I don't.

The creator of the pi harness did say that the claude system prompt changes often enough that he had to build his own tooling to try and improve reliability and repeatability.

I'm not convinced the differences in roles I've observed are claude personality differences as much as humans giving different prompts.

The real world is more complicated than that. For example, we still have a Windows 7 machine in my office. It has some very expensive but still very useful software locked to it that has no direct replacement available on either Linux or Windows 11. Obviously we have to be careful about security and controlling access to a legacy OS like that.

Blunt statements about "forcing an upgrade" are worthless in this kind of situation. Chances are anyone who is still using a system like that has a good reason for it, at least if it's in use professionally. We buy these assets because they solve problems. Those problems might or might not have a useful and cost-effective solution available on a different platform. If there is no modern solution available and the original still works, your statement that "the old ways are obsolete" is by definition false.

What you do need to do is rationally assess the risks and the threats you face and provide other ways of mitigating the risks and protecting against the threats if you can't rely on, for example, a legacy OS that no longer gets security updates to be secure by itself. But then ideally you shouldn't be relying on any single device or piece of software being secure as your only line of defence anyway, and assuming you already have some degree of defence in depth, accommodating unusual requirements is more a redistribution of security responsibilities than a fundamental change of approach.

Yes, it does look like we broadly agree here.

I suppose the main thing I'd have said very differently is the terminology, in that I wouldn't regard the kind of incompetent senior as a senior in the first place. But then I'm pretty old school about this: to me, a junior developer needs quite close supervision to produce useful results, a regular/mid developer can perform routine tasks with minimal supervision but might need more help with larger or more complex tasks, while a senior is someone you can give more or less any task on your project to and they'll figure it out, and senior is also the level of someone who would be capable of supervising and training a junior.

We've had a wave of people, particularly since the tech boom during COVID, who have obviously been over-promoted due to the employee's market and title inflation. They might now have titles like "senior" or even "lead" or "staff", but they don't have the skills and experience to operate successfully at those levels. I agree the acceleration of everything due to increasing AI use tends to show these people up and I agree that a good mid-level developer using AI might well outperform them. But then I suspect in reality a good mid-level developer was probably outperforming them before AI as well, it just wasn't so obvious.

How do you decide to trust code you write?

How do you decide to trust code someone else wrote?

Tests. Design discussions. Code reviews. Code review questions. Design Questions. "What about this problem?" Real validation testing.

I was in a funny situation last week. Two different humans told their claude agents to fix the same bug. Claude came up with two _slightly_ different implementations.

I told _my_ claude agent to code review both implementations - using a new prompt I'm working on to try and automate away a lot of the code review value I was adding manually.

Same model; same bug, two implementations, and the code-reviewer agent found different bugs in both PRs.

We ended up blending the best things from both PRs into the one that shipped.

I am really confident that the code I ended up shipping here is better than what our specific humans would have done without using AI, and 10x-100x faster.

I am spending more of my time telling agents how to think like me, what to look for, what tradeoffs to make, etc. They wont do those things unless I tell them to. They don't always do those things perfectly.

(Neither do the real human software engineers who work for me.)

That is wildly optimistic IME. Frontier models do a great job of sounding authoritative on any given subject. This is not the same as actually having expert-level knowledge and understanding, and the choices the models make when you ask them to implement something can and often do reflect that. There are several domains I've worked in over the past few years where AIs lack even basic knowledge an expert practitioner would have, probably because these fields are too specialised to have a lot of books available or papers published, so presumably there hasn't been much subject-specific content to train the models on.

I don't think it's usually about what AI "did really badly on" at this point. It's more about whether the overheads of adding all the guard rails and then reviewing and correcting all the output end up costing at least a similar amount to just writing the code yourself.

For a junior developer, I'd say frontier models passed their standard some time ago. Today's LLMs routinely write code at the level of a competent junior-mid but with the advantage of an inhumanly broad knowledge base.

For a good senior, I'm much less convinced. The frontier models are hit-and-miss when it comes to writing good test suites, which matters a lot when they rely on tests so heavily to reach acceptable quality. IME, they are still mostly miss when it comes to the business insight that seniors will take into account and design/architecture decisions that keep the code manageable as it evolves. While they have become much better at recognising existing patterns in the code, and I would say they follow them reasonably well the majority of the time now, there are still bizarre anomalies that creep in, and they aren't very good at extending those patterns when necessary.

I think AI advocates also tend to underestimate just how much time it takes to properly review what they are doing. Take a half-day Claude session to implement some new feature. It might take half an hour to give it the initial brief and then review its plan. Make a few edits and it'll propose a new plan that is also long and detailed and has no edit markings to show what it changed so you have to review the whole thing, carefully and in detail, again to pick up the minor changes it also made for no obvious reason. Then you let it start doing its thing. You can't really leave it unattended for long because it'll stop to ask questions. Some of those questions might be whether it can run a screenful of ad-hoc Bash script to make some edits to your source files, because for some reason it decided not to show the actual edits as it usually would, so now you have to figure out what all the sed incantations are actually going to do while looking at those files in another editor or just trust it and then review all the changes properly later anyway. Sometimes it decides to change its plan mid-flight, but not always in a good way, and if you interrupt it to apply corrections or redirect, you break the neat plan flow it was in. Then you get to the end and you can finally see how everything it has done fits together, and you still need to review everything with the same care as you would with a junior developer's code and probably apply a few fixes where it's come up with weird names or not quite followed a pattern or imagined some instructions that were never there and made other changes in other parts of the system that should be out of scope.

If you read to the end of that last paragraph, you know how I typically feel at the end of a half day working with an agentic UI. And the thing is, I do those sessions as experiments fairly often to keep up with progress, but a lot of what I do is still written by hand, which gives me simple, objective data to compare the two ways of working and see whether the AI tools are really making me more productive once you take everything into account.

Currently, based on objective data comparing similar fully completed development tasks like for like, I still outperform agentic workflows using frontier models by about 25-50% on average, and I don't have to pay anyone extra fees to do that, and subjectively I also find it more engaging to work that way. So I don't really buy the hype about AIs making us all orders of magnitude more productive unless you're happy to YOLO everything forever and take the much-discussed risks that comes with.

Personally, I think the optimum use of LLMs right now is probably not to use them for the whole coding workflow like that or rely on agentic tools, but to use them for tasks like answering quick questions about the existing code, doing research like a fancy search engine, writing a first draft of some boilerplate, and writing quick and dirty throwaway code for experiments, one-shot tools and the like, where you don't really care about the quality as long as it gets the job done and you will see immediately if it has in fact got the job done. For these things, the LLM can read and type faster than me, and that's useful.

Use a paid subscription to a frontier model. Make sure it knows how to run your build and run your tests.

If you're worried, have it write tests. Look at the tests; see if they look like the right tests.

Tell it to ask you questions if it needs to resolve something ambiguous. Have it explain what it thinks it should do to the code. Ask it probing questions if you aren't sure it understands. Ask it about design tradeoffs.

I have yet to find a problem where AI generated code doesn't get me at least 90% of the way there. Multi-domain, multi-language, multi-platform. That includes stuff I was doing a year ago. It's gotten dramatically better in 2026.

If someone has an example of a software engineering problem that AI actually did really badly on, I would like to know the model and see the prompts. I'm not saying it doesn't exist. I'm saying I haven't seen it yet, and I'm really curious.

I've done software development professionally since the 1990s. I started coding on the Apple ][ in 5th grade. I've had AI do the wrong thing, or misunderstand something, or miss something that seemed obvious to me. But on all of those same criteria; I've had human software engineers do far worse, far more often.

Hello fellow Frame owner.

I bought a Frame 65 just because of how beautiful the display was in Art Mode, and I want pretty art in my house for the 90% of the time the TV would otherwise be off.

I use the "Art Mode", but only with my own sideloaded content.

One thing that stinks is that sideloaded art doesn't support the full Art mode experience; specifically no Metadata. I seeded the display with lots of public domain images of classical and romantic european art (my taste - and why I never considered a paid art mode subscription), and I'm not cultured enough yet to just remember what all of it is. So I wish I could get the tv to show metadata sidecars for my custom images.

The Samsung firmware is garbage. I hate it whenever I accidentally hit the remote button for voice assist or AI assist or any of that garbage.

But the way the display looks when showing paintings is too good to pass up. If i could get a firmware that took out home screen nonsense and disabled 80% of what the TV did, but added metadata display for sideloaded images... it would be perfect.

Why is Palmer Luckey a "creep"?

Are you a TikTok girl or something?

Have you actually looked into his relationship habits?

He is a huge anime and retro video game nut. He married a cosplayer. (He did a little cosplay himself). They've been married since 2019 and have a kid together.

He won at life, basically.

Don't you have to roll trucks more frequently for copper though?

It looks like the OPEX for FTTH vs Copper broadband is actually quite a bit lower.

This has to do with better basic reliability of FTTH vs Copper, and possibly some energy and field equipment savings.

Anyone in the industry actually know?

So It sounds like if Comcast had invested more in FTTH upgrades (high CAPEX), they'd now be enjoying the lower OPEX that their competitors are theoretically enjoying.

Upgrading infrastructure to FTTH is high CAPEX, but there's usually federal money to help with that in the US, and, there are always very favorable tax and accounting rules for CAPEX spending.

It looks like Comcast's problem is that they are irrationally married to an outdated business model and outdated technology. If they get priced out of the market, "the system worked"

it could also be price anchoring. they could know the price is BS but they are anchoring something unrealistic now to help later.

if we spend the next 2 years thinking the next xbox is going to be $1800, when it launches for $999, some people will be overjoyed at the great deal they are getting.

but their concerns were ultimately proven correct, over and over.

there were significant LPEs in other OSes that were exploitable because of kernel lock bugs and race conditions.

and since the smp days, entire new classes of bug (eg info disclosure because of observable side effect bugs in cpus w parallel speculative execution) have also been invented as new processor architecture features have become common.

concurrency is still hard, 30 years later.

Take absolutely any business.

Add "instant, real support by competent Americans"

Loudly proclaim that your customer service is based on this. Make it a credible promise.

Charge x% more than your competitors.

Congratulations: you have a small, lucrative share of the market cornered. You also have a Moat that is AI resistant.

I only ever contact "customer support" when the company has fucked up and I can accurately explain how and I cannot fix their problem my self.

But Increasingly companies have simply removed any mechanism by which you can contact a human with agency. You are subjected to chatbot humiliation loops until you give up. If they give you phone number, you are on hold, or hung up on, or transferred until you give up.

Latest example: For the last 24 hours, an Azure portal blade that my team uses has been completely non-functional, with a knockout-js error in the Azure portal code.

Their own AI-troubleshooting thing says there is no problem with Azure. [they shipped the org chart, again].

Because we don't have a paid support contract to go with our paid cloud shit, there is no way for me to tell Microsoft there is a problem with the service we buy from them. The AI says there's no problem. Without a paid support contract, there's no "plan B".

(Technically, I can also write a forum post, if I agree to getting data mined and spammed forever. During the signup process, I tried changing my country to Germany, and the automatic opt-in changed to manual opt-in, but the continue button was blocked until I "opted in")

The enshittification is preposterous, and there are a class of people out there who will pay more - sometimes MUCH more - to not be humiliated by incompetence.

Those customers are out there, but where are the companies who want them?

The gutter is filled with thousands of crowns.... waiting for the next king to simply pick one up.

>hurting brown people

This _probalby_ wont get through your confirmation bias filter, but if you look at who trump is giving _pardons_ to, i think the leading groups are:

> jews
> blacks

I don't think white Boomers (never mind white 2A supporters) even register.... with the possible exception of releasing some J6 prisoners.

A lot of the people you dislike, because of who they dislike, and who supported Trump, are pretty upset about all of the "pandering" Trump does to criminal blacks.

So if he's supposed to be a white supremacist president, the majority of white supremacists don't seem to agree.

Most people cannot actually see things from outside of their bias filters.

(ironically enough, Stephen Miller, the main mouthpeice of Trump's "racist" immigration policies, is Jewish... again, much to the consternation of many pro-white Trump supporters)

Obviously, the majority of ammosexual 2a supporters view what ANTIFA, BLM, and anti-ICE protesters are doing as much worse than what the Trump admin is doing.

It turns out that almost nobody is against authoritarian violence per-se. Everyone just wants it done to their enemies instead of themselves.