Feed aggregator

Article URL: https://knhash.in/custom-search-engine-on-safari-and-spotlight-macos/

Comments URL: https://news.ycombinator.com/item?id=47270801

Points: 3

# Comments: 0

LLM agents and tool-calling systems frequently retry or replay actions.

This becomes dangerous when the action is irreversible: - sending emails - opening tickets - executing trades - triggering payouts

SafeAgent is a small Python library that enforces exactly-once execution for agent actions using request-ID deduplication.

Example:

from settlement.settlement_requests import SettlementRequestRegistry

registry = SettlementRequestRegistry()

def send_email(): print("EMAIL SENT")

registry.execute( request_id="email:user123:invoice", action="send_email", payload={"to": "user123@example.com"}, execute_fn=send_email )

If the same request_id is replayed, the action does not run again.

Instead the original execution receipt is returned.

pip install safeagent-exec-guard

GitHub: https://github.com/azender1/SafeAgent

PyPI: https://pypi.org/project/safeagent-exec-guard/

Comments URL: https://news.ycombinator.com/item?id=47270797

Points: 2

# Comments: 0

Article URL: https://medicalxpress.com/news/2026-03-brain-cells-dementia-proteins.html

Comments URL: https://news.ycombinator.com/item?id=47270796

Points: 4

# Comments: 0

Article URL: https://www.seroundtable.com/google-patent-ai-generated-pages-search-41010.html

Comments URL: https://news.ycombinator.com/item?id=47270785

Points: 3

# Comments: 0

Article URL: https://blog.system76.com/post/system76-on-age-verification/

Comments URL: https://news.ycombinator.com/item?id=47270784

Points: 2

# Comments: 0

Article URL: https://www.verak.io/demo

Comments URL: https://news.ycombinator.com/item?id=47270719

Points: 1

# Comments: 0

Article URL: https://odysa.github.io/one-agent-sdk/

Comments URL: https://news.ycombinator.com/item?id=47270716

Points: 1

# Comments: 1

Article URL: https://www.theatlantic.com/ideas/2026/03/intelligence-concept/686121/

Comments URL: https://news.ycombinator.com/item?id=47270715

Points: 1

# Comments: 0

Article URL: https://en.wikipedia.org/wiki/Parakaryon

Comments URL: https://news.ycombinator.com/item?id=47270714

Points: 1

# Comments: 0

Article URL: https://warden.sentry.dev/

Comments URL: https://news.ycombinator.com/item?id=47270710

Points: 1

# Comments: 0

Hello HN,

This is a food log powered by Google Gemini.

Thanks, Enzo

Comments URL: https://news.ycombinator.com/item?id=47270700

Points: 1

# Comments: 0

Article URL: https://lists.debian.org/debian-legal/2026/03/msg00018.html

Comments URL: https://news.ycombinator.com/item?id=47270687

Points: 1

# Comments: 0

Article URL: https://www.allaboutcircuits.com/industry-articles/breaking-down-50-million-pins-a-smarter-way-to-design-3d-ic-packages/

Comments URL: https://news.ycombinator.com/item?id=47270672

Points: 1

# Comments: 0

I built Gluon because I was tired of switching between a project manager, a to-do app, and a calendar every day. Gluon combines all three. The core idea is the Impact Score — each task gets a 1–10 score so you prioritize by importance, not just deadlines. Features: - Projects with task tracking and completion rates - Calendar view with tasks and events side by side - Location-based reminders (arrive/leave a place) - Productivity stats with streak tracking and weekly insights Available on iOS. Free to download with a Pro plan for advanced stats. Would love any feedback — especially on the Impact Score concept. Is this something you'd actually use? app store link: https://apps.apple.com/us/app/gluon-project-manager/id675893...

Comments URL: https://news.ycombinator.com/item?id=47270663

Points: 1

# Comments: 1

Hi HN,

I run a small Pilates studio in NYC, but before that I spent most of my life as a dancer. Recently I decided to do something that feels slightly irrational and produce an evening-length dance theater piece independently.

Normally projects like this rely on grants, institutions, or large arts organizations. Those systems can work well, but they also move slowly and can make it difficult for smaller experimental work to happen.

So I started wondering: what would it look like to approach producing a piece of performance art more like building a small startup?

The “product” is the performance itself. The budget mostly goes toward rehearsal space in NYC, paying the second performer, building a small set, costumes, and renting a venue.

Instead of waiting on grants, I’ve been experimenting with more direct community support — a mix of small donations, personal outreach, and sharing the process publicly.

A few things I’ve already learned:

• People respond much more to the story behind the work than to the work itself. • Direct personal messages raise far more support than public posts. • Funding creative work is strangely similar to early-stage startup fundraising — it’s mostly momentum and belief.

What’s been interesting is realizing that artists are rarely taught to think about funding this way. Most training focuses on the craft itself, not on building the systems that allow the work to exist.

I’m curious if anyone here has experimented with unconventional funding models for creative work or small projects.

Would love to hear any thoughts or experiences.

Comments URL: https://news.ycombinator.com/item?id=47270660

Points: 1

# Comments: 0

I'm researching problems people face when searching for jobs online.

Many people mention fake job postings, duplicated listings, or companies that never respond after applying.

I'm curious how common this actually is.

Have you encountered fake job postings during your job search?

If so, what were the signs that made you realize the job wasn't legitimate?

Did you notice any patterns (for example: certain job boards, suspicious requests, or companies that never replied)?

Comments URL: https://news.ycombinator.com/item?id=47270647

Points: 1

# Comments: 0

I wanted Claude Code to notify my ESP32 when it finished a task. A `curl` in the Stop hook worked — until I needed a local dashboard too. The dashboard couldn't expose an HTTP endpoint, it needed to subscribe. And every new client meant editing hook configs across all my projects.

So I built agent-pulse: a local gateway that captures AI agent lifecycle events and fans them out to registered clients.

You register clients once in a global YAML. Projects just call `agent-pulse hook --provider claude --event stop` from their hooks. The gateway handles routing, per-client filtering, and parallel dispatch. It auto-starts on the first event.

Two delivery modes: HTTP POST fan-out for webhooks and scripts, SSE stream (`GET /events/stream`) for dashboards and anything that can't expose an endpoint. You can also attach project metadata via `.agent-pulse.json` that travels with every event.

Single Go binary, zero runtime dependencies. Claude Code and Gemini CLI supported today, OpenCode and Codex CLI in progress.

Note: Claude Code recently added native HTTP hooks, so you can POST directly to an endpoint without any intermediary. agent-pulse is useful when you have multiple clients, need SSE, or want one config across projects.

Thanks!

https://github.com/SantiagoBobrik/agent-pulse

Comments URL: https://news.ycombinator.com/item?id=47270638

Points: 1

# Comments: 0

Netwall (https://netwall.org) is an ultra-simple, text-only public wall.

- No accounts, no sign-ups.

- You type a message, hit enter, and it deletes itself after exactly 1 hour.

- If the community likes a post, they can click "+5m" to vote to keep it alive a bit longer.

Stack: Vanilla JS, Node/Express, Postgres. It features a few classic terminal themes (including Solarized Dark and the Openwall mailing list aesthetic), and sits behind OpenAI's Moderation API to keep it from turning into a complete swamp.

Let me know what you think!

Comments URL: https://news.ycombinator.com/item?id=47270637

Points: 1

# Comments: 0

This is a realtime collaborative blog! It works like git!

Comments URL: https://news.ycombinator.com/item?id=47270630

Points: 1

# Comments: 1