3Sophons
Re:I Met Cixin Liu on Three Body day today. New movie is coming
on Sunday October 25, 2026 @11:07AM (#50232347)
yes. a movie nothing to do with netflix. Not any english translation for the Three Body Day event
Re:I Met Cixin Liu on Three Body day today. New movie is coming
on Sunday October 25, 2026 @11:06AM (#50232326)
sorry i meant oct 24
Re:I Met Cixin Liu on Three Body day today. New movie is coming
on Saturday October 24, 2026 @02:10PM (#50223683)
excited so I wrote an article staying up late! today Oct 10 2026 is the first time I met Big Liu in person. Also excited about the new movie Zhang Yimou is good. For more photos i took you can DM me
Re:Qwen 3.8 27B is excellent, but it defaults to overthinking things
on Monday August 17, 2026 @08:32AM (#49329811)
powerful enough models are becoming a reality on personal hardware. Olares is an open-source personal AI cloud OS, supporting local AI, Ollama, Open WebUI, Hermes etc
Re:Self hosted email continues to steeply decline
on Monday August 17, 2026 @08:07AM (#49329559)
powerful enough models are becoming a reality on personal hardware. Olares is an open-source personal AI cloud OS, supporting local AI, Ollama, Open WebUI, Hermes etc
Re:How do I permanently disable Google Photos pop-up prompt to backup ...
on Monday August 17, 2026 @08:06AM (#49329542)
Here is a open source OS to allow you to self host immich with 1 click https://www.olares.com/docs/use-cases/immich
Re:Ask HN: Is there any AI OS that has local AI and all are integrated...
on Friday July 24, 2026 @08:56AM (#49034905)
Not so sure about the shadowban policy so i won't paste the github link but you can search Olares. It is an AI OS for one click AI deployment and more.
try if out if you wanted AI woven into the OS itself: the model runs on your machine, your files and chats never leave your walls, and the agent layer talks to the system natively instead of through a browser tab.
Re:Ask HN: AI Agent and harness containerization/security recommendations
on Wednesday July 15, 2026 @01:19AM (#48916564)
isolated container per run, no mounted secrets, vault at runtime, egress off. Open Source Olares (biased) runs agents as isolated workloads on your own hardware.
Re:Can I Run AI locally?
on Friday March 13, 2026 @08:23PM (#47371883)
a lighter-weight alternative of docker and python is the Rust+Wasm stack https://github.com/LlamaEdge/LlamaEdge
Running a full voice stack (ASR –> LLM –> TTS) locally with Docker
Re:Running a full voice stack (ASR –> LLM –> TTS) locally with Docker
on Thursday December 18, 2025 @09:25AM (#46313045)
covers how to wire up the components to run a real-time voice agent that you can actually talk to via an ESP32 client, keeping the heavy lifting on your local machine.
Re:So – – – Is AI a Bubble?
on Tuesday December 09, 2025 @07:59AM (#46204470)
huh
So – – – Is AI a Bubble?
Re:
on Friday November 28, 2025 @07:03AM (#46077910)
This post summarizes WasmEdge's recent talks at OSSummit Korea and KubeCon NA 2025, focusing on its new role as a premier AI runtime. Key technical highlights include expanded multi-GPU support (NVIDIA, AMD, Apple), multi-backend inference (TensorRT, OpenVINO), and the use of Embedded Rust/Wasm for building real-time voice AI agents (EchoKit project).
Re:
on Thursday November 20, 2025 @12:50PM (#45995439)
customize both hardware and software. Their voice cloning lets you recreate your own voice for truly personal AI experiences.
Re:
on Monday October 27, 2025 @08:04AM (#45720019)
Voice is the next frontier of conversational AI. It is the most natural modality for people to chat and interact with another intelligent being.
Re:LLMs Can Get "Brain Rot"
on Friday October 24, 2025 @12:37AM (#45690821)
why they don't prompt ai to avoid using dashes. and bullet points etc
Show HN: EchoKit – An open-source, ESP32-based AI voice agent with a Rust server
https://www.instructables.com/Create-Your-Own-AI-Voice-Agent-Using-EchoKit-ESP32/
Have you wanted a voice AI agent that you could fully control, customize, and understand from the ground up—not just a black box.EchoKit is a DIY, open-source voice agent running on an ESP32-S3. The fun part is the server backend, which I wrote entirely in Rust to handle the AI pipeline (ASR, LLM, TTS).The stack is:Hardware: EchoKit board (ESP32-S3)Firmware: ESP-IDFServer: Rust (Actix...
Re:
on Friday October 17, 2025 @07:02AM (#45615282)
The talk explores the idea that while human-centric languages like Python are popular for their ease of use, they are suboptimal for AI-driven development. Rust, with its strict compiler and strong type system, provides an excellent reward function and a tight feedback loop for LLMs, forcing them to generate correct, efficient code. This could make Rust the de facto language in a future where most code is written by AI. The video demonstrates this with a voice AI agent built with Echokit and Rust. the orignal tak is there https://www.youtube.com/watch?v=bbq0b_FpYEY
Re:
on Thursday October 16, 2025 @04:59AM (#45603035)
made the anime with Veo 3
Re:
on Monday September 08, 2025 @10:42AM (#45168934)
We Built an Open-Source Voice AI Kit (Hardware + AI Server + Docs) for Education & Tinkering
Show HN: Videolangua – end-to-end video translate and subtitle/ dub
What it is A practical pipeline to go from video → transcripts → bilingual subtitles (A/B at once) or voice dub (choose female or male). It targets lectures, tutorials, tech talks etcCurrent constraints (honest version)No speaker diarization yet → one TTS voice for the entire videoVoice choice: female / maleBilingual subtitles (e.g., EN+JP, EN+ZH, EN+KR) with length-aware line breakingYou can...
Show HN: EchoKit –Fully Open Source AI Voice Agent Hardware and Server
It is powered by Rust most “open” AI devices are actually closed on the backend, limiting customization and privacy. EchoKit is fully open—from ESP32-S3 hardware to the Rust-based server. You can customize ASR, TTS (including voice cloning), LLM prompts, and even add your own MCP actions. We’d love your feedback, ideas, and contributions. Try it out, check the code, and let us know what you think!
Re:
on Tuesday June 03, 2025 @11:37AM (#44171183)
Edge LLM Osmosis-Structure-0.6B for structured data
Re:
on Friday May 16, 2025 @12:20PM (#44007242)
Here is the tutorial link for Llama4 https://www.secondstate.io/articles/llama-4/
Re:
on Friday April 04, 2025 @07:02AM (#43580506)
1⃣ Virtual Filesystem Security for Plugins
Secure WASM sandboxes by enforcing WASI APIs in plugins like WASI-NN. Prevent host filesystem bypasses while maintaining performance. Skills: C++, WebAssembly 13
2⃣ Port WasmEdge to IBM s390x Bring AI/LLM inference to mainframes! Adapt the runtime and WASI-NN ggml backend for s390x, enabling enterprise-grade hybrid cloud deployments. Skills: C++, s390x, LLVM 13
3⃣ Cloud Testing with Kubernetes & Runwasi Validate WasmEdge in multi-node K8s clusters. Design workflows for scalable AI inference and edge services. Skills: Rust, C++, GitHub CI
Re:
on Monday March 31, 2025 @02:49AM (#43531946)
LlamaEdge supports multimodal GenAI besides LLMs: https://llamaedge.com/docs/user-guide/
Monetize to your QwQ on Gaia: https://github.com/GaiaNet-AI/node-configs/tree/main/qwq-32b
Video demo: https://youtu.be/QuHr7xLYzQU
LlamaEdge on GitHub: https://github.com/LlamaEdge/LlamaEdge
Gaia on GitHub: https://github.com/GaiaNet-AI/gaianet-node
WasmEdge on GitHub: https://github.com/WasmEdge/WasmEdge
Re:
on Wednesday February 05, 2025 @07:47AM (#42947763)
Full OpenAI-compatible API
Rust + Wasm = pure effortless deployment