Krea 3 is a production-focused image editing model designed for designers and creative teams to make precise, reference-driven changes at scale. It emphasizes regional editing - draw a box, specify the change, and only that area is redrawn - alongside exact color matching by hex code, up to eight reference images for compositing, and preserved character consistency across edits. Outputs are native 2K, support common design tools (Figma, Photoshop, Blender, After Effects, Premiere, DaVinci, ChatGPT), and include 251 launch presets and voice-driven commands to apply edits as fast as a user speaks. Example workflows shown include re-skinning billboards, swapping products between images, converting illustrations to photos, combining portraits, and turning pixel art into stylized 3D renders.
The material positions Krea 3 as significantly faster, cheaper, and more precise than competitors: an illustrative benchmark claims single-edit playback of ~8 seconds and ~$0.06 per 2K edit versus Nano Banana Pro at ~26.8 s/$0.135 and GPT Image 2.5 at ~39.9 s/~$0.21, noting these are pre-generated times and approximate pricing. It highlights per-pixel precision metrics that minimize unintended changes, enterprise features such as custom brand models, SSO and IP indemnification, and a single workspace/billing option, targeting e-commerce, marketing, packaging, film, gaming, and photography production pipelines.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Sergey Brin states that Google's AI models are entering a phase of recursive self-improvement, where AI helps develop better AI systems. This process could accelerate AI development significantly within the next year, according to industry experts. (businessinsider.com)
A JavaScript tool called Handwired converts code into neural networks that run in browsers without GPU training. It enables real-time weight adjustments and complex tasks like search and rendering using neural network techniques. (chenglou.me)
Terence Tao discusses the allure of AI and large language models in advancing mathematics and science, comparing it to Borges's imagined Library of Babel containing all possible knowledge. He highlights how AI's potential to generate vast amounts of research could revolutionize scientific discovery, despite the challenges of sorting through misinformation. (terrytao.wordpress.com)
A new LSP daemon spec reduces token overhead in multi-turn AI agents by 70-82% through structural AST context pruning. This improves performance and efficiency in AI agent communication. (github.com)
Companies rushed to adopt AI technology, leading to increased errors, low-quality work, and security risks. Some firms, like Meta, are now pulling back on AI integration to address these issues and reduce costs. (theguardian.com)
Accenture has limited employee spending on the AI tool Claude to $29 per month, down from as much as $1,000. Employees must now find ways to fund additional usage if they exceed the cap, reflecting broader industry cost-cutting measures on AI tools. (404media.co)
Today's best Hacker News stories, summarized and screenshotted, one email a day.