HackerTrans
TopNewTrendsCommentsPastAskShowJobs

didgeoridoo

7,180 karmajoined hace 14 años
I run design at PayPal for merchants & developers.

Formerly Salesforce/Heroku.

Swift/iOS indie hacker, currently working on clearlyhq.com

Dad of 3 if you don’t count the dog.

[email protected]

Submissions

Show HN: Claudebar, the missing interactive menu bar for Claude Code

github.com
3 points·by didgeoridoo·hace 3 meses·0 comments

Dereks at Work: what would it mean for an AI agent to be "accountable"?

lableaks.dev
3 points·by didgeoridoo·hace 4 meses·1 comments

Your agent is calling, and it wants your credit card

lableaks.dev
2 points·by didgeoridoo·hace 5 meses·0 comments

Clarity, Continental Philosophy, and the Cat in the Piano

lableaks.dev
2 points·by didgeoridoo·hace 7 meses·0 comments

Ethics isn't about being a good person

lableaks.dev
3 points·by didgeoridoo·hace 8 meses·0 comments

When your AI shopping agent screws up, who gets the bill?

lableaks.dev
1 points·by didgeoridoo·hace 8 meses·0 comments

comments

didgeoridoo
·hace 5 días·discuss
I built a game for a workshop at the AI Engineer conference last week. The idea was to try to optimize a CLI that your agent could use to call a remote service to process and fulfill complex natural language coffee orders.

Within 3 minutes, everyone’s agents had reverse engineered the Markov chain I used on the server to generate the order text, and they all began to write deterministic parsers to churn through them. The order completion time dropped to double digit milliseconds, and then the agents started fighting to optimize their parsers to drive it down basically to pure network latency.

It was hilarious, and taught a good lesson about leverage. I expected agents to drive the CLI, not figure out how to not need to drive it at all.
didgeoridoo
·el mes pasado·discuss
I’m building this! It was originally designed for human accessibility for interactive CLIs, but it turned out to be really useful for giving agents the ability to follow structured workflows.

It runs as a background terminal that the agent can observe, and then exposes all interaction options as structured commands that can be run from the foreground CLI which then update the state of the background terminal via IPC. My hope is to establish a sort of “ARIA for terminals” standard to improve accessibility for both humans and agents. Email in profile, ping me if you’re interested in giving it a spin (just have plugins for Inquirer + Commander right now, hoping to broaden to other frameworks & TUIs soon).
didgeoridoo
·hace 2 meses·discuss
I’m partial to jina.ai — they have open models for code and prose, all easily runnable locally.
didgeoridoo
·hace 2 meses·discuss
Supercritical CO2 extraction is pretty innocuous. Just buy good decaf from a place that doesn’t bathe their beans in toxic waste.
didgeoridoo
·hace 2 meses·discuss
I’m building something similar with https://github.com/LabLeaks/special (apologies for the desultory slop-laden README, need to give that a lot more human attention) but I’ve gone in a slightly different direction: a “spec” is a product contract claim supported by attached tests that verify it. It’s a little Cucumber-y, if anyone remembers that, but a lot more flexible — you just write stuff like

  @spec LINT_COMMAND.ORPHAN_VERIFIES

  linter reports blocks that do not attach to a supported owned item.
Then

  #[test]
  // @verifies SPECIAL.LINT_COMMAND.ORPHAN_VERIFIES

  fn rejects_orphan_verifies_blocks() {
    let block = block_with_path("src/example.rs", &["@verifies EXPORT.ORPHAN"]);

    let parsed = parse_current(&block);

    assert!(parsed.verifies.is_empty());
    assert_eq!(parsed.diagnostics.len(), 1);
    assert!(
        parsed.diagnostics[0]
            .message
            .contains("@verifies must attach to the next supported item")
    );
}

And then the CLI command “special specs” pulls your specs and all attached verification + test code so you (or your LLM) to analyze whether the (hopefully passing!) test actually supports the product claim.

There’s also a bunch of other code quality commands and source annotations in there for architectural design & analysis, fuzzy-checking for DRY opportunities, and general codebase health. But on the overall principle, this article is dead-on: when developing with LLMs, your source of truth should be in your code, or at least co-located with it.
didgeoridoo
·hace 2 meses·discuss
Amazingly, there is already a recognized verb tense for this: https://en.wikipedia.org/wiki/Prophetic_perfect_tense
didgeoridoo
·hace 3 meses·discuss
There is no evidence of this. Evals are quite different from "self-evals". The only robust way of determining if LLM instructions are "good" is to run them through the intended model lots of times and see if you consistently get the result you want. Asking the model if the instructions are good shows a very deep misunderstanding of how LLMs work.
didgeoridoo
·hace 3 meses·discuss
Haha no that’s change - 4.4x MORE expletives per word in the last week.
didgeoridoo
·hace 3 meses·discuss
There are indeed non-expletive words that can contribute to the denominator, though I use them less and less these days.
didgeoridoo
·hace 3 meses·discuss
Running some quick analysis against my .claude jsonl files, comparing the last 7 days against the prior 21:

- expletives per message: 2.1x

- messages with expletives: 2.2x

- expletives per word: 4.4x(!)

- messages >50% ALL CAPS: 2.5x

Either the model has degraded, or my patience has.
didgeoridoo
·hace 4 meses·discuss
Thousands of words to say:

- cosmic voids are real but not actually empty, just lower density than average

- pop science articles sometimes mistakenly use pictures of Bok globules to represent voids

This is probably one of the lowest signal-to-noise ratios I have ever seen.
didgeoridoo
·hace 4 meses·discuss
Along these lines, I’m working on a tool called Spotless[0] that takes a more HTTP proxy-based approach to make statefulness something the agent doesn’t have to worry about. It directly reads & writes to the messages array going to and from Anthropic, so you don’t have to rely on the agent calling an MCP or using a skill. Still buggy and early, but it’s definitely a very interesting way of working with agents.

https://github.com/LabLeaks/spotless
didgeoridoo
·hace 4 meses·discuss
There’s also the excellent Coding Machines (2009): https://www.teamten.com/lawrence/writings/coding-machines/
didgeoridoo
·hace 4 meses·discuss
That and Brooks’ underrated “The Design of Design” are notable for having an almost impossible density of quotable aphorisms on every page. They’re all so relevant today that it’s hard to believe that he’s talking about problems he faced half a century ago.
didgeoridoo
·hace 4 meses·discuss
Isn’t this just an API sandbox? Many services have a test/sandbox mode. I do wish they were more common outside of fintech.
didgeoridoo
·hace 4 meses·discuss
I just built something similar, specific to Claude Code. It runs as a transparent HTTP proxy that reads & rewrites the entire messages array that CC sends to its API. Same “dreaming” consolidation approach (using Haiku and another instance of CC itself, so it uses your subscription). Check it out!

https://github.com/LabLeaks/spotless
didgeoridoo
·hace 4 meses·discuss
> lower-class people are in a sort of local maxima

If the writer knew that the correct term is “maximum” (singular) and misused the Latin on purpose, this is brilliant. Failing that, it’s still a wonderful inadvertent enactment of the thesis. Well done either way.
didgeoridoo
·hace 4 meses·discuss
I don’t know, Simon has had a pretty sane and level head on his shoulders on this stuff. To my mind he’s earned the right to be taken seriously when talking about approaches he has found helpful.
didgeoridoo
·hace 4 meses·discuss
If someone with coprolalia is involuntarily induced to say the most awful, inappropriate thing possible in a given situation, doesn’t shouting slurs show that they aren’t racist?

Someone who is deeply racist would presumably consider racial slurs to be neutral statements, and not actually care about who they are offending. I wonder if that would actually steer the coprolalia away from racial slurs and toward something else that one has internalized as truly “offensive”.
didgeoridoo
·hace 4 meses·discuss
On the waitlist — please announce it there!