DeepSeek is a Chinese AI research laboratory that has developed highly capable open-source language models including DeepSeek-V3 and DeepSeek-R1, notable for their efficiency and performance.
DeepSeek released official macOS and Windows desktop apps for DeepSeek Harness v0.2, the MIT-licensed agent harness, adding a plugin manager, file and code-change review, and scheduled Automation Task…
A developer built RapidOS, an open-source WhatsApp claims assistant for insurers in the Democratic Republic of Congo, released under AGPL-3.0 and deployable with a single `docker compose up`. The syst…
A developer's analysis of CodeSmith v0.5.0 shows how a single drifting byte in an LLM system prompt — such as an embedded timestamp — invalidates automatic prefix caching for every token after the cha…
Google DeepMind introduced Gemini 4 Argon, a frontier model for long-horizon coding, enterprise knowledge work, and cyber defense that sets a state of the art of 77.9% on DeepSWE v1.1 and raises the o…
A developer released llm-api-adapter, an open-source Python library that provides a unified interface for function calling across 57 model IDs from nine LLM providers, including OpenAI, Anthropic, Goo…
A user on the Level1Techs forum reported running four AMD Radeon R9700 GPUs on an AM4 platform to requantize a DeepSeek model to MXFP4 and run it in the vLLM engine, with the first layer of a 48-layer…
Anthropic now lets developers modify Claude Code's behavior and appearance with TypeScript plugins installed via the /plugin command, an announcement that drew 19,861 likes and 4 million views on X. C…
DeepSeek released Harness 2.0, adding an official desktop app for macOS and Windows plus a web interface for Linux, with the Mac build at version 0.2.0 release candidate 2 at time of testing. The harn…
DeepSeek open sourced its Huawei Ascend programming stack, according to AI Stock Wire. The release covers DeepSeek's software stack for Huawei's Ascend AI accelerators, a move that matters as an alter…
DeepSeek released Harness Desktop v0.2, a GUI installer for its open-source coding agent Harness that removes the Node.js and terminal prerequisites previously required to run the CLI tool, which laun…
Nvidia researchers reported in the paper "Staying on Task: Testing the Foundations of Long-Horizon Agent Reliability" (arXiv:2609.38712, released September 30, 2026) that average model accuracy fell 6…
DeepSeek released Harness v0.2 on September 29, 2026, moving its open-source AI agent framework from a developer preview to a downloadable desktop app for macOS (Apple silicon and Intel) and Windows, …
SWE-sweep tested autonomous bug fixing by asking models to find and fix real bugs across 100 repositories with no ticket to guide them, and the best configuration fixed under 5% of bugs. The result in…
A developer reported that Claude Sonnet 5.5 generated two Rust functions for about $0.06 after DeepSeek V4.1 Flash produced hard-to-read code and a slight performance regression. The developer said So…
A message-intervention study of role-specialized QA pipelines found that faithful rationales passed from a reasoner to a verifier add almost no answer accuracy over no rationale, while corrupted ratio…
A developer built a benchmark using field data from 123 university students in Goa, India, covering 24 real institutional disputes across education, healthcare, justice and finance to test how frontie…
A developer released Grist, an open-source coding harness built on Opencode v2, which routes tasks across four tiers — easy, medium, hard and frontier — to cheaper models such as DeepSeek for simple w…
Proteus ran a DeepSeek Harness (DSH) rc.8 self-evolution experiment in which the harness added audio input, grounded transcription, and reusable verification across 30 logical Episodes, with 27 accept…
Adaption Labs published research on October 1, 2026 evaluating its Invent API against APIs from Anthropic, Google, OpenAI, DeepSeek, and Zai on synthetic dataset generation in a zero-data regime. The …
A firm rented four Nvidia H200 GPUs to test DeepSeek's claim that its model runs 80 times cheaper, according to the article's headline. The source body contains no further reporting, figures, or named…