OpenAI Wants to Know if an AI Industry Slowdown Would Even Be Legal42m ago Oracle Posts Cloud Sales That Top Estimates on AI Demand1h ago iPhone 18 Pro Max vs Samsung Galaxy S26 Ultra: How these XL phones compete1h ago AWS open-sources Pizza Bot: email-style inbox for background AI agents1h ago ToolGrad: Efficient tool-use dataset generation with textual "gradients"1h ago CA governor signs 'landmark' laws on youth use of social media and AI chatbots1h ago OpenAI pulls out of Caltech math hackathon after mathematicians issue open letter criticizing AI math 'slop'1h ago OpenAI spent millions to solve this famous math problem — mathematicians are furious2h ago OpenAI asks Congress for mandatory national AI safety rules before it adjourns2h ago Anthropic Details Disrupted Claude Misuse Across Seven Harm Areas2h ago Meet Redis LangCache: A Managed Semantic Cache That Cuts LLM API Costs by Up to 90% and Returns Cache Hits Up to 15x Faster2h ago Reduce LLM latency with prefix-aware routing on Amazon SageMaker Inference2h ago NVIDIA Details BioNeMo Inference Runtime (BioIR): 2.90x Higher Boltz-2 Folding Throughput and 58.5K Residues per GPU-Hour on 8xH1002h ago Jensen Huang explains why Nvidia will grow an astounding 70% next year2h ago

OpenAI Wants to Know if an AI Industry Slowdown Would Even Be Legal42m ago Oracle Posts Cloud Sales That Top Estimates on AI Demand1h ago iPhone 18 Pro Max vs Samsung Galaxy S26 Ultra: How these XL phones compete1h ago AWS open-sources Pizza Bot: email-style inbox for background AI agents1h ago ToolGrad: Efficient tool-use dataset generation with textual "gradients"1h ago CA governor signs 'landmark' laws on youth use of social media and AI chatbots1h ago OpenAI pulls out of Caltech math hackathon after mathematicians issue open letter criticizing AI math 'slop'1h ago OpenAI spent millions to solve this famous math problem — mathematicians are furious2h ago OpenAI asks Congress for mandatory national AI safety rules before it adjourns2h ago Anthropic Details Disrupted Claude Misuse Across Seven Harm Areas2h ago Meet Redis LangCache: A Managed Semantic Cache That Cuts LLM API Costs by Up to 90% and Returns Cache Hits Up to 15x Faster2h ago Reduce LLM latency with prefix-aware routing on Amazon SageMaker Inference2h ago NVIDIA Details BioNeMo Inference Runtime (BioIR): 2.90x Higher Boltz-2 Folding Throughput and 58.5K Residues per GPU-Hour on 8xH1002h ago Jensen Huang explains why Nvidia will grow an astounding 70% next year2h ago

Machine Learning Dev3 min reading time

Are we measuring AI coding ability wrong?

Hacker NewsPublished 7 days ago

Current AI coding benchmarks rely on pass/fail metrics that overlook code quality aspects like readability, fragility, and maintainability. The author proposes five programmatic views—reliability, verbosity, complexity, specialization, and writing clarity—to better evaluate AI-generated code beyond simple scores.

#code-quality-evaluation #opus-5 #terminal-bench

More in Machine Learning

Machine Learning4 min read

Mistral wants open-weight AI to compete at the frontier. It just raised $3.5 billion to do it.

The New Stack (AI)5h ago

Machine Learning3 min read

OpenAI Releases GPT-6 Astra for Coding and Computer Use

InfoQ (AI, ML & Data)6h ago

Machine Learning4 min read

OpenAI’s Supposed Mathematical Breakthrough Devolves Into Explosive Drama as Mathematician Accuses It of Stealing His Work

Futurism5h ago