Author: com

claud’n and codex’n and all the ai’s eryday
as a builder, I have various projects going all the time and the all-the-time driver is claude, with chatgpt/codex creeping up in usage, and various other models that I’ll write about later.

every week – shoot – nearly everyday there is updates and improvements, so embracing the new and the change with these tools is the way to go. yes its all about tokens, and that continues to ramp up exponentially as the frontier models burn thru them like high-test gasoline.

how do I track everything in the age of various contexts / full-stacking / solo-builder-prenuering?

ai

😆

all jokes aside, a handful of the thing I do
- plan everything – like really – work thru initial idea by creating document(s) of what you are doing. I built my scaffolding grovv-stack to walk me thru my idea and build out a brief, product spec, tech spec, and further documents to lay foundations.
- use an issue/item tracker of some-kind – text file in the repository, GitHub issues, linear, whatever … make sure you can track things per project.
- then of course connect your model of choice to that tracker. chat to go thru your project to summarize status, re-focus priorities, or any way you work best.
- I have agents and skills that make sure to keep documentation & the tracker up-to-date, and in some cases also have a simple HTML “board” listing out everything – including a focus and blocker list. will have to share some of this in future post
sounds simple, but it goes a long way to have your knowledge graph documented instead of just figuring it out as you go (whatever works best for you tho, I engineer.

have fun

👋

Døn
August 10, 2026
mistral vibe is a good vibe

back to going down journeys of ai cli tools, this weekend was mistrals vibe. I’ve been a long time occasional user of mistrals le chat (now just “vibe” and had to try out the CLI.

simply put, good vibes. affordable. quick.

for this post, I just focused on adapting my grovv-stack “harness” for vibe, and circle back to the codex also since I’ve been running that cli lately also as I’ve been burning thru my claude max 20x plan with fable, which with opus 5 now its “cheaper” / more work for the usage.

I mean yes it’s nothing “complex” copy/pasting (to be unfair) of the existing claude setup, but I just really liked that table above – even if not the most efficient way of handling my harness which I have since corrected. reviewing the PR, did ok. (again just analyzing / adapting stuff) the overall flow of the cli is really what I’m referring to. will see once I have it do more “complex” things.

I think this will be creeping into my daily driver usage, and just thinking about having a docker setup already with everything or getting back into sprites.dev again b/c ya know you gotta sandbox. 🏖️

vibe on.

👋

Døn

July 26, 2026
Opus 5 and I tackool things.

opus 5 has been good, but seems to have forgotten how to spell a couple times. I think it meant “tackle” and said “tackool” … 🤔

agi is so coming

👋

Døn

July 25, 2026
claude status would be a cool shirt

checkout that nice colorway… feels very 1970’s comfy couch.

switching over to another model … shatgpt or something.

👋

Døn

July 24, 2026
quick intro to grovv – my builder stack

grovv (pronounced grow) at grovv.ai is now live showcasing my build ecosystem. My sorta harness is now live via GitHub and as a Claude plugin. I run it on everything. Keeping it “simple” and improving where I can. It’s an opinionated approach for the way I’m currently building all of my grovv projects. Typescript, node, next, Postgres’s (Supabase or neon) and handful of other things I’ve been getting into as I build out a loose loop approach — because let’s be honest the latest frontier models are token burners and will still go off the rails if you don’t watch em.

nothing novel here, just a dude building.

👋

July 19, 2026
fable 5. It’s cool, def thinks a lot / token burn

I was most excited about getting features like /workflow /goal and essentially running “deep complex work” and of course being on the loop train. But there is something to be said for knowing how a model behaves and what the output you can expect. Don’t get me wrong, Fable 5 has been pushing out some work for me, but I’m not totally sold on it being so awesome / mind-blowing crazy.

of course I ran thru my weekly usage in a couple days when it came back to Claude after being grounded by the US government… and I couldn’t help spinning up sessions to work on projects I had stalled on to see how it would go…

no real point to be made here – it’s done some good stuff for me, but I think also because I’ve been improving my harness and implementing / riding the whole loop train 🚂 which has been more of a step change than the model itself.

Will share my “grovv-stack” setup soon and how I’ve been loopin’

👋🚂

Døn

July 8, 2026
harness eh? when’s the lasso?

in the ongoing ai development world, there is now the “harness.” all the things for your agent to use automatically so you don’t have to tell it. its mostly markdown content, but then you get fancy with scripts that run in loops and “remember” for you.

goodtimes.

always wondering what the next word to define an ai thing. prompt, skills, harness … maybe we are building up to horsey on the ranch.

👋

Døn

June 9, 2026
cognitive load when agentic engineering, and looks like full-stack is back

many other folks have written about it, but just adding my own notes. with cloudflare recently announcing a layoff of ~20% of their workforce and notably a concept/practice of moving to a “team of one” approach where engineers essentially become “full stack” … yeh bringing that back it seems. essentially loading on various types of work into one person that would have previously been many, of course with the heavy-help of Ai.

now, full-stack wasn’t so bad, but you could definitely tell when a person leaned a specific way in their knowledge; e.g. design, devops, coding, etc.. even project management/organizational skills. now, we are seemingly standardizing some roles with Ai deep in the mix. So now now, from my perspective it’s the solutions/thinkers-heads that can capitalize and really drive value because they can “get it” by digging in and relying on their skills for comprehension, and just doing.

Of course those with varying levels of risk aversion will go different distances, and almost like “we” are encouraging taking risks again… the ol “just ship it”

back to cognitive load. of course the full-stackers can “do all the things” but at what cost? a big or little bug? stress? burnout? we’ll see, but probably a mix of all of it.

feeling like I’ll have followups to this topic…

👋

Døn

May 10, 2026
recent annoying ai things: Claude Opus 4.7 – API Error: Stream idle timeout – partial response response received

Since Opus 4.7, I’ve increasingly ran into a stream idle timeout while using claude code via desktop or mobile apps. as of this posting, things are better, but was a rough couple weeks with roll-out of opus 4.7.

I even got involved at https://claudestatus.com and saw similar issues pop-up.

Seemingly was only to do with cloud containers/environments when using the apps, as using Claude Code terminal and VS Code extension worked well.

just a little gripe post, but it gets better over time.

👋

døn

May 9, 2026
claude agent teams – agentic fun

a number of ago after claude released agent teams, I dove in to check and see how the ol agent teams would work. good fun… parallel frenchmen doing their thing based off a shared to do list.

testing with my “grovv stack” scaffolding for projects and was able to get six running around doing stuff.

the claude cli has some cool outputs to keep you updated

I now have agent teams setup in my settings.json for my gro\/\/ stack for all projects and it generally works well, including using the claude desktop and mobile apps.

March 28, 2026