Developer Shares ~200-Line Pure JAX Implementation of DeepSeek V3
A developer posted a minimal implementation of DeepSeek V3 on Hacker News, written in about 200 lines of pure JAX. The code is presented as a compact educational example rather than a full production deployment.
Coverage timeline
Hacker NewsVaibhaavTiwari
Related stories
DeepSeek opens full-suite app APIs with web search, files, voice, OCR, ASR, TTS
DeepSeek announced the release of a full-suite API covering the capabilities of its consumer app, including web search, deep-thinking search, file input, link reading, safety, voice, OCR, ASR, and TTS. These features are available as standalone interfaces or built-in tools, with V4.1-Flash (deepseek-flash) supporting them across Messages, Responses, and Chat Completions, with server-side tool calls and context assembly. DeepSeek also open-sourced a lightweight chat frontend demo that supports importing conversation history, enabling developers to replicate the full app experience.
2 reports · 2 sources
Five inference providers now support abliterated DeepSeek
A Hacker News post notes that there are now five inference providers offering support for abliterated versions of DeepSeek, indicating growing ecosystem adoption of this model modification. The post highlights the availability of these providers as a notable development for users interested in using abliterated DeepSeek models.
1 reports · 1 sources98 points · 120 comments
DeepSeek open-sources Super-agent architecture for autonomous bug-fixing agents
DeepSeek has publicly released the architectural blueprint for its Super-agent, a research prototype of a personal agent that maintains cross-session context to handle multi-task coordination. Internal tests show the agent can autonomously identify bugs and submit pull requests without being explicitly prompted, with a median task completion time of 12.4 minutes in simulated multi-task environments. DeepSeek positions this as a step toward reducing human attention bottlenecks in multi-task workflows.
3 reports · 3 sources
Llama-modchip runs 284B DeepSeek model on 64GB RAM without GPU
A project called Llama-modchip demonstrates running a 284B-parameter DeepSeek model on a system with 64GB RAM and no GPU, using a modchip-like approach. The technique was discussed on Hacker News, highlighting a potential path for large-model inference on memory-constrained hardware.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe