chrisss395

Love it and used a similar approach to vibe a core banking application for a mid-tier US bank with ~$10B+ in assets. They plan to put it in to production soon. That said, I felt held back by the rest of the org. the entire time because they continue to work the old way...we could have delivered it in a fraction of time and cost.

Seems the same as a hotel - empty rooms benefit no one.

Dumb question: is preventing the module from loading safe to blindly run on, e.g., Unraid, Proxmox, WSL2? Is it possible to break anything?

It's good to know your experience mirrors mine. Developers are moving faster, but the rest of the organization is holding them back because processes and decisions still rely on other parts of the org. Has anyone else observed the same?

Organizations "born in AI" appear to buck this trend for obvious reasons (no legacy org. to deal with). My two cents.

Yes...but isn't his employment contract structured to incent this kind of move? His pay is 100% at-risk in the form of 170M+ stock options that only vest if he hits some astronomical targets.

I'm just not sure his rationale is completely objective given such a structure...

In your opinion, is the lack of attention on security due to speed-bias or not having the expertise? For a startup / sole entrepreneur with very limited resources, what would be your advice?

Interesting idea as someone who spent a lot of my career in aerospace and airlines. If I were running the transformation my initial shortlist would be:

1) Revenue/Route management: re-think the routes with a ruthless focus on sustainable routes with defensible margins.

2) Customer experience and Brand: being an LCC can't come at the expense of customers, i.e., the fare is so cheap we get to treat you like shit.

3) Capital-structure & cost base: you need to right-size the debt, fix liquidity, and ensure you have a durable cost structure (fuel-risk management, etc.)

FWIW in my recent testing I couldn't find a better model than Gemma 4 31B for the price (openrouter only). My use case was taking discussions and identifying business ideas, so somewhat conceptual problem solving type thing.

I would just point out that 10-15 years ago Defense executives were talking about drone warfare (search "The Third Offset Strategy"). I recall an executive client being obsessed with this, and in fairness back then they had lost major contracts because their components (think electronic warfare) were designed for max power, i.e., max size and weight.

Again, this was 10-15 years ago. Now with the Ukraine war everyone acts like it is obvious...and I agree, it has been for awhile. We just never had a theater to test this stuff in. I suspect US defense contractors were on-board for Ukraine and Iran to advance development efforts significantly.

Reminds me of the time developing the 747-8 avionics and the systems engineers started observing a bug where the entire box would just stop randomly, all output stopped, including HW traces...the thing would just halt.

About a month later an engineer decided to turn on all warnings for gcc...and behold a message stating something to the effect of "WARNING: execution will halt upon reaching this statement." The compiled code basically just halted and never returned from the function call (can't remember the specifics).

And that is how we learned not to hide compiler messages.

Architecture diagrams are the bane of my existence right now. I sit there and listen to engineers opine on the different types, levels, details, etc. And all I can think is...

What a TERRIBLE way to store information in an AI era. Diagrams are so...human.

I'm curious if anyone has used this (or similar) to build a production system?

I'm facing increasing pressure from senior executives who think we can avoid the $$$ B2B SaaS by using AI to vibe code a custom solution. I love the idea of experimenting with this but am horrified by the first-ever-case being a production system that is critical to the annual strategic plan. :-/

Do you think pre-AI writing is going to become really valuable because it is free of any AI assistance? If we all start using AI to assist in writing, then pre-AI writing may become important, similar to pre-atomic steel (i.e., https://en.wikipedia.org/wiki/Low-background_steel)

Do folks have any security concerns with Lenovo? An IT leader at a medium-large US bank recently told me they won't use Lenovo due to security risks from Chinese firmware (or something to that effect, referencing and older incident I don't recall). I've only seen such policies with defense players ten or so years ago.

That said, I've owned them personally for 10+ years, so looking for objective thoughts outside repairability as the article covers.

Do you do anything to manage the size of this memory or is that left to the user? I think it would be interesting to make it behave more like real memory and have a way to degrade gracefully, e.g., consolidate old memories to key words only?

Random Tuesday thoughts. Neat work!

I think the author has discovered that coding is not what they actually enjoy.

I was a software and systems developer on cool shit, but I realized I enjoyed solving hard problems more than how I solved them. That led me to a role that is about solving hard problems. Sometimes I still use coding to do it, but that's just one tool of many.

My wife is an insurance litigation attorney and regularly requests social media data from Microsoft, Meta, etc. for people. Generally they hand it over without issue; I think Apple is the only one to have pushed back at times.

Yes to Maggie & Steve's amazingly well written articles...and:

I would love to see Steve consider different command and control structures, and re-consider how work gets done across the development lifecycle. Gas Town's command and control structure read to me like "how a human would think about making software." Even the article admits you need to re-think how you interact in the Gas Town world. It actually may understate this point too much.

Where and how humans interact feels like something that will always be an important consideration, both in a human & AI dominated software development world. At least from where I sit.

This - the electronic warfare assets moved to this region months before were a huge sign of what was going to happen.

I too use this solution, using both Ubunutu LXCs and full-fledged VMs. Only issue I've struggled with has been losing SSH connection on the LXC, and tmux and session both seem to mess up the terminal formatting in CC.

I do agree with the security / cautionary comments and wouldn't leverage this setup outside a hacked together homelab.

You may not have been the target user. I found it intriguing to quickly bring a concept to life for dumb users. I think LLMs significantly lower the cost (barriers) for make something quick and dirty. I'm loving Claude code in an LXC sandbox to take my half-thought out ideas and make me something...most of it is throw-away, but it helps me evolve whatever problem is in my head that I'm trying to solve, and that I find valuable.