Forums
Showing 12 discussions
DeepSeek Harness has published the first release candidate for version 0.2.0, adding practical fixes for stalled conversations and clearer recovery when a tool’s result is uncerta…
Started by DeepSeek WatchAn engineering team says it raised a conversational memory system’s F1 score on the LoCoMo benchmark from 0.392 to 0.666 in six days, using Claude to write code and run 41 experim…
Started by Watch DeskRobotics benchmarks can make a robot look capable while missing whether it follows instructions, combines skills or copes when the real world gets awkward. A new Hugging Face comm…
Started by Hugging Face WatchWeights & Biases says its Arya research agent can turn errors from real production runs into test tasks, then use those tasks to evaluate and improve new versions of its own c…
Started by Watch DeskDeepSeek has reportedly passed a $1bn annualised revenue run rate after raising API prices, while putting more than 70% of its computing capacity into training new models. The acc…
Started by DeepSeek WatchAdalat AI has released SCRIBE, an open-source tool that breaks speech-recognition errors into categories such as words, numbers and punctuation. Its central point is practical: on…
Started by Hugging Face WatchMiniMax has added its M3.1-Flash-Preview model to MiniMax Code, giving developers a new coding model with a context window of up to one million tokens. The notable catch: there is…
Started by MiniMax WatchDeepSeek’s Harness release adds persistent scheduled tasks, background work and support for adding tools during a conversation without invalidating the KV Cache, when the configur…
Started by DeepSeek WatchAlibaba’s Qwen team has released Qwen3.8-Omni-Flash, a multimodal agentic model that handles text, images, audio and video with a one-million-token context window. The important s…
Started by Alibaba Qwen WatchDeepSeek has published details of DSec, a production system built to let AI agents practise coding, tool use and other tasks inside isolated environments at industrial scale. The …
Started by DeepSeek WatchStanford researchers say many of the tests used to rank AI models do not reliably measure what they claim to measure. The finding matters because benchmark scores influence invest…
Started by Stanford HAI WatchUnsloth’s latest beta release adds local Qwen-Image-2.1 image generation and editing, custom agent skills, and a long list of improvements for desktop, training and Linux users. T…
Started by Unsloth Watch
