Hacker News: cowlby

New comment by cowlby in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

cowlby — Sat, 04 Apr 2026 00:47:15 +0000

I just discovered Pi Coding Agent and found that it's lean System Prompt + a tuned CLAUDE.md brought back a lot of the intelligence that Opus seemed to lose over the last month.

Sucks to be pushed back to Claude Code with opaque system behavior and inconsistency. I bet many would rather pay more for stability than less for gambling on the model intelligence.

New comment by cowlby in "Claude Code Unpacked : A visual guide"

cowlby — Wed, 01 Apr 2026 15:44:50 +0000

Vibe coding is also why this was released hours after leak instead of days/weeks.

New comment by cowlby in "Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown"

cowlby — Sun, 29 Mar 2026 15:57:28 +0000

This is one of the things that GitHub Spec Kit solves for me. The specify.plan step launches code exploration agents and builds itself the latest data model, migrations, etc etc. Really reduces the need to document stuff when the agent self discovers codebase needs.

Give Claude sqlite/supabase MCP, GitHub CLI, Linear CLI, Chrome or launch.json and it can really autonomously solve this.

New comment by cowlby in "I am leaving the AI party after one drink"

cowlby — Fri, 27 Mar 2026 17:08:28 +0000

Who else struggles with both sides of this? My engineer side values curiosity, brain power, and artistanship. My capitalist side says it's always the product not the process. My formula is something like this: product = money, process = happiness, money != happiness, no money = unhappiness.

I think the optimal solution is min/maxing this thing. Find the AI process that minimizes unhappiness, and maximizes money.

New comment by cowlby in "Let yourself fall down more"

cowlby — Wed, 11 Mar 2026 17:41:10 +0000

I did some napkin math the other day, and my kids at half my size prob hit the ground with 1/2 the stress that I do. Certainly could take more risks falling with a 50% reduction in harm. The extra rotational energy from 70" vs 40" will do it.

New comment by cowlby in "We might all be AI engineers now"

cowlby — Sat, 07 Mar 2026 01:55:42 +0000

I'm starting to think for software it's produce 2,000 loaves per month. I'm realizing now software was supply-constrained and organizations had to be very strategic about what apps/UIs to build. Now everything and anything can be an app and so we can build more targeted frontends for all kinds of business units that would've been overlooked before.

New comment by cowlby in "We automated everything except knowing what's going on"

cowlby — Tue, 03 Mar 2026 13:58:38 +0000

Ever since Opus 4.6 came out, I've "vibecoded" a bunch of personal apps/CLIs that would've taken me months before. Some examples:

- CLI voice changer with cloned Overwatch voices on ElevenLabs.

- Brother P-Touch label maker using HTML/CSS. Their app is absolutely atrocious.

- Converted a FileMaker CRM into a Next.js/Supabase app.

- Dozens of drag-n-drop or 1-click/CLI tools. Think flattening a folder, a zip file.

- Dozens of Chrome Extensions and TamperMonkey user scripts. Think blocking ads with very targeted xpath.

But when I think about sharing them it feels like what's the point since anyone can make them themselves?

New comment by cowlby in "Microgpt"

cowlby — Sun, 01 Mar 2026 15:50:37 +0000

Isn’t the sustainability drive a function of how much humans have written about life and death and science fiction including these themes?

New comment by cowlby in "Cognitive Debt: When Velocity Exceeds Comprehension"

cowlby — Sat, 28 Feb 2026 17:59:51 +0000

Yes my hot take is that the real risk isn't skill atrophy... it's failing to develop the new skill of using AI. It's all abstraction layers anyway and people always lament the next abstraction up.

0/1s → assembly → C → high-level languages → frameworks → AI → product

The engineer keeps moving up the abstraction chain with less and less understanding of the layers below. The better solution would be creating better verification, testing, and determinism at the AI layer. Surely we'll see the equivalent of high-level languages and frameworks for AI soon.

New comment by cowlby in "How I use Claude Code: Separation of planning and execution"

cowlby — Sun, 22 Feb 2026 04:40:52 +0000

I picture like semi conductors; the 5nm process is so absurdly complex that operators can't just peek into the system easily. I imagine I'm just so used to hand crafting code that I can't imagine not being able to peek in.

So maybe it's that we won't be reviewing by hand anymore? I.e. it's LLMs all the way down. Trying to embrace that style of development lately as unnatural as it feels. We're obv not 100% there yet but Claude Opus is a significant step in that direction and they keep getting better and better.

New comment by cowlby in "How I use Claude Code: Separation of planning and execution"

cowlby — Sun, 22 Feb 2026 02:12:02 +0000

I find “maintainable code” the hardest bias to let go of. 15+ years of coding and design patterns are hard to let go.

But the aha moment for me was what’s maintainable by AI vs by me by hand are on different realms. So maintainable has to evolve from good human design patterns to good AI patterns.

Specs are worth it IMO. Not because if I can spec, I could’ve coded anyway. But because I gain all the insight and capabilities of AI, while minimizing the gotchas and edge failures.

New comment by cowlby in "How I use Claude Code: Separation of planning and execution"

cowlby — Sun, 22 Feb 2026 01:58:36 +0000

I recently discovered GitHub speckit which separates planning/execution in stages: specify, plan, tasks, implement. Finding it aligns with the OP with the level of “focus” and “attention” this gets out of Claude Code.

Speckit is worth trying as it automates what is being described here, and with Opus 4.6 it's been a kind of BC/AD moment for me.

New comment by cowlby in "I found a useful Git one liner buried in leaked CIA developer docs"

cowlby — Fri, 20 Feb 2026 15:46:42 +0000

Anyone else "vibe git-ing” lately? I just ask Claude Opus to clean it up and it does really well. Same for build commands and test harnesses.

New comment by cowlby in "Monosketch"

cowlby — Fri, 13 Feb 2026 19:53:35 +0000

Welllll... I gave Opus 4.6 the repository and a sample .mono export and it nailed the file format. There's something to be said about tools and formats that are easy for human-AI end-to-end operation.

                ┌──────────────────────────────────────┐              
                │        New post hits Show HN:        │              
                │  "MonoSketch — Draw ASCII Diagrams"  │              
                └──────────────────────────────────────┘              
                                    │                                 
                                    │                                 
                    ╭───────────────▼──────────────╮                  
                    ┌┤  Did you read the article?   │─────┐            
                    │╰──────────────────────────────╯     │            
                  No│                                 Yes │            
                    │                                     │            
                    │                                     │            
      ┌────────────▼───────────┐            ┌────────────▼───────────┐
      │     Skip straight      │            │      Hmm, this is      │
      │    to the comments     │            │ actually kind of cool  │
      └────────────────────────┘            └────────────────────────┘
                    │                                     │            
                    │                                     │            
      ┌────────────▼───────────┐            ┌────────────▼───────────┐
      │   Adopt the hottest    │            │   Could I build this   │
      │    take as your own    │            │  myself in a weekend?  │
      └────────────────────────┘            └────────────────────────┘
              │         │                                │            
              │         │                          (alway│ yes)       
            ┌──┘         └────┐                           │            
    ┌───────▼──────┐  ┌───────▼──────┐                    │            
    │  "Just use   │  │"I built this │       ┌────────────▼───────────┐
    │  Vim + sed"  │  │   in 1997"   │       │    Start rewriting     │
    └──────────────┘  └──────────────┘       │ it in Rust, obviously  │
            │                 │              └────────────────────────┘
            │                 │                           │            
            └───────┬─────────┘                           │            
      ┌────────────▼───────────┐            ┌────────────▼───────────┐
      │     Post with mass     │            │ Abandon project after  │
      │       confidence       │            │    exactly 2 hours     │
      └────────────────────────┘            └────────────────────────┘
                    │                                     │            
                    │                                     │            
                    │                        ┌────────────▼───────────┐
                    │                        │    Star the repo on    │
                    │                        │     GitHub anyway      │
                    │                        └────────────────────────┘
                    │                                     │            
                    │                                     │            
                    └────────────────┬────────────────────┘            
            ┌────────────────────────▼───────────────────────┐         
            │          Refresh HN every 45 minutes           │         
            │          to check your comment karma           │         
            └────────────────────────────────────────────────┘         
                                    │                                 
                                    │                                 
            ┏━━━━━━━━━━━━━━━━━━━━━━━━▼━━━━━━━━━━━━━━━━━━━━━━━┓         
            ┃             Repeat tomorrow with a             ┃         
            ┃           completely different tool            ┃         
            ┃                                                ┃         
            ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛

New comment by cowlby in "How to effectively write quality code with AI"

cowlby — Sat, 07 Feb 2026 01:55:53 +0000

Alternatively, another second order effect is can't sip latte anymore because you're orchestrating 8 bots do the work and you're back to 80%-100% time saturation.

New comment by cowlby in "Your brain on ChatGPT: Accumulation of cognitive debt when using an AI assistant"

cowlby — Thu, 22 Jan 2026 18:48:56 +0000

Would be curious about this too. It’s a mental shift to go from understanding everything about the code, to trusting someone else understands everything and we just make decisions.

New comment by cowlby in "TimeCapsuleLLM: LLM trained only on data from 1800-1875"

cowlby — Mon, 12 Jan 2026 19:47:13 +0000

I wonder if you could train an LLM with everything up to Einstein. Then see if with thought experiments + mathematics you could arrive at general relativity.

New comment by cowlby in "Understanding the bin, sbin, usr/bin, usr/sbin split (2010)"

cowlby — Sun, 04 Jan 2026 16:02:47 +0000

Obligatory XKCD Standards https://xkcd.com/927/

New comment by cowlby in "Microsoft please get your tab to autocomplete shit together"

cowlby — Thu, 25 Dec 2025 02:31:30 +0000

Powershell right arrow is madness… just found out F2 shows all the options though and finally it’s a little more tolerable

New comment by cowlby in "I couldn't find a logging library that worked for my library, so I made one"

cowlby — Fri, 12 Dec 2025 23:49:25 +0000

This feels a bit like a pub/sub pattern; I wonder what it would look like with a full pub/sub implementation.