” compared to previous models. Specifically for coding, GPT-5 achieved significant improvement in complex front-end generation and debugging larger repositories. Early testers said that it made better design choices in terms of spacing, typography, and white space, according to the company.  “We think you will love using GPT-5 much more than any previous AI,” CEO Sam Altman said during the livestream. “It is useful. It is smart. It is fast. It’s intuitive.” Anthropic releases Claude Opus 4.1 This latest update improves the model’s research and data analysis skills, and achieves 74.5% on SWE-bench Verified (compared to 72.5% on Opus 4).  It is available to paid Claude users, in Claude Code, and on Anthropic’s API, Amazon Bedrock, and Google Cloud’s Vertex AI.  The company plans to release larger improvements across its models in the coming weeks as well....

Melissa, a provider of data quality solutions, is making it possible for customers to run its SQL Server Integration Services (SSIS) components in Azure Data Factory through the Azure-SSIS Integration Runtime. This brings the power of Melissa’s data quality features to the cloud, providing customers greater flexibility in where their data is stored. SSIS is Microsoft’s ETL solution that allows companies to extract and transform data from sources like XML data files, flat files, and relational data sources, then load it into different data destinations, such as SQL Server, Azure SQL Database, Azure Synapse Analytics, or cloud storage. “A lot of clients say ‘hey, we’re still using SSIS, and we would like to do the same thing, but not on my local machine anymore. Now we want to do it in the Azure cloud environment,’” said Ben Nguyen, sales engineer II and software engineer II at Melissa.  This led Melissa to create this integration that would allow its SSIS packages to be seamless...

During a livestream today, OpenAI announced the availability of GPT-5 , which it says is “smarter across the board” compared to previous models. Specifically for coding, GPT-5 achieved significant improvement in complex front-end generation and debugging larger repositories. Early testers said that it made better design choices in terms of spacing, typography, and white space, according to the company .  “We think you will love using GPT-5 much more than any previous AI,” CEO Sam Altman said during the livestream. “It is useful. It is smart. It is fast. It’s intuitive.” He likened GPT-3 to talking to a high school student, in that sometimes there were flashes of brilliance. Then, GPT-4 was like talking to a college student, with real intelligence and real utility. He says that GPT-5 is like talking to a PhD level expert in any area you need.  The model can answer most questions and leverages a deeper reasoning model for harder problems and a real-time router for deciding ...

Elastic has announced the release of Log Essentials, providing SREs and developers with capabilities for ingesting, searching, visualizing, and alerting on logs. It is designed to enable developers to access observability capabilities without needing to manage the operations, upgrades, or tuning.  “SREs need a hassle-free, scale-as-you-go, high-availability logging solution that empowers them to focus entirely on operational insights, not infrastructure, without the complexity of standing up and maintaining observability tooling,” said Santosh Krishnan, general manager of Observability & Security at Elastic. “Logs Essentials makes it easy to get started with Elastic by offering a simple, reliable path to insights at a lower entry point.” It enables root cause analysis via log search using filters, pattern matching, and event identification.  Users can also use Elastic’s query language, ES|QL; set alerts for error spikes or unusual log volumes; and use Kibana-based visu...

It’s imperative that business leaders can enable their business to work at the speed that technology is moving. However, lengthy and cumbersome approval processes to adopt new tools can hinder an organization’s ability to keep pace, especially when they need to remain compliant with regulations and standards, such as FedRAMP and SOC-2.  With a three-stage developer experimentation framework, organizations can make it easier to evaluate new technologies, determine their fit and accelerate their adoption across the organization. Stage One: Trial The goal of the first stage involves exploratory testing to gauge how a development tool might benefit the organization. The primary objective is to identify concrete applications for the organization through hands-on experimentation. During the trial stage, the tool should be used only by a small cohort of engineers while it’s still new, untested and unvetted. Additionally, the trial stage should be limited to a short period of time for ...

OpenAI is joining the open weight model game with the launch of gpt-oss-120b and gpt-oss-20b.  Gpt-oss-120b is optimized for production, high reasoning use cases, and gpt-oss-20b is designed for lower latency or local use cases.  According to the company, these open models are comparable to its closed models in terms of performance and capability, but at a much lower cost. For example, gpt-oss-120b running on an 80 GB GPU achieved similar performance to o4-mini on core reasoning benchmarks, while gpt-oss-20b running on an edge device with 16 GB of memory was comparable to o3-mini on several common benchmarks.  “Releasing gpt-oss-120b and gpt-oss-20b marks a significant step forward for open-weight models,” OpenAI wrote in a post . “At their size, these models deliver meaningful advancements in both reasoning capabilities and safety. Open models complement our hosted models, giving developers a wider range of tools to accelerate leading edge research, foster innovation...

Microsoft has announced the release of .NET Aspire 9.4, which the company says is the largest update yet.  .NET Aspire is a set of tools, templates, and packages that Microsoft provides to enable developers to build distributed apps with observability built in.  With this release, Aspire’s CLI is now generally available and includes four core commands: aspire new (use templates to create an app), aspire add (add hosting integrations), aspire run (run the app from any terminal or editor), and aspire config (view, set, and change CLI settings).  Additionally, there are two new beta commands that can be turned on using aspire config set . exec allows developers to execute CLI tools and deploy allows apps to be deployed to dev, test, or prod environments.  Microsoft also redesigned the experience around its eventing APIs and added an interaction service that allows developers to create custom UX for getting user input. It supports standard text input, masked t...

With cloud native technologies becoming foundational for software development and deployment, and finding developers skilled in those areas a challenge, talent marketplace provider Andela and the Cloud Native Computing Foundation have partnered to create the Kubernetes African Developer Training Program that more than 5,600 Africans have completed. Andela and the CNCF are looking to train between 20,000 – 30,000 African technologists by 2027, skilled in everything required to create and use AI systems. The eight-week program is free, and those completing the training have the option to seek CNCF certification. (Of the 5,600 learners that participated in the training, 1157 have achieved official KCNA certification, according to Andela.) “Kubernetes is a technology you can bet your career on. It’s the backbone of modern software, and increasingly, of scalable AI systems. The demand for this skill is exploding,” Carrol Chang, CEO of Andela, said in an announcement of the program. “At An...

Since the 2001 Agile Manifesto, software development has thrived on principles like “individuals and interactions over processes,” continuous delivery, and embracing change. Over the following decades, we watched Agile disrupt heavyweight, documentation-driven SDLCs by enabling iterative value delivery and adaptive planning. Now, fast forward to 2025, and AI is drastically changing software development . Models like GPT-4o and Claude 3.5 Sonnet can generate code in seconds, prompting a critical question for industry veterans: Is Agile still relevant? Or have AI-driven workflows reshaped what “agile” should be? AI Isn’t Killing Agile, It’s Reframing It Generative AI tools like Copilot and GPT-based systems have become essential in modern developer workflows, automating routine tasks and accelerating prototyping. For example, Robinhood’s engineering teams report that the majority of new code is generated by AI, with near-universal adoption among developers. However, this shift ha...

Google’s new Opal tool allows users to create mini AI apps with no coding required Google has launched a new experimental AI tool designed for users who want to build apps entirely using AI prompts, with no coding needed at all. Opal  allows users to create mini AI apps by chaining together AI prompts, models, and tools, using natural language and visual editing. “Opal is a great tool to accelerate prototyping AI ideas and workflows, demonstrate a proof of concept with a functional app, build custom AI apps to boost your productivity at work, and more,” Google wrote in a  blog post . The tool consists of a visual editor to help creators see the workflows in their apps and connect different prompts together to build multi-step apps. It allows the user to describe the logic they want in the app and have Opal build the workflow for them. Users will be able to edit the generated workflow either in the visual editor or through additional prompts. Gemini 2.5 Flash-Lite is now g...