Hacker News: shay_ker

New comment by shay_ker in "Previewing the Model Hardware Standard"

shay_ker — Thu, 27 Aug 2026 22:33:08 +0000

How is this different from tool calls? Or rather, MCP?

New comment by shay_ker in "WebMCP: Teaching Your Website to Talk to AI Agents"

shay_ker — Wed, 26 Aug 2026 16:51:11 +0000

I think pinning WebMCP to the browser was the wrong choice. To list or call tools, you have to have access to the browser environment. "Declarative" WebMCP allows you to read the HTML, but to call tools you still need the JS execution env.

This limits the utility of WebMCP to in-browser agents. In practice, what's the use case? Computer Use can work, but at that point you can circumvent WebMCP entirely.

IMO the better option would be to unify MCP with a standard protocol, like HTTP. Right now, you have to rely on the MCP registry for discovering MCP servers, but wouldn't it make more sense to have this natively in HTTP?

Pi-Duplex

shay_ker — Wed, 26 Aug 2026 16:33:22 +0000

Article URL: https://diverging.run/checkpoints/pi-duplex/

Comments URL: https://news.ycombinator.com/item?id=49451916

Points: 15

# Comments: 2

New comment by shay_ker in "The turbulent AI era is here"

shay_ker — Wed, 26 Aug 2026 13:36:22 +0000

> I doubt I would have put in the same work if I had had an AI companion back then. They talk to you in ways you’re already comfortable with. They don’t push you outside your comfort zone. They are always available and never get mad at you. This gives them the potential to become highly addictive and to rob us of the lessons we learn from connecting with other people.

I've been waiting for a long, long time for us to figure out how AI makes us more social, not less. Outside of memes of course.

New comment by shay_ker in "The turbulent AI era is here"

shay_ker — Wed, 26 Aug 2026 13:35:11 +0000

> I’m also worried about AI’s impact on education. Ironically, the same tool that will allow people to learn more than ever could also lead to many people learning less.

For teachers/admins who are on HN: what has worked in a past for a "new way to educate" students to actually be implemented by educators? Does it happen through conferences? Do some states take the lead and others follow? Does it follow from private schools into public schools?

I know AI labs are trying to include teachers here and there... but IME teachers are very "anti-AI", "anti-datacenter", etc. etc. In coastal cities, the unions will be entirely opposed. This seems less of a "can AI be useful for education" question and more around politics and messaging. But I'd love to learn more.

New comment by shay_ker in "The turbulent AI era is here"

shay_ker — Wed, 26 Aug 2026 13:27:47 +0000

> In the United States, I’ve met families who, understandably, were overwhelmed by the process of applying for health insurance, student aid, or food assistance. Faced with a huge stack of complicated bureaucratic forms, many felt like giving up. AI can streamline things dramatically

I'd love to see anyone building Grokbot or ChatGPT Work talk about how they're thinking about this use case, specifically. It seems greatly important and tractable given how little government websites & forms change over time.

On the other end - yes, it will create massive vectors for abuse & fraud, since govt services are designed to have roadblocks to reduce usage. But fraud has always been possible, even without AI (so many recent examples to pull from).

IMO it's best to maximize social benefits to see where the tradeoffs really are. We won't know until we push on it!

New comment by shay_ker in "RAG Is Simpler Than You Think"

shay_ker — Wed, 26 Aug 2026 12:49:51 +0000

How long have "large scale RAG systems" really existed in the first place? I'm always surprised at this, given how new all this really is, relatively speaking.

"Model Effort" Has It Backwards

shay_ker — Wed, 26 Aug 2026 12:46:33 +0000

Article URL: https://diverging.run/checkpoints/human-effort-not-model-effort/

Comments URL: https://news.ycombinator.com/item?id=49448116

Points: 2

# Comments: 0

"Model Effort" Has It Backwards

shay_ker — Mon, 24 Aug 2026 19:33:01 +0000

Article URL: https://diverging.run/checkpoints/human-effort-not-model-effort/

Comments URL: https://news.ycombinator.com/item?id=49424767

Points: 2

# Comments: 0

New comment by shay_ker in "Feature Request: Support AGENTS.md"

shay_ker — Wed, 19 Aug 2026 22:54:55 +0000

how does agents.md work for subagents and swarms? is it actually that useful?

New comment by shay_ker in "Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp"

shay_ker — Tue, 11 Aug 2026 15:37:28 +0000

I recall there was another YC startup that was working on Mac-specific ML optimizations for local inference (and perhaps fine-tuning).

I wonder if their work is related?

New comment by shay_ker in "Rust SIMD on the GPU"

shay_ker — Mon, 10 Aug 2026 22:33:45 +0000

Hm is the intent to one day replace the CPU?

New comment by shay_ker in "How I use LLMs to learn complex topics"

shay_ker — Sun, 09 Aug 2026 23:26:37 +0000

i've asked llms to write a presentation for me on a given topic. for whatever reason, that finds the hidden layer responsible for explaining things well.

A Comprehensive Guide to InnoDB Locking

shay_ker — Sun, 09 Aug 2026 02:06:57 +0000

Article URL: https://jahfer.com/posts/innodb-locks/

Comments URL: https://news.ycombinator.com/item?id=49227744

Points: 2

# Comments: 0

New comment by shay_ker in "Shopify replaced Redis with MySQL for inventory reservations–and it scaled"

shay_ker — Sun, 09 Aug 2026 02:06:38 +0000

outside the slop, i liked this post that was linked on innodb locking: https://jahfer.com/posts/innodb-locks/

New comment by shay_ker in "Databricks drove down AI coding spend 70%"

shay_ker — Fri, 07 Aug 2026 20:47:12 +0000

how do any of these routing approaches handle kv cache misses? Devin Fusion is the only one that explicitly addresses this, though it does so by switching models during compaction (not sure this isn't still a cache miss though)

New comment by shay_ker in "Responding to the next frontier of critical cyber capabilities"

shay_ker — Fri, 07 Aug 2026 18:22:53 +0000

i'm surprised there isn't more commentary on the vulnerabilities themselves (mostly in apps developed on the jvm, e.g. artifactory)

Can the Cloud Be Disrupted with AI?

shay_ker — Fri, 07 Aug 2026 14:01:50 +0000

Article URL: https://diverging.run/checkpoints/cloud-ai-disruption/

Comments URL: https://news.ycombinator.com/item?id=49210576

Points: 2

# Comments: 0

New comment by shay_ker in "Devtools must be open source"

shay_ker — Mon, 03 Aug 2026 18:09:32 +0000

Separately, JetBrains's revenue grew 25%: https://www.jetbrains.com/lp/annualreport-2026/

But back to OP, for this prompt:

> Set up a nightly cron job that executes the prompt: fetch upstream changes to the and rebase all local changes on top of upstream. Check that the software works as intended and replace the current version.

Seems like nice syntax sugar to add a `/maintain-fork` command.

Time-Lock Encryption for Historical Artifacts

shay_ker — Mon, 03 Aug 2026 12:55:28 +0000

Article URL: https://diverging.run/checkpoints/historians-will-hate-encryption/

Comments URL: https://news.ycombinator.com/item?id=49155165

Points: 2

# Comments: 0