DEEPSEEK
28 items
25 posts, 3 tools
llama-modchip claims DeepSeek-V4-Flash 284B fits in 64GB of RAM with no GPU. What the repo says, vendor-reported speeds, what Hacker News could not reproduce, and when a hosted model wins.
DeepSeek open-sourced dsh-superagent, an always-on coding agent built on a router and worker split. What the design says, what the code ships, and the safety debate.
DeepSeek open-sourced DeepInfer, the inference engine behind its API. It is offline-only, V4.1-Flash-only and Blackwell-or-Ascend-only. What it is, what is missing, and who benefits.
DHS ordered DeepSeek products removed from US civilian agency IT. The scope reaches third-party products built on DeepSeek implementations - here is what that means for builders.
DeepSeek V4.1-Flash-1017 jumps 11 points on Terminal-Bench 4.0 at the same deepseek-flash price. Benchmarks vs Opus 5, K3, GLM-5.3 and when to switch.
DeepSeek 4.1 Flash as a daily coding model: what a session costs, how peak hours double the bill, why caching matters, and where the subsidy argument holds.
DeepSeek V4.1 Flash replaced V4 Flash. Official API: $0.15 input, $0.60 output off-peak. OpenRouter hosts start near $0.05. MIT weights are on Hugging Face.
DeepSeek V4 Flash Vision Exp guide: supported image formats, three input methods, the 384-token per-image cap, and how to run it in OpenCode today.
DeepSeek V4 Flash via Novita on Vercel AI Gateway was 90% off for Pro customers through August 11. The before/after cost math and the provider-pinning setup.
Claude Haiku 5.5 and GPT-6 Luna both list at $0.10/$0.50 per MTok. The price tie breaks at Haiku's 100K cliff, and Anthropic's benchmarks favor Haiku. Checked Oct 8, 2026.
DeepSeek V4 Flash 0731 was re-post-trained for agent work. Its benchmark numbers, native Responses API and Codex support, and how to wire it up today.
DeepSeek V4 Flash 0731 is the official V4 Flash API release, re-post-trained to beat V4-Pro-Preview on agent benchmarks. How to run it in OpenCode today.
DeepSeek paused its fundraising after a leaked investor transcript exposed its compute gap with US labs. What Liang Wenfeng said and how HN read it.
Cheap subagents like DeepSeek, Kimi and GLM suit drafts and exploration only when their output is visible. A shared canvas makes that work reviewable.
DeepSeek V4 economics for agentic coding: worked cost math, the Flash vs Pro split, and when to route coding work to DeepSeek instead of a frontier model.
GLM-5.2 vs DeepSeek V4 vs Qwen3 vs Kimi K3: open-weights coding models compared on benchmarks, pricing, context windows, self-host footprint and best picks.
deepseek-chat is retired after July 24, 2026. Migrate to DeepSeek V4, now served as deepseek-flash, with a what-maps-to-what table and a step-by-step checklist.
GPT-5.4 vs Gemini 3.1 Pro vs DeepSeek V4: pricing, benchmarks, context behavior, and license terms for the mid-tier models that carry most production traffic.
DeepSeek's open-weights frontier family, previewed April 24, 2026. V4-Pro is 1.6T total / 49B active params; V4-Flash is 284B / 13B. 1M context standard. Weights on Hugging Face.
Fable 5 vs DeepSeek V4 on cost and quality: a 178x output price gap, a real quality difference, and the task split most production teams end up running.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.