Beat GPT-4o at Python by searching with 100 dumb LLaMAs
Scale up smaller open models with search and evaluation to match frontier capabilities.
Best practices for serverless inferenceModal
8 Top Open-Source OCR Models Compared: A Complete GuideModal
Google Cloud Run functions pricing: understanding costs and optimizationModal
Fine-tuning a FLUX.1-dev style LoRAModal
Azure Functions pricing: Consumption vs. Flex ConsumptionModal
Glossary: LLM fine-tuning hyperparametersModal
Trained on 100,000+ Voices: Deepgram Unveils Next-Gen Speaker Diarization and Language DetectionDeepgram
Some Things You Oughta Know When Working with Viewport UnitsCss Tricks
Introducing DocChat: GPT-4 Level Conversational QA Trained In a Few Hours - CerebrasCerebras
Real-Time Computational Physics with Wafer-Scale Processing [updated]Cerebras
Accelerating GPT-5.6 Sol UltrafastCerebras
15 Best Submagic Alternatives & Competitors 2026Heygen
AGENTS.md outperforms skills in our agent evalsVercel
How to Use Voice to Control Music with Python and Deepgram - Deepgram Blog ⚡️Deepgram
Announcing Python Tooling ImprovementsPulumi
Improving Pulumi’s Docker ImagesPulumi
How sync. uses Modal to lipsync 100 hours of video a dayModal
Announcing: DuckDB code snippet sets with MotherDuck SharingMotherduck
Cerebras Systems and National Energy Technology Laboratory Set New Milestones for High-PerformanceCerebras
How we fine-tuned Llama2-70B to pass the US Medical License Exam in a weekCerebras
