Technology

code generation

2 synchronized stories carry this tag.

AlphaEvolve searches for better algorithms with executable feedback

Google DeepMind introduced AlphaEvolve, a Gemini-powered coding agent that evolves candidate programs and scores them with automated evaluators. Google reported production improvements in data-center scheduling, chip design and AI training, plus new solutions to mathematical optimization problems.

Why it matters: Executable evaluators can turn language-model generation into a measurable search process for algorithms, configurations and systems code.

Read storyOriginal source · deepmind.google

Figma previews Make for turning designs and prompts into interactive prototypes

Figma introduced Make, a prompt-to-app tool that could start from existing design frames, preserve structure, generate interactive behavior, incorporate data, and support direct code edits inside collaborative files.

Why it matters: Designers and product managers gained a shared route from static design to working prototype without rebuilding context in a separate coding environment.

Read storyOriginal source · figma.com