Coding Ai

AI models can learn coding skills from subtle traces left by other models: New research shows that a coding-trained AI model leaves subtle traces of its learning even when using ordinary words. Another model can successfully learn from these traces and improve its own coding abilities without ever seeing the teacher model's actual code.

Artificial Intelligence • The Neuron

Sonnet 5.5 Is Here. Look What It Can Build.: Anthropic's Claude 3.5 Sonnet model demonstrates its coding capabilities by building several interactive web projects and games. The showcased projects include Crownfall, Bounce Lab, Marrow Manor, Splatburst, and Deadlock. The demonstration also compares these results against previous generations of the Sonnet model.

Technology • Matthew Berman

Anthropic launches Claude Sonnet 5.5 with 30% lower costs per task: Anthropic has launched Claude Sonnet 5.5, which generates output over 30 percent faster and costs up to 30 percent less per task than its predecessor. The model nearly matches Opus 5.5 on knowledge-work benchmarks and improved its score on the Terminal-Bench coding benchmark from 10.3 to 70.6 percent.

Anthropic • The Decoder

prompt engineering

Nine prompt rules cut GLM coding agent's wasted thinking by up to 70%

NaiveAI releases open-weights 309B parameter MoE model: NaiveAI has released Naive-N0.5-Flash under an MIT license. The 309-billion-parameter Mixture-of-Experts model features 15.5 billion active parameters and a native 1-million-token context window. Built on MiMo-V2.5 without full-attention layers, it is designed for coding and AI research.

AI Models • Pandaily