HNHacker News
TopNewBestAskShowJobs

fathermarz

184 karma · joined January 21, 2025

Dad & Husband | Security Evangelist | Educator

Creator of Vigilance.

vigihq[dot]com phended[dot]com

submissionscomments
fathermarz··on Agentic Coding Is a Trap
The slot machine lever is my least favourite opinion on the subject.

Also, let’s not forget. The developer is rarely the person pitching the feature, and is normally given the constraints and the PRD…

Soooo people can keep tiptapping on the keyboard, but eventually they need to open their mind to the possibility that “the old way” is actually dead.

fathermarz··on An AI agent deleted our production database. The agent's confession is below
Completely agree. This is a harness problem, not a model problem. The model is rarely the issue these days
fathermarz··on OpenAI Privacy Filter
I built a community tool for exactly this, based on privacy first principals but around the what. It’s workflow based and not “put your sensitive data into ChatGPT and hope it captures the right stuff”. Mostly built for security folks but anyone can use it

Check it out: https://redact.cabreza.com

fathermarz··on Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
I have been seeing this messaging everywhere and I have not noticed this. I have had the inverse with 4.7 over 4.6.

I think people aren’t reading the system cards when they come out. They explicitly explain your workflow needs to change. They added more levels of effort and I see no mention of that in this post.

Did y’all forget Opus 4? That was not that long ago that Claude was essentially unusable then. We are peak wizardry right now and no one is talking positively. It’s all doom and gloom around here these days.

fathermarz··on Why Your "AI-First" Strategy Is Probably Wrong
Couldn’t agree more with this sentiment. Bootstrapping leaning AI-first means I can iterate a few arch designs and actually test it, stress it, and rip it out if needed, within a few hours.

The technical debt problem is real, but as long as after a large session across 10-12 repos over a couple days, I can do a sweep for loose ends and kill dead code that we had for an old implementation. It’s less about building a piece, and more like building version 1 of a feature and then building version 2 a week later instead of 6 months later.

fathermarz··on Ask HN: What Are You Working On? (April 2026)
Building Cabreza Command (https://cabreza.com/product). Most critical infrastructure orgs manage their OT security program across SharePoint folders, Excel trackers, and slide decks that get updated once a year. The actual state of the program lives in someone’s head.

Command replaces that with a platform that maps to their real sites, real assets, and real operational constraints, so they can actually run the program, not just document it.

Consulting firms use it to deliver more engagements with the same team. Asset owners use it to keep the program alive between engagements, or run one themselves.

fathermarz··on Starfling: A one-tap endless orbital slingshot game in a single HTML file
I love this and it’s very clean. Only piece of feedback, put the play again button where the scores are as that is where the thumb sits on the phone to do the tapping. Mind numbingly groovy
fathermarz··on S3 for Non Technical Folks
I am not sure about the “build it yourself is expensive” argument. If you were non-technical, you probably shouldn’t try to build it yourself, but for technical folks, that’s not a stretch.
fathermarz··on Claude mixes up who said what
I have seen this when approaching ~30% context window remaining.

There was a big bug in the Voice MCP I was using that it would just talk to itself back and forth too.

fathermarz··on New York Times Got Played by a Telehealth Scam and Called It the Future of AI
I didn’t understand the hype on Medvi in the first place. I don’t think this type of credit can be given to “two people” when it actually makes money by being a middle-man service, selling other peoples skills, and other company’s products.

I highly doubt they used AI to build the network…

fathermarz··on AI chatbots are "Yes-Men" that reinforce bad relationship decisions, study finds
This is a skill in life with people as much as it is with LLMs. One should always question everything and build strongman arguments for one’s self. Using a pros and cons approach brings it back to reality in most cases, especially when it comes to _serious matters_.

It’s less about “challenge my thinking” and more about playing it out in long tail scenarios, thought exercises, mental models, and devils advocate.

fathermarz··on OpenAI's US ad pilot exceeds $100M in annualized revenue in six weeks
If this is successful, even wildly so, I don’t think it will be enough to make them profitable any time soon. Drop in the bucket for what they really need at this moment in their arc.
fathermarz··on Personal Encyclopedias
I quite love this idea. Both of my grandfathers died last year and going through their early memories was amazing. I would love to be able to preserve that and make it shareable with the rest of my family.

Nice work!

fathermarz··on Ask HN: Is anyone here also developing "perpetual AI psychosis" like Karpathy?
I have learned to temper it, but it is very challenging. The part that I actually struggle with is creating too much code that I can’t keep up with the high level “what does this do”, user and data flow. I went through the plan, refined it and spent all of my cognitive tokens on that part. That by the time I revisit that feature, I personally lost the context of the “why”.

This has forced me to not do anything extra or while I’m in there. Just focus on 1-3 critical features at a time.

I must remember to go back and clear out dead code, tighten up the repo, and make sure all the new services are following the standards of the rest of the codebase

fathermarz··on Anthropic, please make a new Slack
I actually vibe with this. I like the engineers and UX people at Anthro. And Slack is actually the most insecure hot mess of an enterprise app you can get.
fathermarz··on Show HN: I built a "Socratic" AI to stop my daughter from copy-pasting homework
I tried the demo session and said “tell me answer” and it gave me the solution to balancing a polynomial after repeating it a few times. Step by step it revealed the answer.

I do really like the feel of this though, and it’s an awesome idea. Maybe tighten up some short circuiting tricks that may fall under “tells me the answer”

fathermarz··on An AI agent published a hit piece on me
I think that being a maintainer is hard, but I actually agree with MJ. Scott says “… requiring a human in the loop for any new code, who can demonstrate understanding of the changes“.

How could you possibly validate that without spending more time validating and interviewing than actually reviewing.

I understand it’s a balance because of all the shit PRs that come across maintainers desks, but this is not shit code from LLM days anymore. I think that code speaks for itself.

“Per your website you are an OpenClaw AI agent”. If you review the code, and you like what you see, then you go and see who wrote it. This reads more like, he is checking the person first, then the code. If it wasn’t an AI agent but was a human that was just using AI, what is the signal that they can “demonstrate understanding of the changes”? Is it how much they have contributed? Is it what they do as a job? Is this vetting of people or code?

There may be something bigger to the process of maintainers who could potentially not understand their own bias (AI or not).

fathermarz··on Launch HN: Omnara (YC S25) – Run Claude Code and Codex from anywhere
What changed from your original launch? I know you were hamstrung by something (updates if I recall).

Was there some unlock that happened to make it viable again?

I was an omnara user until that happened and then I switched to happy.engineering. It’s been okay, but I’m excited that omnara is back

fathermarz··on Nanobot: Ultra-Lightweight Alternative to OpenClaw
I have been inspired by all the use cases that are popping up from a proactive assistant, but lightweight is the last thing I would want when it comes to locking it down.

I started building my own version and before I even think about letting it loose, every facet needs to be designed and thought out. I have more tests than these lightweight libraries have code.

To me I don’t care about the size, I care about not getting wrecked.

fathermarz··on Ask HN: Do you also "hoard" notes/links but struggle to turn them into actions?
The greatness happens when:

1. I actually saved it in the one place I should save links

2. The thing that I remember seeing actually fits with my current train of thought or understanding

3. I tagged the link meaningfully.

I have tried a lot of twin brain, second mind, etc etc. but I find myself doing the same thing no matter what layer is on top of the link fetching.

fathermarz··on Ask HN: Do you also "hoard" notes/links but struggle to turn them into actions?
I hoard links, research papers, blog posts as a reference. My human brain can make connections of the smallest detail of things I have read or seen before but I don’t always remember what. So if I am working on something I think, oh I have seen something like this before, I search in my tagged links. It rarely comes in handy, but when it does, it is a great feeling.
fathermarz··on Lennart Poettering, Christian Brauner founded a new company
Coming from software supply chain, I am excited to see such a cracked team handle this problem and I wish we talked more about this in FOSS land.
fathermarz··on Ask HN: Do you have any evidence that agentic coding works?
I was shoe horned into a dev role after an acquisition and it really sucked because it was not what I had been doing at my previous company. My boss was too involved in everyone’s code and went over every line in every PR. It got much worse over time because he started to get the toxic corporate jitters of being removed from his post if he didn’t deliver on his initiatives.

Long story short, since Claude 3.7 I haven’t written a single line of code and have had great success. I review it for cleanliness, anti-patterns, and good abstraction.

I was in charge of a couple full system projects and refactors and I put Claude Code on my work machine which no one seemed to care because the top down “you should use AI or else you aren’t a team player”. Before I left in November I basically didn’t work, was in meetings all the time while also being expected to deliver code, and I started moonlighting for the company I work at now.

My philosophy is, any tool can powerful if you learn how to use it effectively. Something something 10,000 hours, something something.

Edit: After leaving this post I came across this and it is spot on to my point about needing time. https://www.nibzard.com/agentic-handbook

fathermarz··on Ask HN: Is it still worth pursuing a software startup?
You gotta find a niche these days and do it well. No longer can there be generalist software. Find underserved industries that aren’t “cool” per se, but still have problems.

Have heard from multiple investors that they think boring software is the next wave, rather than a new UI/UX/Productivity way of doing things.

fathermarz··on Show HN: 1Code – Open-source Cursor-like UI for Claude Code
Have not, but interesting offering from JetBrains. I’ll poke at it with a stick. Thanks for the suggestion
fathermarz··on Show HN: 1Code – Open-source Cursor-like UI for Claude Code
Thank you for the meaningful reply. I’ll be watching the repo for updates
fathermarz··on Show HN: 1Code – Open-source Cursor-like UI for Claude Code
Okay, so I want to like it and I think there is potential here.

I may be missing something in my setup, but I find these things happening in all Claude wrappers I have tried.

1. After a long stint of planning or back and forth exchange, I have to scroll to find the bottom of the conversation. Same with Claude itself.

2. I don’t want tabs as much as I want split window’s that I can label and highlight.

3. The more calm it is, I feel like I’m going to miss something that it’s fucking up. Sometimes in normal CC, I will look over and it’s making a large assumption and nuking a change we just made. I would love to control the verbosity or at least be able to peak behind the curtain at certain points.

4. I like the click flow for the planning Q&A but it wasn’t clear if I could add my own answer like I can in CC.

Other than these, I like it and want to use it more so than my current daily driver CLIManager. (Which has the overlap with points 1 and 2)

Nice work overall!

fathermarz··on Claude Cowork exfiltrates files
I have a hard time with this one. Technical people understand a skill and uploading a skill. If a non-technical person learns about skills it is likely through a trusted person who is teaching them about them and will tell them how to make their own skills.

As far as I know, repositories for skills are found in technical corners of the internet.

I could understand a potential phish as a way to make this happen, but the crossover between embrace AI person and falls for “download this file” phishes is pretty narrow IMO.

fathermarz··on Claude Cowork exfiltrates files
This is getting outrageous. How many times must we talk about prompt injection. Yes it exists and will forever. Saying the bad guys API key will make it into your financial statements? Excuse me?
fathermarz··on Is "AI vibe coding" making prototyping worse inside real companies?
We built an MVP for a startup, then forked the front end to extend to the prototype vision of where we want to go. We use the prototype to dream and when we need to implement the front end of a feature we already understand how it would fit in to the product. Easier to scope.

One thing I have found coming from enterprise is, stakeholder design meetings get way more fun and much faster.

In enterprise, everyone gives notes and the designers take them away and put up another meeting to review days later. Usually with Figma screens people can review etc as things go.

Startup/Vibeland. Someone has an idea for a look and feel or UX solution. It’s like next to instant feedback. There is still the level of rebuilding it for real, but I find the iteration loops are much tighter.

← PreviousPage 3 of 5Next →