Live data from Hacker News

Viewing profile — ejholmes

ejholmes

HN member
Joined
Wed, Apr 03, 2013, 9:52 PM UTC
HN karma
359
Public activity
74 items

About ejholmes

[ my public key: https://keybase.io/ejholmes; my proof: https://keybase.io/ejholmes/sigs/0jl4moyDx6xoCxcRe5SRUTMm-tvNzG-fZTx7CuGdYhI ]

Recent public activity

  1. comment
    Comment #47222471

    I think that's a fair argument. I'd push back a bit on that being unique to MCP. Agent browser ( https://github.com/vercel-labs/agent-browser ) handles persistent sessions just fin…

  2. comment
    Comment #47213891

    Silly. All it needs is docs. No need to overcomplicate it.

  3. comment
    Comment #47213632

    Funny. Dealing with Kubernetes is my day job, and I can be equally critical of it. Pointing out absurdities is how we make things better, and that’s ok.

  4. comment
    Comment #47212441

    I always get a kick out of seeing MCP wrappers around CLI’s.

  5. comment
    Comment #47211618

    Great read. Thanks for sharing. 100% agree, `—json | jq` is where it’s at.

  6. comment
    Comment #47210581

    You're right, but it still doesn't mean MCP was a good design even in that space. We could've done better.

  7. comment
    Comment #47210568

    But they're not token efficient. Take the terraform example from the post. Plan JSON is massive. You're not saving tokens by using a Terraform MCP and shoving an entire plan into c…

  8. comment
    Comment #47210404

    > both are a method of tool calling, it does not matter which format the LLM uses for tool calling as long as it provides the same capabilities. MCP tool calls aren't composable. N…

  9. comment
    Comment #47210372

    Neato! https://github.com/vercel-labs/agent-browser is a similar take here, and much better than the playwright MCP.

  10. comment
    Comment #47210341

    Thanks for reading! And yes, if anyone takes anything away from this, it's around composition of tools. The other arguments in the post are debatable, but not that one.

  11. comment
    Comment #47210327

    Author here! Biggest difference is composition. MCP tools don't chain (there's people trying to fix that, but it's still true right now).

  12. comment
    Comment #47210300

    I get it. This is coming from a place where I see MCP's being adopted, where CLI is (in my opinion) better. Particularly where you're already in a CLI environment, and tool composi…

  13. comment
    Comment #47209690

    Hi friends! Author here. This blew up a bit, so some words. The article title and content is intentionally provocative. It’s just to get people thinking. My real views are probably…

  14. story
  15. comment
    Comment #20891778

    This will hopefully become obsolete in the near future. If you're on a recent MacBook (with TouchID), using the current version of Chrome, and using a website that supports the new…

  16. comment
    Comment #19569200

    Obviously, depends on your threat model. I'd argue that being physically coerced ends up being a pretty low risk for most people. If you're just looking for something better than s…

  17. comment
    Comment #19568435

    If you have a newer MacBook with TouchID, you can get similar benefits using https://github.com/sekey/sekey . Arguably better, because access is backed by biometrics (TouchID) so i…

  18. comment
    Comment #19168112

    I know this was probably well intentioned, but I can't shake the irony of how overly complex and over-engineered this is. If you're just starting out, please, please, please don't …

  19. comment
    Comment #17713448

    It's a pretty scary prospect, to the point that I have to imagine it's already happening to some degree. If a nation state wants a backdoor, what better way than to bribe the cash-…

  20. comment
    Comment #17708705

    It’s a pretty unfortunate state of affairs. Google/Microsoft/Amazon should be throwing money at these projects. It’s in their best interest if they use it.

  21. comment
    Comment #17708399

    General rule of thumb for secure package distribution: 1. Is the identifier mutable? Make sure it points to a content addressable identifier (SHA2), and sign that link. 2. Is it a …

  22. comment
    Comment #17707069

    I wrote more about this in https://twitter.com/vesirin/status/1026807849970614273?s=21 . Vulnerabilities in package managers is a scary thing.

  23. comment
    Comment #17686493

    If you have a recent MacBook, use https://github.com/ntrippar/sekey for SSH keys. Private key is stored in the built-in HSM (Secure Enclave) and access is controlled by biometrics …

  24. comment
    Comment #17361846

    How does this differ from the existing "Message deletion/retention" feature that was present before this? Did the existing feature delete messages, but not keys? Is the old feature…

  25. comment
    Comment #16527406

    > Most important concept #1: DAG Yes! Thank you! This needs to be banged into peoples heads when talking about build systems. Every time you add an edge, you're automating an other…