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.)

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.

I fly 200ish flights a year so figure 70-80 nights away.

2025 was 100% hotels but 2019 was about 80% Airbnbs.

Airbnb will never get my business back. Ever. The professional scammer hosts are so good at finding a way to nail me for a fee. Iâ(TM)ve taken perfect check out video and still had to spend hours fighting fees.

Airbnb allowed making guests do it.

They lost so much money to hotels theyâ(TM)re banning hosts from requiring it.

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.

The number of people within FedGov who have heard of DeepSeek is small. The number who could tell you why it might be better than some other model at some specific task is much smaller.

The number who could want to use deepseek for a valid reason is vanishingly small.

One thing that should be abundantly clear is that the Trump admin doesn't control everything in the executive branch. There is still significant employee resistance to Trump and anything construed as a trump edict or trump agenda.

There's no evidence the administration is afraid of smart people.

There is substantial evidence that people within the executive branch have attempted to undermine or simply ignore Trump's directives.

Banning use of Chinese AI in fedgov makes sense to me; similar to banning use of certain chinese cellphones for fedgov use. Doesn't matter if they are better. What matters is the high liklihood of foreign systems being used in espionage.

It may be that the "ban" isn't prima-facie about limiting the use of deepseek, but, announcing a policy and then firing-for-cause people who choose to violate it.

They didn't support SMP for a long time either.

OpenBSD tends to lag behind most OSes in "workstation quality of life" features, whereas they tend to be world-leading on unambiguous specs, and code correctness. (And man pages, IMO)

Their excellent security reputation is well deserved, and is downstream of their priorities... which I would describe as "skeptical of shiny new things with ambiguous semantics"

Have you ever worked for a US defense contractor?

For some of the roles at those companies, you need a SECRET (or higher) national security clearance.

So the "private company" thing is a bit of a false distinction because of how much classified/top-secret national security material is developed and held by "private" corporations in the US.

For example, the coatings and techniques for applying them to US stealth aircraft are secrets developed and/or held by US private companies.

Employees at those companies who attempt to exfiltrate secrets to foreign governments are absolutely committing espionage against the United States, and should be considered for execution.

Frontier AI work is becoming a matter of national security. It is _possible_ that secrets exfiltrated from OpenAI could be implicated in foreign espionage, and the death penalty might be appropriate. I don't know the specifics of what was leaked or to whom or for what reasons. My strong suspicion is that secrets were leaked to a party acting on behalf of a foreign government.