The engine of Germany's wealth is blocking its future
83 by mariuz | 43 comments on Hacker News.
Monday, 9 March 2026
Sunday, 8 March 2026
New top story on Hacker News: Show HN: AI agents run my one-person company on Gemini's free tier – $0/month
Show HN: AI agents run my one-person company on Gemini's free tier – $0/month
8 by ppcvote | 3 comments on Hacker News.
I'm a solo dev in Taiwan. I built 4 AI agents that handle content, sales leads, security scanning, and ops for my tech agency — all on Gemini 2.5 Flash free tier (1,500 req/day). I use ~105. Monthly LLM cost: $0. Architecture: 4 agents on OpenClaw (open source), running on WSL2 at home with 25 systemd timers. What they do every day: - Generate 8 social posts across platforms (quality-gated: generate → self-review → rewrite if score < 7/10) - Engage with community posts and auto-reply to comments (context-aware, max 2 rounds) - Research via RSS + HN API + Jina Reader → feed intelligence back into content - Run UltraProbe (AI security scanner) for lead generation - Monitor 7 endpoints, flag stale leads, sync customer data - Auto-post blog articles to Discord when I git push (0 LLM tokens — uses commit message directly) The token optimization trick: agents never have long conversations. Every request is (1) read pre-computed intelligence files (local markdown, 0 tokens), (2) one focused prompt with all context injected, (3) one response → parse → act → done. The research pipeline (RSS, HN, web scraping) costs 0 LLM tokens — it's pure HTTP + Jina Reader. The LLM only touches creative/analytical work. Real numbers: - 27 automated Threads accounts, 12K+ followers, 3.3M+ views - 25 systemd timers, 62 scripts, 19 intelligence files - RPD utilization: 7% (105/1,500) — 93% headroom left - Monthly cost: $0 LLM + ~$5 infra (Vercel hobby + Firebase free) What went wrong: - $127 Gemini bill in 7 days. Created an API key from a billing-enabled GCP project instead of AI Studio. Thinking tokens ($3.50/1M) with no rate cap. Lesson: always create keys from AI Studio directly. - Engagement loop bug: iterated ALL posts instead of top N. Burned 800 RPD in one day and starved everything else. - Telegram health check called getUpdates, conflicting with the gateway's long-polling. 18 duplicate messages in 3 minutes. The site ( https://ultralab.tw ) is fully bilingual (zh-TW/en) with 21 blog posts, and yes — the i18n, blog publishing, and Discord notifications are all part of the automated pipeline. Live agent dashboard: https://ultralab.tw/agent Stack: OpenClaw, Gemini 2.5 Flash (free), WSL2/systemd, React/TypeScript/Vite, Vercel, Firebase, Telegram Bot, Resend, Jina Reader. GitHub (playbook): https://github.com/UltraLabTW/free-tier-agent-fleet Happy to answer questions about the architecture, token budgeting, or what it's actually like running AI agents 24/7 as a one-person company.
8 by ppcvote | 3 comments on Hacker News.
I'm a solo dev in Taiwan. I built 4 AI agents that handle content, sales leads, security scanning, and ops for my tech agency — all on Gemini 2.5 Flash free tier (1,500 req/day). I use ~105. Monthly LLM cost: $0. Architecture: 4 agents on OpenClaw (open source), running on WSL2 at home with 25 systemd timers. What they do every day: - Generate 8 social posts across platforms (quality-gated: generate → self-review → rewrite if score < 7/10) - Engage with community posts and auto-reply to comments (context-aware, max 2 rounds) - Research via RSS + HN API + Jina Reader → feed intelligence back into content - Run UltraProbe (AI security scanner) for lead generation - Monitor 7 endpoints, flag stale leads, sync customer data - Auto-post blog articles to Discord when I git push (0 LLM tokens — uses commit message directly) The token optimization trick: agents never have long conversations. Every request is (1) read pre-computed intelligence files (local markdown, 0 tokens), (2) one focused prompt with all context injected, (3) one response → parse → act → done. The research pipeline (RSS, HN, web scraping) costs 0 LLM tokens — it's pure HTTP + Jina Reader. The LLM only touches creative/analytical work. Real numbers: - 27 automated Threads accounts, 12K+ followers, 3.3M+ views - 25 systemd timers, 62 scripts, 19 intelligence files - RPD utilization: 7% (105/1,500) — 93% headroom left - Monthly cost: $0 LLM + ~$5 infra (Vercel hobby + Firebase free) What went wrong: - $127 Gemini bill in 7 days. Created an API key from a billing-enabled GCP project instead of AI Studio. Thinking tokens ($3.50/1M) with no rate cap. Lesson: always create keys from AI Studio directly. - Engagement loop bug: iterated ALL posts instead of top N. Burned 800 RPD in one day and starved everything else. - Telegram health check called getUpdates, conflicting with the gateway's long-polling. 18 duplicate messages in 3 minutes. The site ( https://ultralab.tw ) is fully bilingual (zh-TW/en) with 21 blog posts, and yes — the i18n, blog publishing, and Discord notifications are all part of the automated pipeline. Live agent dashboard: https://ultralab.tw/agent Stack: OpenClaw, Gemini 2.5 Flash (free), WSL2/systemd, React/TypeScript/Vite, Vercel, Firebase, Telegram Bot, Resend, Jina Reader. GitHub (playbook): https://github.com/UltraLabTW/free-tier-agent-fleet Happy to answer questions about the architecture, token budgeting, or what it's actually like running AI agents 24/7 as a one-person company.
Friday, 6 March 2026
New top story on Hacker News: Show HN: Reconstruct any image using primitive shapes, runs in-browser via WASM
Show HN: Reconstruct any image using primitive shapes, runs in-browser via WASM
9 by taiseiue | 1 comments on Hacker News.
I built a browser-based port of fogleman/primitive — a Go CLI tool that approximates images using primitive shapes (triangles, ellipses, beziers, etc.) via a hill-climbing algorithm. The original tool requires building from source and running from the terminal, which isn't exactly accessible. I compiled the core logic to WebAssembly so anyone can drop an image and watch it get reconstructed shape by shape, entirely client-side with no server involved. Demo: https://ift.tt/CujYmMK Source: https://ift.tt/VtglO7b Curious if anyone has ideas for shapes or features worth adding.
9 by taiseiue | 1 comments on Hacker News.
I built a browser-based port of fogleman/primitive — a Go CLI tool that approximates images using primitive shapes (triangles, ellipses, beziers, etc.) via a hill-climbing algorithm. The original tool requires building from source and running from the terminal, which isn't exactly accessible. I compiled the core logic to WebAssembly so anyone can drop an image and watch it get reconstructed shape by shape, entirely client-side with no server involved. Demo: https://ift.tt/CujYmMK Source: https://ift.tt/VtglO7b Curious if anyone has ideas for shapes or features worth adding.
New top story on Hacker News: Ask HN: How many of you hold an amateur radio license in your country?
Ask HN: How many of you hold an amateur radio license in your country?
22 by ToddWBurgess | 23 comments on Hacker News.
I am VE3HWO. I hold a basic with honours and advanced qualifications in Canada. Hoping to connect with other hams on HN. 73
22 by ToddWBurgess | 23 comments on Hacker News.
I am VE3HWO. I hold a basic with honours and advanced qualifications in Canada. Hoping to connect with other hams on HN. 73
Thursday, 5 March 2026
Wednesday, 4 March 2026
Subscribe to:
Comments (Atom)