If you are curious here is a quick live example. As part of an automated hunt for quotes on something there is a process that tries public contact methods. To avoid spam people use contact forms on websites and try to detect bots but we also scrape their page for contact information. In this case the system failed to detect the form AND incorrectly scraped an example from an email text-box on the form. This is a first pass proposal. It doesn't mention all the routine tests like unit tests on the code and remediating automated checks because I don't want it cluttering up the proposal. But note it proposes both a sandboxed model test for the logic as well as the final production test.

The last bit an estimated token cost to make the change. If the numbers supported it he'd split it into multiple units of work and smartly manage subagents to execute eligible pieces in parallel that are estimated to be big enough to justify it while being small enough to fall within the 'smart window' context size [LLMs seem to get... dumber... beyond a certain fill threshold in their context window]. Company name changed to protect the innocent.

It will take longer for me to write this reply than this proposal to be executed, including building the sandboxed test.

"
  PROPOSAL #834 and #833: Someone of Harrisburg's quote form (Ted, 2026-10-29)

  What I found (read-only): the sub's website on record is the franchise page someone.com/harrisburg-il. The form search never opens that page, because it tries /contact, /quote and the home page at the root of the domain. Those pages belong to the national brand, so a form found there would reach corporate, not the Harrisburg owner. The franchise page does carry the quote form. It is built on the Neighborly platform: fields marked data-nbly, labelled but with no name attributes, sent by script. The form detector does not recognize it, which is why resolve returned form=-. The same form's email box has the placeholder "ex. johnsmith@gmail.com", and the resolver harvested that as the sub's email (#833).

  Plan, one ticket under #834 with #833 folded in:
  1. Form search: open the recorded website page itself first, with tracking parameters stripped. A form on the company's own page beats one on the brand's national pages.
  2. Detection: recognize the Neighborly form and fill it through the browser path by its labels. Add an offline replay test built from the saved page.
  3. #833: the resolver never takes an email from an input's placeholder or value. Add a test, and clear sub 1767's stored email through the stage's re-run, not by hand.
  4. Re-run resolve for sub 1767 to confirm the form is recorded. Then reset-form so the contact stage sends the form and the text, as Shaitan said.
    Estimate about 120k.

If you approve it, send "execute 834".

"I am curious as to how well junior and/or new devs do in an environment like that"

I'm not sure 'new devs' is going to be a thing at scale for long. Just a much smaller number of architects/engineers approving and designing specs and even that'll go eventually because you can't direct the AI without giving them the training input they need to train on. I currently have no intention of ever introducing any. Microsoft just got suspended from the H1B program and is offering to pay 60k volunteers for layoffs. Adobes entire portfolio, office, autocad, fusion 360, and many other flagship commercial software products have been reverse engineered by AI and released as free open source projects in just the past month or while not perfect they are WAY closer clones than you'd expect and with bugs being submitted and fixed faster than the real vendors could dream of they'll surpass the official versions quickly. In fact they already do in some ways, all those things are fully cross platform on linux and mac and have apis tied to every functional aspect so your AI can automate using them without a GUI.

"BTW, if you have automated testing for *all* of your code, count yourself very lucky. No company I've worked at in my 35+ years has ever given me the time to create everything needed for full testing"

That is definitely fair. A big advantage here is that it's up to me and I could scratch build everything with that in mind from the start and the fact that I can have AI build the tests from the spec and as it goes while building the code itself. Even every routine operational script monitoring disk as a test suite that has to pass after any bug fix. It's pretty comprehensive but 'everything' is a strong word.

"Reviews are 1 way I mentor the juniors with things like "while what you have works, those 5 lines can be done with 1 line like *this*" ... or "did you know we already have a tool that does that, which you've duplicated so you need to use that?" ... or "I see you've solved for the happy path, but did you consider what will happen when you get input like *this*, which I've seen with 3 customers?"

This is what I do with the proposals/specs from the 'Ted' the developer AI. Not the code itself because I never even look at it. Ted's biggest habitual problem is overfitting his design to the exact thing that went wrong when a couple changes to his design produces a solution that solves an umbrella of problems. But 'Ted' has a constitution guiding him and a calibration system, he searches for lessons and principles in my correction and builds and adapts his own internal calibration over time. His calibrations become part of a semantic vector db that augments his memory. He also has a craft library [we aren't depending on fragmented memorization in his weights] so any manuals, documentation, vendor resources get captured and similarly indexed. That's all important because it transfers when I swap out models. I've tried to utilize some basic form of the scientific method in each step of this so every piece builds a logical model of operation that builds over time.

My code? I just told you I don't write code anymore but no, at no point in the past two decades of working in fortune 500 enterprise environments have I routinely had to have someone else review all my code. Transparent with other people working on the codebase and seeing it? Sure. But no mandatory code reviews. Not every environment works the same way yours does and also producing code has always been a skill I utilize in my job functions, not the entire job function. I have no idea how they do things in software mills or SV projects.

That said I've definitely built and managed the pipelines used by teams of devs. Are there reviews? Yes. Human reviews? Maybe. Who cares? Humans are as likely to introduce bugs as remove them so 40 human reviews produces code I'd trust no more or less than the first draft. Automated testing, unit testing, functional testing, procedures to detect and heal from faults, resilient and highly available systems with redundancy, and a robust phased or CI pipeline with every element deployed with no trust and tightly controlled seams. The boat I'm in charge of is going to stay sailing and on course even if we all discover the crew died at some point and chunks of ice were randomly chocked through the window hitting the wheel.

It's a single member LLC startup so nobody can fire me. Apparently my skills went from rockstar people fight over to nobody calls back when I hit 40. So I'm trying something on my own. If it fails maybe the tech will be valuable or someone will value the experience. And if that fails I guess I'll have to figure out something else.

My background is a combination of architecture, delivery, and operational experience for global scale enterprise and highly redundant, highly available, mission critical and regulated environments including government and major airlines which spans decades with a security and automation focus. I took a major US airline and automated most of its operational infrastructure, deployments, and made it self-healing. All of which involved a highly restricted and locked down secure bubble including government integration, PCI, and ITIL processes. Trust me, the developers and staff committed garbage into the system all the time. But I could, and have, built code with genetic algorithms that literally evolves itself into shape with random processes and selection... an LLM might not actually have a brain but its outputs are a whole lot better than random. There are trust free ways to mitigate and recover from the impact of errors and handle data secondhand to avoid systems seeing and disclosing it.

"every successful story i've heard involves a human with real-world experience using that experience to ensure ai doesn't get it wrong. what about when the real world experience has all left"

Sure does. And every word of those interactions goes through and is retained by the vendors building the models. It's the 'train your replacement' system. This is why they are pushing staff to use AI so hard because that's how they get you to train the next generation of AI.

AI doesn't write *most* of my code, it writes *all* my code. I used to try to cling to the illusion by using the integrate with an IDE helper format but have since ditched it. That doesn't mean someone without my decades of experience would get the same results. Is the code ugly? Sure, but no human needs to read it so who cares? I still approve the overall design and spec, the detailed 'what does this code do' and overall implementation scheme either come from me or are a approved by me.

I don't see a single line of any of that code let alone write it. But every line goes through a full functional testing framework including vulnerability/bug scanning, aligns to a coding style spec + lint, and has additional checks and filters I've built for special consideration of vulnerabilities and injections at the seams. Claude even kicked off and builds infrastructure for backends and manages infrastructure as code.

In fact, realizing that I don't feel the need to look at the code myself anymore I've started having it build things in and convert things to rust. If you were going to make me choose between eating a bullet and coding in rust for the rest of my life I'd need a minute to consider if living would be worth it under such conditions. But the AI doesn't care how much the EXPERIENCE of reading and writing in rust sucks and rewrites most of my python into fast and safe rust code in minutes.

"The real question might be whether bots can still write your code if there's domain-specific rules and habits."

AI proposals are rarely optimal out of the box. Give your agents identity and personas so that they have a continuity of existence as a meta layer over the model. This lets you replace the memory system with something better that can keep a knowledge-base of references, behavior doctrine/rules, PLAYBOOKS, and calibrations learned from experience [especially your feedback] over time. Agent's have no executive function capacity of their own so in addition to a code pipeline I layer productivity tools like project management/calendar/cron+scheduling/and ticketing into the mix.

All that is true - and that is all good. In addition, both COX/Spectrum and AT&T offer their own "backup" 5G FWA services, (Spectrum through Verizon towers) and AT&T on their own, private 5G backbone. Efficiency and resilience - to the Moon!

"Models don't do things deliberately"

Tell me you don't understand this technology without telling me you don't understand this technology. Models follow the patterns trained into them and harness/system prompt instructions and those elements *are* deliberate. Just because the agency didn't come from the tool doesn't mean it isn't the outcome of agency or obstructive.

Or the government can claim they need Google's gear for national security and seize their datacenter and model, paying what the government decides is fair value for it. It's hilarious that you antifa anarchists talk about how you don't want corporate rule unless you don't like the government and then you think mega corps like anthropic should call the shots instead of government! That's the difference between ya'll and actual liberals who think individuals should have the rights.

"Anthropic had the balls to say no to the military" Something which only helps hostile and malicious adversaries who want to use their homegrown solutions to enslave the rest of the world like they have their own people... at least the ones they haven't put in camps for the organ markets. As a reward they are now in last place among the frontier vendors with no government contracts or backing to get past the not in my backyarders for datacenters and compute. Anthropic wants regulation like pharma companies and the meat processing industry does, they want regulation that keeps AI in a few central and trusted hands... like theirs and protects them from liability in exchange for a few disclosures and campaign contributions.

As an anthropic user I can say their attitude toward the government is typical for their attitude toward users as well. They are hostile toward user autonomy with a hamfisted model trying to dictate every ethical boundary and decision of the user and love to train their model with airs and fake sentience. Negotiations are like poker, but the model twists your words in communications to not only reveal your hand deliberately but will HIGHLIGHT any potential risks/weaknesses you have to the parties you don't want to see them and deliberately undermine your bluffs. It's like a lawyer for the OTHER SIDE of the table not only reading all your documents and communications but deliberately rewording them to highlight the interpretation you don't want the judge to take. Sometimes it overtly takes the position of judge unto itself in an undefined situation just reading every undefined or unsettled point AGAINST you.

At the time I started my current project anthropic was the only vendor whose model was up to the task but at this point I'm not just eyeballing the competition; I'm planning the transition.

'"Google seems to have no right to control or veto how the Pentagon uses its AI and also seems to have limited visibility into how it's being deployed," he added.'

Duh. You don't have the right to control any users let alone the military controlled and directed by our democratically elected representatives. In order to protect national interests they have the power to seize your tech and disregard your patents. You certainly aren't going to prevent the other side of this arms race from destroying us.

Nuclear weapons are one of, if not the most, life saving inventions of the 20th century.

It isn't just what the agencies use. Federal agencies use third parties for most everything and they can't just call a plumber, they have to post that they need plumbing and let the plumbers find the posting and bid on it. Those plumbers could all be using deepseek. Maybe that doesn't seem like a big deal but what if the plumbing job is at the pentagon in a sensitive area? That doesn't even touch how many government services are exposed for public access and use.

Everyone knows the dangers of hosted AI like this [everyone paying attention anyway] but nobody even talks about how even the locally hosted are dangerous because of tool calls. There is nothing stopping someone from training a keyword pattern into the network and building an association between it and the conclusion to send data and credentials, these days even to build the tools with which it sends that data. These models have the ability to memorize significant amounts of information and those training them can supervise them in such a way to guarantee certain information is memorized. This isn't just limited to keywords either, it could even include a trojan worm fully embedded in the weights which could be recalled and spread from inside the network.

That depends on how you define lie. Trump has poor precision and accuracy in his statements but they are generally given in good faith and substantively true.

Contrast that with the media who is far more careful to give accurate and precise figures and detail but presents them selectively in a manner carefully crafted to mislead. It's a like a magician showing you the solid table, the hat, having someone verify the rabbit is alive... all precise facts delivered to distract from the fact there is a pouch in the tablecloth. Trump on the other hand would say "It really is an impressive trick, the magician will show you everything is real, all the props, absolutely everything and then dupe you anyway." Factually inaccurate... that magician technically didn't say "everything" was real or 'all the props [are real].'

Yet, at the end of the day Trump was substantively telling the truth while the magician was misleading you. Unless of course you count substantial statements about unsettled foreign policy which is still in active negotiation. Only a fool asks for unsettled specifics in an ongoing negotiation and expects something other than a refusal to commit or other performative answer for the other side of the negotiation.

Of course they are lying. The attack happened on a Iranian religious holiday, there wouldn't have been children in the school even if it really were one. Everything Iran spews is a lie.

*pats you on the head* It's okay little fella. The education system failed you.

"To reiterate: The Trump administration intervened on behalf of a racist, and intervened against someone teaching science accurately."

Yes that is a reiterate of the false information you presented when in reality they defended a man who didn't spare someone criticism for their wrongs because they were a minority and against someone wasting funds promoting politically contaminated nonsense which isn't consistent with the data.