OpenAI is updating its API with support for Structured Outputs to ensure that the outputs of its models match the JSON Schemas provided by developers. According to OpenAI, one of the core use cases for AI today is the ability to generate structured data from unstructured inputs, but previously, developers needed to utilize open source … continue reading
Good teamwork is key to any successful AI project but combining data scientists and software engineers into an effective force is no easy task. According to Gartner, 30 percent of AI projects will be abandoned by the end of 2025 thanks to factors such as poor data quality, escalating costs and a lack of business … continue reading
JetBrains has announced the 2024.2 updates for its IDEs, the highlights being that the new UI is now the default and several improvements were made to AI Assistant. “We are thrilled to announce the 2024.2 updates to our IDEs and significant enhancements to our AI Assistant,” said Vladislav Tankov, Head of JetBrains AI. “With the impressive … continue reading
On Monday, a federal judge ruled that Google had violated antitrust laws to achieve its dominance in the search engine market, where it currently holds over 90% of the market share. “Google is a monopolist, and it has acted as one to maintain its monopoly,” Judge Amit P. Mehta of U.S District Court for the … continue reading
Technical debt is a normal and unavoidable side effect of any IT implementation. It occurs as teams “borrow” against quality by making sacrifices, taking shortcuts or using workarounds to meet delivery deadlines. Eventually, this can impact performance, scalability, resilience, complexity, agility or similar characteristics. The impact of technical debt in integration can be much higher … continue reading
Qualys has announced a new tool called Qualys TotalAI that will enable teams to better address the security risks of generative AI. Specifically, it addresses the issues listed in the OWASP Top 10 for LLMs, which includes things like prompt injection, sensitive information disclosure, and model theft. According to Qualys, one of the big challenges … continue reading
Various studies have shown that developers spend only 25% to 35% of their time actually coding. That means if a copilot boosts their coding productivity by a factor of 2, it may only save an hour of their day. Which begs the question: where is the rest of their time spent and how can AI … continue reading
GitHub is announcing a new sandbox environment — GitHub Models — where developers can experiment with AI models from different providers right from within GitHub. Developers can access models and then test different prompts and model parameters in a playground environment. “For most of us, learning to be a developer didn’t happen on a linear … continue reading
Developers, it appears, will not be replaced by artificial intelligence – at least not yet, anyway. What they will need to do is learn or improve their skills in providing templates for AI, become masters of fixing problems in AI-generated code, and actually learn the best uses for AI in software development. In its current … continue reading
Earlier this week, Microsoft introduced the Agent Framework to its open source project Semantic Kernel, an SDK that integrates LLMs with C#, Python, and Java so that developers can incorporate AI features into their apps. With this new experimental framework, agents are now supported in the platform. According to Microsoft, agents are AI entities that … continue reading
Generative AI has the potential to have a positive impact on software development and productivity, but with that increased productivity comes increased pressure on software testing. If you can generate five or even 10 times the amount of code you previously could, that’s also five to 10 times more code that needs to be tested. … continue reading
The White House is issuing recommendations not to restrict the use of open source AI models, based on a report from the Department of Commerce’s National Telecommunications and Information Administration (NTIA). The report recommends open models continue to be monitored for potential risks. Part of NTIA’s recommendation is that the government should start an ongoing … continue reading
Google has announced three new products that are part of the Gemma 2 family, a series of open AI models that were introduced in June. The new offerings include Gemma 2 2B, ShieldGemma, and Gemma Scope. Gemma 2 2B is a 2 billion parameter option, joining the existing 27 billion and 9 billion parameter sizes. … continue reading
When an event like the CrowdStrike failure literally brings the world to its knees, there’s a lot to unpack there. Why did it happen? How did it happen? Could it have been prevented? On the most recent episode of our weekly podcast, What the Dev?, we spoke with Arthur Hicken, chief evangelist at the testing … continue reading