A developer benchmarked four Chinese LLM families—DeepSeek, Qwen, Kimi, and GLM—over 30 days using 1,247 prompts across code generation, reasoning, Chinese language, English chat, and vision tasks. De…
A backend engineer at an unnamed company slashed their team's LLM API costs from $11,400 to $1,830 per month by switching to cheaper models for most tasks and implementing tiered routing. The team rep…
A developer cut their company's AI API bill by 95% from $11,000 to under $400 per month by implementing per-request model routing and tiered escalation. The team replaced expensive GPT-4o calls with c…
New research from arXiv reveals that larger language models consistently outperform smaller ones on reasoning benchmarks by an average of 6-7%, with the key advantage being constraint-guided reasoning…
UC San Diego researchers developed DFlash, a speculative decoding method that uses a lightweight block diffusion model to draft entire token blocks in parallel, achieving up to 6.08x speedup on Qwen3-…
Researchers at SPAR argue that language models can report on their own internal activations, a method called self-report, which is underexploited compared to external analysis tools. They test five op…
Researchers introduced JetSpec, a speculative decoding method that trains a causal parallel draft head on a frozen target model to draft entire speculative trees in one pass while preserving autoregre…
JetSpec, a new speculative decoding method, trains a causal parallel draft head over fused hidden states from a frozen target model, enabling lossless verification of candidate trees in one forward pa…
Researchers trained Qwen3-8B natural language autoencoders with varying length penalties and found that explanation length can be significantly reduced without harming reconstruction fidelity, suggest…
Anthropic developed a method to read a model's internal state as plain English. Groq's founder argued that cheaper AI only increases compute demand. GLM-5.2 released an MIT-licensed model with near-fr…
Researchers introduced PragReST, a self-supervised framework that uses counterfactual reasoning to improve large language models' pragmatic language understanding. Across four benchmarks, PragReST boo…
Researchers introduced Regressive Plasticity Schedule (RPS), a two-stage post-training schedule that couples a learning-rate drop with a curriculum boundary between easier and harder data. Testing on …
Amazon Web Services announced container image caching for Amazon SageMaker AI inference, reducing end-to-end latency by up to 2x for generative AI models during scale-out events by eliminating contain…
Researchers propose ASAG, a training-free method that monitors attention distributions to detect when a reasoning model has reached a conclusion, stopping generation early. Applied to DeepSeek-R1-Dist…
Researchers introduced PERIA, a tool-augmented visual agent designed to improve spatial reasoning in vision-language models by actively acquiring evidence and performing multi-step visual interactions…
A team of developers has built an AI-powered job search tool that uses a fine-tuned Qwen3-8B language model to generate LinkedIn queries, scrape job postings, and score each role against a candidate's…
A developer cut their AI API bill from $420 to $28 per month — a 93% reduction — by routing simple tasks to cheaper models like DeepSeek V4 Flash and Qwen3-8B instead of GPT-4o. The engineer built a t…
NVIDIA released Nemotron-Labs-Diffusion, a tri-mode language model that unifies autoregressive, diffusion, and self-speculation decoding within a single architecture. The model, trained with a joint A…
The provided text contains a Python script for a "white-box LLM jailbreak" technique that uses weight orthogonalization. The script loads harmful and harmless instruction datasets, extracts hidden sta…