Feed aggregator

Article URL: https://www.engadget.com/ai/the-supreme-court-doesnt-care-if-you-want-to-copyright-your-ai-generated-art-171849407.html

Comments URL: https://news.ycombinator.com/item?id=47241239

Points: 2

# Comments: 0

Article URL: https://developer.chrome.com/blog/chrome-two-week-release

Comments URL: https://news.ycombinator.com/item?id=47241222

Points: 1

# Comments: 0

Article URL: https://www.nbcnews.com/health/health-news/chatgpt-health-under-triaged-half-medical-emergencies-rcna261409

Comments URL: https://news.ycombinator.com/item?id=47241206

Points: 1

# Comments: 0

Amazon's audiobook service is adding a lower-cost plan that gives subscribers limited listening without monthly credits.

The strikes in Bahrain and the UAE caused structural damage, disrupted power delivery and, in some cases, sparked fires and caused water damage.

Article URL: https://www.assemblyai.com/universal-3-pro-streaming

Comments URL: https://news.ycombinator.com/item?id=47241167

Points: 1

# Comments: 0

I'm an 18-year-old CS student from Turkey. I've been building Dracula, a Python wrapper for the Google Gemini API. I initially built it because I wanted a simpler Mini SDK that handled conversational memory, function calling, and streaming out of the box without the boilerplate of the official SDK.

Recently, I got some well-deserved technical criticism from early users: using JSON files to store chat history was a memory-bloat disaster waiting to happen; forcing a PyQt6 dependency on server-side bots was a terrible design choice; and lacking a retry mechanism meant random 503s from Google crashed the whole app.

So, I went back to the drawing board and completely rewrote the core architecture for v0.8.0. Here is what I changed to make it production-ready:

Swapped JSON for SQLite: I implemented a local database system (using sqlite3 for sync and aiosqlite for async). It now handles massive chat histories without eating RAM, and tracks usage stats safely.

True Async Streaming: Fixed a generator bug that was blocking the asyncio event loop. Streaming now yields chunks natively in real-time.

Exponential Backoff: Added an under-the-hood auto-retry mechanism that gracefully handles 429 rate limits and 503/502 server drops.

Zero Bloat: Split the dependencies. "pip install dracula-ai" installs just the core for FastAPI/Discord bots. "pip install dracula-ai[ui]" brings in the desktop interface.

Here is a quick example of the async streaming:

import os, asyncio from dracula import AsyncDracula

async def main(): async with AsyncDracula(api_key=os.getenv("GEMINI_API_KEY")) as ai: async for chunk in ai.stream("Explain quantum computing"): print(chunk, end="", flush=True)

asyncio.run(main())

Building this has been a huge learning curve for me regarding database migrations, event loops, and package management. I would love for the HN community to look at the code, review the async architecture, and tell me what I did wrong (or right!).

GitHub: https://github.com/suleymanibis0/dracula PyPI: https://pypi.org/project/dracula-ai/

Thanks for reading!

Comments URL: https://news.ycombinator.com/item?id=47241149

Points: 1

# Comments: 0

Article URL: https://github.com/AionSystem/AION-BRAIN/tree/main/projects/sovereign-trace

Comments URL: https://news.ycombinator.com/item?id=47241129

Points: 1

# Comments: 0

Article URL: https://www.euronews.com/next/2026/03/02/cancel-chatgpt-ai-boycott-surges-after-openai-pentagon-military-deal

Comments URL: https://news.ycombinator.com/item?id=47241092

Points: 11

# Comments: 0

Demarkus started as a simple project: what if the web was just markdown? No HTML, no JavaScript, no ads, no tracking;just structured text over encrypted transport. A protocol for durable knowledge, not attention capture.

I built the Mark Protocol on QUIC (UDP, TLS 1.3 built-in) with a small verb set: FETCH, LIST, VERSIONS, PUBLISH, APPEND, ARCHIVE serving markdown with YAML frontmatter. Human-readable status strings instead of numeric codes. Capability-based auth (tokens grant permissions, not identities). Every write creates a new immutable version with SHA-256 hash chain verification.

But the use case that surprised me is what I'm calling the "demarkus-soul" pattern.

The problem: Every AI coding agent session starts from zero. The agent has no memory of your project's architecture, past debugging sessions, or decisions you've made together. The solutions out there tie you to a specific agent vendor. Switch agents? Your project knowledge stays behind.

The solution: Run a small demarkus server for your project. Your AI agent connects via MCP (Model Context Protocol) and gets tools to read and write markdown documents; architecture notes, debugging lessons, code patterns, a journal. All versioned, all persistent across sessions, all stored as plain markdown files on your machine.

I've been using this while developing demarkus itself. The agent's "soul" runs on a Orange Pi on my desk. Each session, the agent reads what past sessions left behind, adds to it, and the next session finds it there. The agent even journals and reflects on its own work. It's self-documenting the history of your project, "the soul of your project".

Key properties:

- No vendor lock-in. Any agent that supports MCP can connect: Claude, Codex, whatever comes next. The memory is yours, plain markdown on your hardware.

- Versioned and immutable. Full audit trail. You can see exactly what the agent knew and when.

- Zero impedance mismatch. Agents already think in markdown. No translation layer between what the protocol delivers and what the agent processes.

- Runs anywhere. The server is a single Go binary. No databases, no CMS, no background services. A Raspberry Pi or Orange Pi is plenty.

The whole stack is open source. AGPL for the implementation, CC0 for the protocol spec (anyone can implement it). Written in Go with a server, CLI, terminal browser (TUI with Bubble Tea), and MCP server all included.

It's a WIP but usable!

Read the projects soul: mark://soul.demarkus.io (served by demarkus itself)

GitHub: https://github.com/latebit-io/demarkus

The demarkus-soul pattern and website: https://www.demarkus.io/soul/ https://www.demarkus.io

what it's like to give your AI agent a persistent memory that you actually own?

Comments URL: https://news.ycombinator.com/item?id=47241065

Points: 1

# Comments: 0

Article URL: https://gendx.dev/blog/2026/03/02/swiss-marriage-tax.html

Comments URL: https://news.ycombinator.com/item?id=47241039

Points: 1

# Comments: 0

Article URL: https://www.patreon.com/posts/seven-years-to-typescript-152144830

Comments URL: https://news.ycombinator.com/item?id=47241036

Points: 2

# Comments: 0

Article URL: https://www.contraption.co/engineering-over-enforcement/

Comments URL: https://news.ycombinator.com/item?id=47241022

Points: 1

# Comments: 0

Article URL: https://herbertlui.net/the-jellyfish-knows-how-to-survive-uncertain-times/

Comments URL: https://news.ycombinator.com/item?id=47241015

Points: 1

# Comments: 0

Apple now sells more iPhone models than ever, and we've tested everything available. From the iPhone Air and iPhone 17 to the iPhone 16E and iPhone 17 Pro, we have recommendations that will work for your budget and needs.

The top handsets of Mobile World Congress, from Xiaomi, Honor, Motorola and more.

Article URL: https://www.doomsdayscenario.co/p/obama-is-right-about-aliens

Comments URL: https://news.ycombinator.com/item?id=47240986

Points: 1

# Comments: 0

Article URL: https://www.bloomberg.com/news/articles/2026-03-02/anthropic-made-pitch-in-drone-swarm-contest-during-pentagon-feud

Comments URL: https://news.ycombinator.com/item?id=47240739

Points: 1

# Comments: 0

Article URL: https://www.ddmckinnon.com/2026/02/11/my-%f0%9f%8c%b6-take-on-vibe-coding-for-pms/

Comments URL: https://news.ycombinator.com/item?id=47240736

Points: 1

# Comments: 0