Hacker News: bojo

New comment by bojo in "Why I love NixOS"

bojo — Sun, 22 Mar 2026 22:58:19 +0000

That's a solid point.

I knew my flake setup could be better but never bothered. Then one day earlier this year I threw Claude at it. Not only did it improve everything, it fixed a small bug that had been bothering me.

My confidence in doing this came from exactly what you said: If it blows everything up I can just rollback.

Learning What Will Happen Next: Predictive Coding in Hyperspace

bojo — Mon, 02 Mar 2026 20:44:53 +0000

Article URL: https://blog.brojo.ai/learning-what-will-happen-next-predictive-coding-in-hyperspace/

Comments URL: https://news.ycombinator.com/item?id=47223792

Points: 1

# Comments: 0

Learning to Hear: Bootstrapping Auditory Cognition Without a Teacher

bojo — Fri, 27 Feb 2026 16:30:09 +0000

Article URL: https://blog.brojo.ai/learning-to-hear-bootstrapping-auditory-cognition-without-a-teacher/

Comments URL: https://news.ycombinator.com/item?id=47182439

Points: 1

# Comments: 0

New comment by bojo in "Show HN: Opty – A Zig-based HDC that reduces token use by up to 90%"

bojo — Thu, 26 Feb 2026 02:38:16 +0000

Perhaps? I just used it to analyze one of my 96k Zig codebases using Claude Code and here is (part of) what came back. (I snipped out the deeper analysis above as it exposes my private project - but it was all correct).

  Head-to-Head

  ┌──────────────┬─────────┬─────────────┬────────────┐
  │    Metric    │  Opty   │ Traditional │   Ratio    │
  ├──────────────┼─────────┼─────────────┼────────────┤
  │ Input tokens │ ~13,500 │ ~39,408     │ 2.9x fewer │
  ├──────────────┼─────────┼─────────────┼────────────┤
  │ Tool calls   │ 21      │ 61          │ 2.9x fewer │
  ├──────────────┼─────────┼─────────────┼────────────┤
  │ Round trips  │ 5       │ 9           │ 1.8x fewer │
  └──────────────┴─────────┴─────────────┴────────────┘

I had it run a separate analysis using traditional vs. opty and count the actual tool calls and input token counts. My prompt was basically, "do a full analysis of this entire codebase."

Show HN: Opty – A Zig-based HDC that reduces token use by up to 90%

bojo — Wed, 25 Feb 2026 21:29:18 +0000

I kept seeing people all over social media talking about how they were making custom local-LLM systems to help reduce the token load injected into their context window.

On the side my recent project has me looking at Hyperdimensional Distributed Memory. I couldn't help but wonder if I could make an MCP server to improve token usage. Sure enough, using a combination of HDC + TOOL format, I was able to get opty's own self audit down by 93% in token usage.

Still experimenting with large codebases but feel pretty good about how this should drive overall token usage down.

Happy to hear any feedback.

Comments URL: https://news.ycombinator.com/item?id=47158143

Points: 4

# Comments: 4

Graph to Hyperspace: How Daimon Replaced Knowledge Graph with 10k-Bit Vectors

bojo — Tue, 24 Feb 2026 20:05:57 +0000

Article URL: https://blog.brojo.ai/from-graph-to-hyperspace-how-daimon-replaced-its-knowledge-graph-with-10-000-bit-vectors/

Comments URL: https://news.ycombinator.com/item?id=47142142

Points: 1

# Comments: 0

Show HN: Building a Low-Power Cognitive Architecture That Learns Without LLMs

bojo — Sun, 22 Feb 2026 21:32:22 +0000

I've been obsessively tinkering for weeks on Daimon, my pet little non-LLM AI realtime cognitive machine. Still trying to figure out what it can actually achieve besides be a massively fun time sink for me.

~32,500 lines of Zig written with me at the helm of Claude Code.

More research than I can even fathom across computer science, cognitive science, neuroscience, and more. As the post points out - I've lost the ability to actually reason about what is going with its internals. I'm just the high-level architect making suggestions at this point.

Comments URL: https://news.ycombinator.com/item?id=47114919

Points: 2

# Comments: 0

New comment by bojo in "Ask HN: What are you working on? (February 2026)"

bojo — Tue, 10 Feb 2026 00:16:31 +0000

I appreciate the feedback. I have been talking to a lot of people about the very same point you make and had a lot of good brainstorming sessions.

I introduced functionality to do it once per week, or specific days, and not just every day to partially alleviate the process if it gets tedious.

More importantly, I see two things:

1. If people have a constant score over time, that should lead to a discussion. I'm not sure what, but it aligns with the goal - get them talking to each other and asking if everything is truly ok

2. If a manager doesn't invest themselves in the process, then yes, it just turns into a "keep the lines aligned" game. I have no fix for this, but those people probably weren't the target of this product anyways

I keep going back and forth on it. In certain lights it genuinely seems useful. In others, hard to say.

It was fun to build. I'll keep tinkering with it for now and see where it ends up later this year.

New comment by bojo in "Ask HN: What are you working on? (February 2026)"

bojo — Mon, 09 Feb 2026 16:51:45 +0000

Humetrical ( https://humetrical.com ) -- A wellness platform that puts people's mental health first by showing work metrics that matter. Because burnout blindness leads to exit interviews.

It wasn't until we had a leadership retreat at my day job with a fantastic speaker (Woodrie Burich) that the idea for my platform spawned. She talked about how the $50B wellness industry is doing it wrong. Your company is giving you useless yoga stipends, when truth is they should be paying attention to your overall well being. One idea she presented that resonated with me was using a traffic light-like system to gauge where your employees are mentally at.

I took that to heart and verbally applied it to my team. Then I realized that a platform would give better visuals of the data and be easier to incorporate into everyone's day to day. A couple months later I finally released it.

Show HN: Humetrical – An Improvement on Team Wellness

bojo — Wed, 04 Feb 2026 15:49:32 +0000

Late last year, my day job had an end-year leadership retreat. The one thing that really stood out to me, a line manager, was our speaker. She talked about the $50B wellness industry and how it was doing it wrong. How they give you $75 yoga stipends for the month, but don't actually address the critical people problems the company is blind to. How we're paid to ignore the problem and just accept that everything is ok.

Imagine this: You are a manager, under a director, trying to explain why things are grim. Your director tells their upper management things are fine. Your team is on absolute fire, because no one listens to them, and everyone above their manager thinks things are fine. Things are not fine. The director never does skip 1:1s. Or at best, they ask good questions when they are available, but don't touch on the heart of what the team is suffering from. This was my last year, literally - it sucked.

I've worked this industry for 26 years now. As of today, 10 years as an EM. Maybe my own problem is that I inject too much compassion into my teams, but the truth is, they are the reason I exist. Their success is my success. Why wouldn't I support them?

My own experience left a bitter taste in my mouth and I really wanted to fix it. So, I built https://humetrical.com over this winter. It's basic, but I'd like to think it hits a lot of points competitors don't. What the heck is the point of annual surveys? It's a single data point. Why not try for daily (or weekly, or specific day) questions that genuinely ask what is up with you, as an employee? That give a chance for leadership to see what they aren't seeing, should they care to look?

I'm using this with my own team right now every day. Originally, I was just doing this verbally using "traffic light colors" and recording it in my notes, but realized I wanted it automated and data points to show what was really going on. I'm not sure this will completely solve my own pain point unless I try to get the rest of my org to use it, but we'll see.

Anyway, I appreciate any feedback from the HN crowd, and am happy to discuss anything else in more detail. The tech stack is kind of boring: React, Rust, fly.io. I think this is the first time in my life I cared more about the product than the tech it took to build it.

Comments URL: https://news.ycombinator.com/item?id=46887307

Points: 2

# Comments: 0

New comment by bojo in "Contracts in Nix"

bojo — Mon, 02 Feb 2026 04:56:33 +0000

Sorry to be that guy. I love nix, I want to read more about how people use nix.

The font presented under NixOS + Firefox is near unreadable on this website.

New comment by bojo in "A few random notes from Claude coding quite a bit last few weeks"

bojo — Wed, 28 Jan 2026 15:36:45 +0000

What kind of costs are you thinking?

New comment by bojo in "A few random notes from Claude coding quite a bit last few weeks"

bojo — Wed, 28 Jan 2026 00:40:51 +0000

In case anyone is curious, here was my epiphany project from 2 weeks ago: https://github.com/boj/the-project

I then realized I could feed it everything it ever needed to know. Just create a docs/* folder and tell it to read that every session.

Through discovery I learned about CLAUDE.md, and adding skills.

Now I have an /analyst, /engineer, and /devops that I talk to all day with their own logic and limitations, as well as the more general project CLAUDE.md, and dozens of docs/* files we collaborate on.

I'm at the point I'm running happy.engineering on my phone and don't even need to sit in front of the computer anymore.

New comment by bojo in "A few random notes from Claude coding quite a bit last few weeks"

bojo — Wed, 28 Jan 2026 00:33:57 +0000

I've been an EM for the last 10 of my 25 year Software Engineering career. Coding is, frankly, boring to me anymore, even though I enjoyed doing it most of my career. I had this project I wanted to exist in world but couldn't be bothered to get started.

Decided to figure out what this "vibe coding" nonsense is, and now there's a certain level of joy to all of this again. Being able to clearly define everything using markdown contexts before any code is even written has been a great way to brain dump those 25 years of experience and actually watch something sane get produced.

Here are the stats Claude Code gave me:

  Overview                                                                                       
  ┌───────────────┬────────────────────────────┐                                                 
  │    Metric     │           Value            │                                                 
  ├───────────────┼────────────────────────────┤                                                 
  │ Total Commits │ 365                        │                                                 
  ├───────────────┼────────────────────────────┤                                                 
  │ Project Age   │ 7 days (Jan 20 - 27, 2026) │                                                 
  ├───────────────┼────────────────────────────┤                                                 
  │ Open Issues   │ 5                          │                                                 
  ├───────────────┼────────────────────────────┤                                                 
  │ Contributors  │ 1                          │                                                 
  └───────────────┴────────────────────────────┘                                                 
  Lines of Code by Language                                                                      
  ┌───────────────────────────┬───────┬────────┬───────────┐                                     
  │         Language          │ Files │ Lines  │ % of Code │                                     
  ├───────────────────────────┼───────┼────────┼───────────┤                                     
  │ Rust (Backend)            │    94 │ 31,317 │     51.8% │                                     
  ├───────────────────────────┼───────┼────────┼───────────┤                                     
  │ TypeScript/TSX (Frontend) │   189 │ 29,167 │     48.2% │                                     
  ├───────────────────────────┼───────┼────────┼───────────┤                                     
  │ SQL (Migrations)          │    34 │  1,334 │         — │                                     
  ├───────────────────────────┼───────┼────────┼───────────┤                                     
  │ CSS                       │     — │  1,868 │         — │                                     
  ├───────────────────────────┼───────┼────────┼───────────┤                                     
  │ Markdown (Docs)           │    37 │  9,485 │         — │                                     
  ├───────────────────────────┼───────┼────────┼───────────┤                                     
  │ Total Source              │   317 │ 60,484 │      100% │                                     
  └───────────────────────────┴───────┴────────┴───────────┘

New comment by bojo in "If you're going to vibe code, why not do it in C?"

bojo — Tue, 09 Dec 2025 22:39:21 +0000

I feel like a grandpa after reading that comment now.

New comment by bojo in "Why I love OCaml (2023)"

bojo — Fri, 07 Nov 2025 17:21:11 +0000

My team still has 8 year old Haskell systems in production. We pivoted away from the language a few years ago, which I discuss here a bit: https://news.ycombinator.com/item?id=37746386

I personally love ML languages and would be happy to keep developing in them, but the ecosystem support can be a bit of a hassle if you aren't willing to invest in writing and maintaining libraries yourself.

New comment by bojo in "Ton Roosendaal to step down as Blender chairman and CEO"

bojo — Wed, 17 Sep 2025 23:07:36 +0000

I have a similar sentiment. While attending university and learning Maya on SGIs, I recall finding Blender in 1997 and chatting with Ton a little in their IRC channel. Was never able to make a career out of it, but I sincerely miss how kind and helpful everyone was.

New comment by bojo in "Chat Control Must Be Stopped"

bojo — Mon, 08 Sep 2025 23:03:04 +0000

This was my thought as well. Back to dumb devices and call it a day.

New comment by bojo in "Go is still not good"

bojo — Fri, 22 Aug 2025 17:55:58 +0000

I recall that one of the primary reasons they built Go was because of the half-day compile times Google's C++ code was reaching.

New comment by bojo in "Ask HN: Who is hiring? (January 2025)"

bojo — Thu, 02 Jan 2025 20:24:18 +0000

I don't work here but have some insight. It's difficult for a lot of companies to vet the proper labor and tax laws required per state, and even city, to hire an individual. Some states even require that their rules be blanket applied to your entire corporation, which may not always be feasible.