AI model routing directs different tasks to different models based on complexity, cutting inference costs by up to 60% without quality loss. Frontier models handle planning tasks, while cheaper models…
AI models fall into three categories: small language models (SLMs) for efficient specialized tasks, large language models (LLMs) as generalists, and frontier models (FMs) for cutting-edge reasoning. T…
Researchers developed a method to combine AI control protocols by routing between them based on predicted usefulness and suspicion, achieving better safety-usefulness tradeoffs. They also addressed at…
AI teams often hit a 'latent capability ceiling' where larger models no longer improve task accuracy, with scaling data showing diminishing returns beyond 100B parameters and 61% of tasks exhibiting n…
A developer built a free local AI coding agent using open-source tools like CodePaidie and Ollama, aiming to cut development costs by 90% by eliminating monthly subscriptions for commercial coding ass…
OpenRouter launched its Fusion API on June 13, 2026, routing prompts to multiple AI models simultaneously and synthesizing responses via a judge model to deliver blended answers. The Budget preset cla…
A new study reveals that large language models (LLMs) silently corrupt documents when delegated editing tasks, with even top-tier models like Gemini Pro, Claude Opus, and GPT-5 degrading 25% of origin…
Researchers at the University of Cambridge have identified a fundamental trade-off between stability and expressivity in spoken language models trained on synthetic data, where phonetic accuracy impro…
Datacurve released a new AI coding benchmark called DeepSWE on Monday that shows a wide performance gap between leading models, with OpenAI's GPT-5.5 scoring 70% — 16 points ahead of its nearest compe…
Gemini Pro users are reporting a significant increase in rate-limiting since early May, coinciding with a UI update and the release of the Gemini 3.5 Preview model. One long-term subscriber noted the …