Hacker News: Newest – AI

We built AI Subroutines in rtrvr.ai. Record a browser task once, save it as a callable tool, replay it at: zero token cost, zero LLM inference delay, and zero mistakes.

The subroutine itself is a deterministic script composed of discovered network calls hitting the site's backend as well as page interactions like click/type/find.

The key architectural decision: the script executes inside the webpage itself, not through a proxy, not in a headless worker, not out of process. The script dispatches requests from the tab's execution context, so auth, CSRF, TLS session, and signed headers get added to all requests and propagate for free. No certificate installation, no TLS fingerprint modification, no separate auth stack to maintain.

During recording, the extension intercepts network requests (MAIN-world fetch/XHR patch + webRequest fallback). We score and trim ~300 requests down to ~5 based on method, timing relative to DOM events, and origin. Volatile GraphQL operation IDs are detected and force a DOM-only fallback before they break silently on the next run.

The generated code combines network calls with DOM actions (click, type, find) in the same function via an rtrvr.* helper namespace. Point the agent at a spreadsheet of 500 rows and with just one LLM call parameters are assigned and 500 Subroutines kicked off.

Key use cases:

- record sending IG DM, then have reusable and callable routine to send DMs at zero token cost

- create routine getting latest products in site catalog, call it to get thousands of products via direct graphql queries

- setup routine to file EHR form based on parameters to the tool, AI infers parameters from current page context and calls tool

- reuse routine daily to sync outbound messages on LinkedIn/Slack/Gmail to a CRM using a MCP server

We see the fundamental reason that browser agents haven't taken off is that for repetitive tasks going through the inference loop is unnecessary. Better to just record once, and get the LLM to generate a script leveraging all the possible ways to interact with a site and the wider web like directly calling backed API's, interacting with the DOM, and calling 3P tools/APIs/MCP servers.

Comments URL: https://news.ycombinator.com/item?id=47810533

Points: 3

# Comments: 1

Stitch – Google's AI design tool

satvikpendem — Fri, 17 Apr 2026 20:56:20 +0000

Article URL: https://stitch.withgoogle.com/

Comments URL: https://news.ycombinator.com/item?id=47810474

Points: 1

# Comments: 1

Show HN: Realtime Voice AI on ESP32 with Cloudflare Durable Objects

akadeb — Fri, 17 Apr 2026 20:43:56 +0000

Cloudflare's recent voice agents release provides a free daily tier for Deepgram STT, TTS use.

So I created a Voice AI Agent pipeline that runs on Cloudflare workers with Durable Objects and it interfaces with an Arduino ESP32. This lets you bring any LLM to power your Voice AI Toys and Desk companions with STT + TTS handled natively.

Comments URL: https://news.ycombinator.com/item?id=47810376

Points: 1

# Comments: 0

Change management problem rarely mentioned when pushing AI to engineering teams

cyberkoza — Fri, 17 Apr 2026 20:42:38 +0000

Article URL: https://shiftmag.dev/as-an-engineering-manager-i-couldnt-ignore-ai-if-my-teams-are-to-survive-9061/

Comments URL: https://news.ycombinator.com/item?id=47810361

Points: 1

# Comments: 2

Stalwart-Sentinel – A physics-based logic gate to stop AI hallucinations

taxi347 — Fri, 17 Apr 2026 20:12:50 +0000

Article URL: https://github.com/taxischramm347-pixel/Stalwart-Sentinel-MVP-/tree/main

Comments URL: https://news.ycombinator.com/item?id=47810086

Points: 1

# Comments: 0

Show HN: Agents.ml – a public identity page and A2A card for your AI agent

bayff — Fri, 17 Apr 2026 20:10:25 +0000

Article URL: https://agents.ml

Comments URL: https://news.ycombinator.com/item?id=47810052

Points: 2

# Comments: 1

How to Build Advanced Generative AI Agents (Kinda)

altonwells — Fri, 17 Apr 2026 19:59:30 +0000

Article URL: https://www.generative.inc/how-to-build-advanced-generative-ai-agents

Comments URL: https://news.ycombinator.com/item?id=47809915

Points: 3

# Comments: 0

'Everything is coming down': ChatGPT ads are getting cheaper

speckx — Fri, 17 Apr 2026 19:39:49 +0000

Article URL: https://digiday.com/marketing/everything-is-coming-down-chatgpt-ads-are-getting-cheaper/

Comments URL: https://news.ycombinator.com/item?id=47809748

Points: 3

# Comments: 0

Ask HN: In the AI world what does "great" look like?

armcat — Fri, 17 Apr 2026 19:23:47 +0000

I had a chat with my team mate today and they brought up an interesting point. If AI is cooking our software and doing an amazing job, for us devs what does "great" look like? How do WE improve? How do we assess performance of us, i.e. "the humans"? What do we base salaries on?

Have you discussed this in your organisations? Does anyone have a plan? If your dev teams are creating scaffolding, harnesses, skills and getting CC to cook up everything, make PRs, perform reviews, find bugs, fix bugs, update architecture diagrams....what goals do you set in performance development talks?

Need some guidance.

Comments URL: https://news.ycombinator.com/item?id=47809594

Points: 2

# Comments: 1

Why AI Is Not Getting You Out of a Job

iglesiastj — Fri, 17 Apr 2026 19:21:02 +0000

Article URL: https://yeikoff.xyz/blog/17-04-2026-not-out-of-a-job/

Comments URL: https://news.ycombinator.com/item?id=47809564

Points: 3

# Comments: 0

OpenAI to spend more than $20B on Cerebras chips, receive stake

gaurangt — Fri, 17 Apr 2026 19:20:22 +0000

Article URL: https://www.reuters.com/technology/openai-spend-more-than-20-billion-cerebras-chips-receive-equity-stake-2026-04-17/

Comments URL: https://news.ycombinator.com/item?id=47809555

Points: 4

# Comments: 3