Feed aggregator

Article URL: https://github.com/alibaba/page-agent

Comments URL: https://news.ycombinator.com/item?id=47319676

Points: 1

# Comments: 0

If you add a $schema field to JSON or YAML, you can run JSON Schema validation. Likewise, if you add a $type field, this tool performs TypeScript-based checks.

It provides both a VSCode extension and a CLI.

The VSCode extension offers Diagnostics (it draws a red underline when something is wrong) and a Go To Definition feature. Since it’s published on both the Marketplace and open-vsx, the extension can also be used in other VSCode-based editors such as Cursor.

The CLI provides check and lsp commands. With the check command, you can run JSON type checks in CI/CD, and with the lsp command, it can be integrated and used in editors other than VSCode.

I’m planning to soon implement type-based field auto-completion and a feature that shows documentation on mouse hover. I’m also considering adding type checking using other static type languages besides TypeScript.

Comments URL: https://news.ycombinator.com/item?id=47319665

Points: 1

# Comments: 0

Article URL: https://github.com/Ja1pr/Ja1pr-750

Comments URL: https://news.ycombinator.com/item?id=47319663

Points: 1

# Comments: 1

We've been thinking a lot about inference infrastructure recently, and it seems like the challenges are very different from training. Training tends to be compute-heavy but predictable, while inference introduces things like: - latency constraints - dynamic batching - unpredictable traffic patterns - model versioning in production - GPU utilization issues at smaller batch sizes For people running inference in production today, what's been the most painful part?

Comments URL: https://news.ycombinator.com/item?id=47319653

Points: 1

# Comments: 0

Article URL: https://apnews.com/article/faa-ground-stop-jetblue-e990b118812f467d904d92375b984d71

Comments URL: https://news.ycombinator.com/item?id=47319647

Points: 1

# Comments: 0

Most LLM interfaces assume thinking happens in a straight line.

prompt → response → refine → refine

But when I explore ideas with AI, it usually branches.

One prompt leads to multiple directions, and it's hard to compare them in a single chat thread.

So I built a small workspace where prompts branch like a tree.

You can explore different reasoning paths and continue from the most interesting one.

I'm curious what HN thinks about node-based interfaces for prompting compared to traditional chat UIs.

Comments URL: https://news.ycombinator.com/item?id=47319646

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=C1jmAj9OUOs

Comments URL: https://news.ycombinator.com/item?id=47319644

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=w8wt0LBCjXM

Comments URL: https://news.ycombinator.com/item?id=47319642

Points: 1

# Comments: 1

Most LLM interfaces assume thinking happens in a straight line.

prompt → response → refine → refine

But when I explore ideas with AI, it usually branches.

One prompt leads to multiple directions, and it's hard to compare them in a single chat thread.

So I built a small workspace where prompts branch like a tree.

You can explore different reasoning paths and continue from the most interesting one.

I'm curious what HN thinks about node-based interfaces for prompting compared to traditional chat UIs.

Comments URL: https://news.ycombinator.com/item?id=47319626

Points: 1

# Comments: 0

Article URL: https://veltora-beta.vercel.app

Comments URL: https://news.ycombinator.com/item?id=47319622

Points: 1

# Comments: 1

Article URL: https://loger-project.github.io

Comments URL: https://news.ycombinator.com/item?id=47319620

Points: 2

# Comments: 0

Article URL: https://twitter.com/chrislaubai/status/2030931602872967460

Comments URL: https://news.ycombinator.com/item?id=47319609

Points: 1

# Comments: 0

How does shared hosting support business continuity and growth?

Comments URL: https://news.ycombinator.com/item?id=47319601

Points: 1

# Comments: 1

With the buzz that's happening with all the new AI models that get released (what feels like every other week), how are companies running internal AI evals to determine which model is best for their use case?

Comments URL: https://news.ycombinator.com/item?id=47319587

Points: 1

# Comments: 0

Article URL: https://www.theregister.com/2026/03/08/deploy_and_manage_attack_infrastructure/

Comments URL: https://news.ycombinator.com/item?id=47319421

Points: 1

# Comments: 0

Article URL: https://www.bunniestudios.com/blog/2026/baochip-1x-a-mostly-open-22nm-soc-for-high-assurance-applications/

Comments URL: https://news.ycombinator.com/item?id=47319387

Points: 1

# Comments: 0

Article URL: https://localrag.app

Comments URL: https://news.ycombinator.com/item?id=47319311

Points: 1

# Comments: 0

Article URL: https://starlog.is/articles/data-knowledge/langwatch-langwatch/

Comments URL: https://news.ycombinator.com/item?id=47319306

Points: 1

# Comments: 0

Article URL: https://en.wikipedia.org/wiki/Bloom%27s_taxonomy

Comments URL: https://news.ycombinator.com/item?id=47319302

Points: 1

# Comments: 0

Article URL: https://thezvi.wordpress.com/2026/03/09/claude-code-claude-cowork-and-codex-5/

Comments URL: https://news.ycombinator.com/item?id=47319294

Points: 1

# Comments: 0