Feed aggregator

Article URL: https://gist.github.com/kevindurb/763ae5bdace325f9dc384c643f7d5d9d

Comments URL: https://news.ycombinator.com/item?id=47152243

Points: 1

# Comments: 1

Article URL: https://www.williamyaoh.com/posts/2020-05-03-permissiveness-solutions.html

Comments URL: https://news.ycombinator.com/item?id=47152220

Points: 1

# Comments: 0

Hey guys,

I wanted to share a small project I've been working on to solve a personal pain point: TinyTTS.

We all love our massive 70B+ LLMs, but when building local voice assistants, running a heavy TTS framework alongside them often eats up way too much precious VRAM and compute. I wanted something absurdly small and fast that "just works" locally.

TL;DR Specs:

Size: ~9 Million parameters

Disk footprint: ~20 MB checkpoint (G.pth)

Speed (CPU): ~0.45s to generate 3.7s of audio (~8x faster than real-time)

Speed (GPU - RTX 4060): ~0.056s (~67x faster than real-time)

Peak VRAM: ~126 MB

License: Apache 2.0 (Open Weights)

Why TinyTTS? It is designed specifically for edge devices, CPU-only setups, or situations where your GPU is entirely occupied by your LLM. It's fully self-contained, meaning you don't need to run a complex pipeline of multiple models just to get audio out.

How to use it? I made sure it’s completely plug-and-play with a simple Python API. Even better, on your first run, it will automatically download the tiny 20MB model from Hugging Face into your cache for you.

pip install git+https://github.com/tronghieuit/tiny-tts.git

Python API:

from tiny_tts import TinyTTS

# Auto-detects device (CPU/CUDA) and downloads the 20MB checkpoint

tts = TinyTTS()

tts.speak("The weather is nice today, and I feel very relaxed.", output_path="output.wav")

CLI:

tiny-tts --text "Local AI is the future" --device cpu

Links:

GitHub: https://github.com/tronghieuit/tiny-tts

Gradio Web Demo: Try it on HF Spaces here

Hugging Face Model: backtracking/tiny-tts

What's next? I plan to clean up and publish the training code soon so the community can fine-tune it easily. I am also looking into adding ultra-lightweight zero-shot voice cloning.

Would love to hear your feedback or see if anyone manages to run this on a literal potato! Let me know what you think.

If you find this project helpful, please give it a on GitHub.

Comments URL: https://news.ycombinator.com/item?id=47152213

Points: 1

# Comments: 0

AI coding agents break when the context window fills up — they lose state, hallucinate, or auto-compact shreds the context you built up.

I built a 3-hook pipeline that rotates before that happens, with a dry-run replay you can run locally (no LLM/API keys).

Quick demo: - https://github.com/Vinix24/vnx-orchestration/tree/master/dem...

How it works:

┌─────────────────┐ │ PreToolUse hook │── checks context % every tool call │ (≥65% → block) │ └────────┬────────┘ ▼ ┌─────────────────┐ │ Agent writes │── structured ROTATION-HANDOVER.md │ handover file │ (task state, files, progress, next steps) └────────┬────────┘ ▼ ┌─────────────────┐ │ PostToolUse │── detects handover → atomic lock │ launches rotator│ → vnx_rotate.sh (nohup, detached) └────────┬────────┘ ▼ ┌─────────────────┐ │ Rotator │── /clear via tmux → waits for SessionStart │ injects resume │ → pastes continuation prompt └─────────────────┘ Why 65%? It’s ~15 points before auto-compact (~80%), so there’s enough headroom to write a clean handover without racing compaction.

I analyzed 5 projects attempting similar fixes — none have a full detect → handover → clear → resume → verify loop.

Repo: https://github.com/Vinix24/vnx-orchestration Docs: https://github.com/Vinix24/vnx-orchestration/blob/master/doc...

Comments URL: https://news.ycombinator.com/item?id=47152204

Points: 1

# Comments: 0

Article URL: https://words.benhutton.me/2026-02-25-speaking-like-a-pirate-is-against-microsoft-ai-content-policy

Comments URL: https://news.ycombinator.com/item?id=47152193

Points: 1

# Comments: 0

Article URL: https://blog.bensontech.dev/posts/How-ai-will-change-mobile-development/

Comments URL: https://news.ycombinator.com/item?id=47152185

Points: 3

# Comments: 0

Alisa Viejo, CA, United States, 25th February 2026, CyberNewswire

The post One Identity Appoints Michael Henricks as Chief Financial and Operating Officer appeared first on The Security Ledger with Paul F. Roberts.

Whether you want a video doorbell to keep track of packages or visitors, these popular models from Ring, Blink and more will get the job done.

Adobe Firefly's Quick Cut tool clips and combines all your raw footage into a video in under two minutes.

The company's new eSIM option should allow for a faster sign-up experience.

Yes, you should absolutely marathon them.

Article URL: https://techcrunch.com/2026/02/24/spanish-soonicorn-multiverse-computing-releases-free-compressed-ai-model/

Comments URL: https://news.ycombinator.com/item?id=47151469

Points: 1

# Comments: 0

Article URL: https://builders.perk.com/gleam-is-boring-so-i-went-to-a-conference-about-it-8f08a52c3de3

Comments URL: https://news.ycombinator.com/item?id=47151461

Points: 2

# Comments: 0

Article URL: https://magazine.sebastianraschka.com/p/a-dream-of-spring-for-open-weight

Comments URL: https://news.ycombinator.com/item?id=47151455

Points: 1

# Comments: 0

I'm CTO at a startup, tired of maintaining five separate tools for our web presence while shipping software with Claude Code every day. So I built seite — a Rust SSG where the AI agent has a proper MCP interface to your site, not just file access.

seite mcp runs a Model Context Protocol server that exposes resources (docs, config, content, themes) and tools (build, create, search, apply theme) to any MCP-compatible agent. seite init also scaffolds a CLAUDE.md context file so the agent knows your schemas and conventions before it writes anything.

Everything else you'd expect: six bundled themes, collection presets for blog/docs/changelog/roadmap, one-command deploy to GitHub Pages/Cloudflare/Netlify, llms.txt and llms-full.txt on every build. Single binary, no runtime, sub-second builds. 331 tests.

MIT licensed, v0.1.6. Early but iterating fast — we're using it on our own startup's site so the feedback loop is tight.

curl -fsSL https://seite.sh/install.sh | sh Site: https://seite.sh Repo: https://github.com/seite-sh/seite

Comments URL: https://news.ycombinator.com/item?id=47151427

Points: 1

# Comments: 0

Article URL: https://www.nytimes.com/2026/02/19/well/mitochondria-longevity-health.html

Comments URL: https://news.ycombinator.com/item?id=47151414

Points: 2

# Comments: 1

Article URL: https://alexzhang13.github.io/blog/2026/scaffold/

Comments URL: https://news.ycombinator.com/item?id=47151409

Points: 1

# Comments: 0

Article URL: https://github.com/francescoalemanno/raijin-mono

Comments URL: https://news.ycombinator.com/item?id=47151406

Points: 1

# Comments: 0

Zeroclaw is a Rust-based Nostr client/relay tool. As of a few hours ago, no one had compiled it natively on Android.

Gemini CLI tried. Gemini Android tried. Both failed.

The blockers: — koffi's build script passes `make -j` bare, which Termux's make rejects — The default linker OOM-kills during the final link step (Android blocks swapon for unprivileged processes)

The fix: mold linker + codegen-units=1 + lto=thin + opt-level=z in a .cargo/config.toml

Binary: 15.5MB. Build time: 23m 55s. Kernel: Linux 5.4.284-moto. Completed at 04:11:47 CST.

Repo with binary, build config, and full reproduction steps: https://github.com/BleakNarratives/zeroclaw-android

Comments URL: https://news.ycombinator.com/item?id=47151385

Points: 1

# Comments: 0

Article URL: https://phys.org/news/2026-02-electrical-magnetism-2d-materials-advance.html

Comments URL: https://news.ycombinator.com/item?id=47151384

Points: 1

# Comments: 0