deepseek
18 stories and discussions about deepseek, aggregated from every source we track.
A foundation model for mobile, wearables, robots, smart home, automotive and microcontrollers. One 8-29 MB binary that beats models 10x its size on mobile tool calls and matches 2-3x bigger models on extraction.
Parity’s engineers tested open-weight AI models through a self-managed inference stack. Over one month, 25 engineers generated nearly 13 billion tokens. Here’s what they learned.
Raycaster's Biopharma Bench V0.1: 71 professional assignments across 12 private biopharma company environments. We evaluate whether frontier agents can navigate contradictory records, identify controlling…
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm - antirez/ds4
In the Stage 2 report we shipped 20 feature tickets on Fizzy and promised to explore benchmarking the agents all on max-effort. Now we have run it: every model on the board, same tickets, reasoning turned all the way…
Self-taught R&D: shared L1 KV for prefix-heavy streaming chat. Problem, approaches tried, results, cost, and lessons in one page.
deepseek-v4-flash from DeepSeek's API vs through OpenRouter (Cloudflare, Together and DigitalOcean), measured daily from 6 cities: direct 698 ms, routes 721 ms to 774 ms.
OpenAI- and Anthropic-compatible inference for coding agents. Call DeepSeek-V4.1-Flash and DeepSeek-V4-Flash with zero data retention.
DeepSeek Flash agent teams for Codex: your model plans and supervises, the swarm does the work - Druidia-Bot/DotSwarm