Codewhale
dive into the deep so you don't have to.
Open-source terminal coding agent that reads and edits code, runs commands and checks, and lets users select hosted or local model providers.
Recent stories
OpenCode removed two low-traffic routing configurations after finding overactive upstream content filters. Its benchmarks did not explain broader quality complaints, and its GPU cluster still faces stability and capacity limits.
DeepSeek releases DeepInfer under Apache 2.0 for V4.1 Flash on Blackwell or Ascend hardware. The engine exposes techniques such as speculative decoding but omits some serving components.
Developers report using Jev to score inbox content, classify invoices, and split documents into categories. DocJev’s author claims 6x lower latency than GPT-5.6 Luna at equivalent accuracy for document classification and splitting.
DeepSeek V4.1 Flash leads Vals and Artificial Analysis open-weight comparisons, according to the evaluators. Its encoder-decoder design shares compressed KV state across decoder layers to reduce serving costs.
DeepSeek released V4.1 Flash, a 552B-parameter multimodal MoE model with 8B input and 16B output active parameters. It supports up to 1 million tokens of context, while an independent BridgeBench run used 23.5 million tokens on one task.
Magic says a new pretraining recipe matched DeepSeek V4 Pro with roughly 50 times less compute. After a 10x scale-up costing about $4 million, the company says it exceeded publicly available base models.
OpenCode revised its Go plan to include $30 in usage for a $10 subscription. The change follows a provider price increase and the company’s effort to secure lower-cost capacity.
OpenCode says it revised Go limits after DeepSeek raised prices. Its operator is testing hosting configurations intended to bring DeepSeek service closer to its prior price point.