Hype? You bet! A good dose of it!
Once AI can spit out all the code necessary for a functioning large, complex, and complicated system by providing only some rough description of it, we should be skeptical.
However, e.g. multi agent collaboration could possibly solve the issue of developing a large, complex software system via subtasking and a separate software engineer, product manager, designer, QA (quality assurance) engineer.
Typical tasks for AI so far: Detecting and fixing bugs or security flaws is fairly easy so is developing und running relevant test cases.
"A new breed of AI-powered coding tools have emerged—and they’re claiming to be more autonomous versions of earlier assistants like GitHub Copilot, Amazon CodeWhisperer, and Tabnine.
One such new entrant, Devin AI, has been dubbed an “AI software engineer” by its maker, applied AI lab Cognition. According to Cognition, Devin can perform all these tasks unassisted: build a website from scratch and deploy it, find and fix bugs in codebases, and even train and fine-tune its own large language model.
Following its launch, open-source alternatives to Devin have cropped up, including Devika and OpenDevin. Meanwhile makers of established assistants have not been standing still. Researchers at Microsoft, GitHub Copilot’s developer, recently uploaded a paper to the arXiv preprint server introducing AutoDev, which uses autonomous AI agents to generate code and test cases, run tests and check the results, and fix bugs within the test cases. ...
Devin, for instance, resolved only 14 percent of a subset of GitHub issues from real-world code repositories. “There’s still a long way to go for it to become something I can rely on blindfolded,” ..."
Following its launch, open-source alternatives to Devin have cropped up, including Devika and OpenDevin. Meanwhile makers of established assistants have not been standing still. Researchers at Microsoft, GitHub Copilot’s developer, recently uploaded a paper to the arXiv preprint server introducing AutoDev, which uses autonomous AI agents to generate code and test cases, run tests and check the results, and fix bugs within the test cases. ...
Devin, for instance, resolved only 14 percent of a subset of GitHub issues from real-world code repositories. “There’s still a long way to go for it to become something I can rely on blindfolded,” ..."
Devin AI Website - The First AI Software Engineer Cognition "Cognition AI has unveiled a groundbreaking development in the field of artificial intelligence with the introduction of Devin AI, the world's first fully autonomous AI software engineer. This innovative AI has set a new benchmark in the industry, showcasing an exceptional ability to handle complex software engineering tasks with finesse and precision."
No comments:
Post a Comment