Hacker News: yammosk

New comment by yammosk in "Zero-Touch OAuth for MCP"

yammosk — Fri, 19 Jun 2026 04:43:06 +0000

As someone who has been creating agentic workarounds at my large employer and in a lot of conversations with security as a result, this does not seem to be a huge advantage from the company side. They are very much invested in users being aware of what they permit. The company does want the final say either with shutting down a compromised user or blocking one service from agents and allowing the other, but they 100% do still want employees to be actively engaged and applying their own consent.

Removing that from the employee also removes the employee from responsibility for any breach of information IMO, and companies definitely don't want that lol. What they do want is users to stop complaining about the annoying reauth every 8-12 hours for a dozen services which this does.

The kinds of wishlists I hear are more about users managing fine-grain service permissions for various agentic roles and managing which agents have access to which role, which leans the other direction. They want to allow users are to treat agents like cloud services and have a greater responsibility for applying least privilege, justify leak risks, etc. The onus to protect this data will always be an employee responsibility in the end.

New comment by yammosk in "Why One Key Shouldn't Rule Them All: Threshold Signatures for the Rest of Us"

yammosk — Mon, 23 Mar 2026 16:26:16 +0000

I just don't think that keys would be accessible by only one person in either scenario for any large business. The article suggests this 3/5 key needed system prevents issues but I don't think so in practical terms. My suspicion is it thinks there is only one person per key but I think in any business scenario a team would have access to all of them negating the benefits. I don't think that's inconsistent, perhaps just my misunderstanding of what this proposed.

New comment by yammosk in "Why One Key Shouldn't Rule Them All: Threshold Signatures for the Rest of Us"

yammosk — Sun, 22 Mar 2026 23:29:29 +0000

What secret is controlled by one person? That's just not how businesses manage secrets.

New comment by yammosk in "The future of version control"

yammosk — Sun, 22 Mar 2026 19:31:59 +0000

And yet after all these year of git supporting no source of truth we still fall back on it. As long as you have an authoritative version and authoritative release then you have one source of truth. Linus imagined everyone contributing with no central authority and yet we look to GitHub and Gitlab to centralize our code. Git is already decentralized and generally we find it impractical.

New comment by yammosk in "Why One Key Shouldn't Rule Them All: Threshold Signatures for the Rest of Us"

yammosk — Sat, 21 Mar 2026 12:59:00 +0000

Even just on a theoretical level I am not really sure the use case of this system. For most keys like ssl certs, this is just too impractical. For anything that has significant business value (like the iOS signing key), I don't think any business would give up all control of such a key to the whims of 3 out of 5 people.

New comment by yammosk in "Our commitment to Windows quality"

yammosk — Sat, 21 Mar 2026 12:18:50 +0000

I am stuck on an arbitrary version of the Win 11 Preview from some years ago because at some point they decided my machine couldn't get updates. No technical reason just business. I can't update to the retail Win 11 and I can't downgrade to Win 10 without wiping my machine. I don't care about whatever new commitment they have, because it is clearly not to me.

New comment by yammosk in "Ask HN: How do you deal with people who trust LLMs?"

yammosk — Thu, 19 Mar 2026 03:40:54 +0000

I am not sure I would even say "believe", I would think of it more as short-circuiting our critical thinking. I think it taps into something at the core of our tribal instincts. It was famously present in even basic systems like Eliza. And it's not just machines... The same tricks are used by conmen, politicians, and psychopaths, which is more negative than I intend. Even with good intentions and positive outcomes, I feel we need to remember that we drive it, not the other way around.

New comment by yammosk in "What Is Agentic Engineering?"

yammosk — Mon, 16 Mar 2026 03:14:34 +0000

I find it quite useful to work out, plan, and refine ideas with agents. An agents ability to call out approaches you haven't thought of is really powerful. I find it useful to steer their feedback and proposals to the exact constraints you have or give yourself a confidence check on if you are leaning toward a solution for the right reasons. The best is when you can test 2-3 avenues and being able to come back and evaluate the results. Normally you would commit to one and spend all your time on that approach, make an assessment it was bad enough to try something else and move on. I find agents completely flip the script on research and planning. I find I am better able to work on hard problems then ever before with these tools. I think people severely limit themselves if they are only using them at the "build it" phase.

New comment by yammosk in "Chrome DevTools MCP (2025)"

yammosk — Mon, 16 Mar 2026 02:51:28 +0000

There are actually a lot of great things you can to to make CLIs more helpful to agents. I use a structured help called '--capabilities' but there is a ton of JIT context you can do from the CLI as well https://keyboardsdown.com/posts/01-agent-first-clis/

New comment by yammosk in "Claude March 2026 usage promotion"

yammosk — Sun, 15 Mar 2026 01:17:45 +0000

It's faster to change user behavior then to buy and setup new hardware. I bet this is just to bleed off the their growing pains with the influx of users.

Agent-first CLIs are about reducing turns, not JSON

yammosk — Thu, 12 Mar 2026 12:56:56 +0000

Article URL: https://keyboardsdown.com/posts/01-agent-first-clis/

Comments URL: https://news.ycombinator.com/item?id=47349927

Points: 1

# Comments: 0

New comment by yammosk in "Helix: A post-modern text editor"

yammosk — Sat, 07 Mar 2026 17:20:04 +0000

The second half of this is spot on. The now is making IDEs that can integrate with agents, not the other way around. Soon the Claude and Codex will do that for us on their hosts and the argument is it will save sending the context up.