siegers

Joined 3 years ago

Karma

311

Submissions

108

Member since

Feb 7

View on Hacker News

Recent submissions

Show HN: Gembop, a block-placement puzzle game in 2D and 3D gembop.games

5 siegers 13 days ago 0 comments

Strands Shell: Give your agent a shell without giving it keys to your machine github.com

9 siegers 4 months ago 0 comments

New in Kiro Web: Build with Spec, GitLab, and More kiro.dev

5 siegers 4 months ago 1 comments

Agent Toolkit for AWS github.com

5 siegers 4 months ago 0 comments

How we contain Claude across products anthropic.com

6 siegers 5 months ago 0 comments

Introducing Kiro Web: Build, delegate, and steer right from the browser kiro.dev

4 siegers 5 months ago 0 comments

What We Learned from One Year of Building Production Agents strandsagents.com

2 siegers 5 months ago 0 comments

HyperFrames lets AI agents compose videos by writing HTML, CSS and JavaScript hyperframes.heygen.com

5 siegers 6 months ago 0 comments

Supabase Feature Preview: RLS Tester github.com

2 siegers 6 months ago 0 comments

Comment · 6 months ago

Hi! Yes, the premium voices are Kokoro. I’m only exposing the English voices right now because the rest of the pipeline around them is English-first and custom, especially pronunciation/G2P, QA, and timestamp awareness. I’d like to expand that over time, but I don’t want to overpromise multilingual support before the surrounding stack is ready. So I'm taking it one language at a time based on demand and feedback.

AI summaries are currently generated remote, not local. Those currently leverage gpt-4o-mini. TTS and OCR are on-device and summarization is the cloud-backed feature.

Comment · 6 months ago

I like this approach and that it's so flexible and approachable. My nit for the site would be to explain it a bit better - it's a bit hard to grok with everything going on until I went to the repo. There's also opportunity for non-tech users here just using the agent skill but I'm not sure they'll understand the use if they read through the site.

I had made a skill for something similar to use just HTML5, Canvas and JavaScript, and export the video to MP4 (https://github.com/siegerts/skill-canvas-video).

Show HN: Readox, playlist-style read aloud extension for articles, PDFs and docs chromewebstore.google.com

4 siegers 6 months ago 2 comments

Show HN: Readox – Turn web pages and PDFs into a playable reading queue readox.ai

4 siegers 6 months ago 0 comments

Comment · 6 months ago

Agree. I keep effort max on Claude and xhigh on GPT for all tasks and keep tasks as scoped units of work instead of boil the ocean type prompts. It is hard to measure but ultimately the tasks are getting completed and I'm validating so I consider it "working as expected".