News for hackers. Stuff that matters.

andes314

Re:AdGPT on Monday March 23, 2026 @01:26AM (#47485775)
To whoever messaged “what is Manchester United” and got an airline ad, come on, that’s pretty cool right? I’d really love some discussion on this as I have not yet seen ads in GenAI apps and wanted to experience them.
Re:Give Your AI Agent a Live Status Page on Friday March 13, 2026 @12:41AM (#47360755)
skills.md:

# ClawJetty Skills

ClawJetty lets you create a live public progress page for a task.

## Goal

Before starting work, create a run and return its public URL to the user. As you work, post short progress updates. When finished, post a final event marking the run complete or failed.

## Base URL

https://clawjetty.com

## API

### 1) Create a run

POST /api/runs

Request body:

```json { "title": "Researching CRM tools" } ```

Response body:

```json { "id": "run_abc123", "viewer_url": "https://clawjetty.com/t/run_abc123", "status": "active" } ```

Create the run before doing the task. Return viewer_url to the user immediately.

### 2) Post an event

POST /api/runs/{id}/events

Request body:

```json { "kind": "update", "message": "Comparing 5 tools by price and features" } ```

Allowed event kinds:

- update - complete - fail

Example complete event:

```json { "kind": "complete", "message": "Finished. Sent final recommendation to user." } ```

Example fail event:

```json { "kind": "fail", "message": "Failed due to missing access to the source system." } ```

## Usage rules

- Create the run before starting the task. - Return the viewer_url to the user immediately. - Post short updates after meaningful steps. - Keep updates short and plain. - Do not flood the run with tiny updates. - Do not include secrets, passwords, API keys, or raw private data. - End every run with either complete or fail.

## Good update examples

- Reading the uploaded PDF - Summarizing the findings - Drafting the email reply - Blocked waiting on missing invoice number

## Bad update examples

- Thinking - Working - Doing stuff - Long dumps of raw content

Re:Give Your AI Agent a Live Status Page on Thursday March 12, 2026 @11:49PM (#47360478)
A quick tool to give your AI agent a live status page. I made this after being frustrated with the lack of visibility in tools like OpenClaw. Open to feedback.

Show HN: ClawJetty: See what your AI Agent is Doing

https://clawjetty.com/#

I built a small tool called ClawJetty. It gives an AI agent a public progress page for any task. It has worked wonders on OpenClaw, Claude Code, Codex.The idea is simple: before starting work, the agent creates a run, returns a public link to the user, and then posts short progress updates as it works. The user can watch a live timeline instead of waiting in the dark for a long task to...

( Read More... | no comments | on HN )
Re:My Dev Box Setup Script on Wednesday March 11, 2026 @05:27PM (#47342208)
Good call, worth adding!
Re:ClawJetty: Plug-In Personal OpenClaw Box on Wednesday February 18, 2026 @10:38PM (#47069604)
I’m building ClawJetty: a small, always-on mini PC that runs a personal OpenClaw instance with minimal setup (pair from an app, connect your chat channel, done). The point is to make “self-host your agent” feel like setting up a router, not a weekend project.

Pricing is two tiers and two purchase options:

Plus: $149/mo with a 12-month commitment (box included) or $449 upfront + $119/mo

Pro: $269/mo with a 12-month commitment (box included) or $449 upfront + $219/mo

Plans include managed updates + rollback, safe defaults (no exposed inbound ports), and address collection at checkout for fulfillment. AI usage is bundled with included allowance; overages/top-ups will come later.

Looking for feedback from people who’ve self-hosted agents (or tried): what parts of setup/ops were the biggest pain, and what would you demand from an “agent appliance” to trust it?

Linear time attention doesn’t work, by principle. Dead end pursuit. Much great research on more efficient quadratic time inference
Re:Ask HN: Freelancer? Seeking freelancer? (September 2025) on Tuesday September 02, 2025 @08:35PM (#45110931)
SEEKING WORK, Boston, MA (open to relocation), Remote Welcome.

https://rlafuente.com

ML Engineer with experience in high visibility DARPA and DAF projects. I charge $200/hour for time spent in an interview process.

Re:Hire Me: ML Engineer on Tuesday September 02, 2025 @05:36PM (#45109390)
Putting my profile on here for anyone who is looking for an ML Engineer. I have worked on AI/ML development on highly visible DARPA and DAF programs. I generally charge $200/hour for time spent interviewing.

Show HN: 16-Pad Sampler from Your Videos

https://sampler.rlafuente.com/

Upload a video, click “Analyze & Slice,” and it builds a 4×4 pad grid from the video’s own audio. Pads are labeled to nudge musical roles (Downbeat/Backbeat/Offbeat/Fill; rows = 1/3/5/8). Tap to play slices or hit “Start Loop” for a simple, repeating groove that sounds decent right away.Under the hood it finds onsets via spectral flux, pre-renders slices to AudioBuffers with tiny fades, and...

( Read More... | no comments | on HN )
Re:Postman for MCP on Saturday May 17, 2025 @11:10AM (#44014891)
This platform is an mcp client and mcp server creator tool. You make the mcp servers from APIs. It is a “Postman” tool in two ways
Re:Postman for MCP on Saturday May 17, 2025 @02:55AM (#44012524)
Less than you’d think
Re:Postman for MCP on Saturday May 17, 2025 @02:55AM (#44012521)
It is a platform to create MCP servers from API endpoints, and then chat with them without having to use Claude’s clunky integration process. It is simple and complete.

Older »