joshribakoff

This author simultaneously admits, he cannot hold the system in his head, but then also claims he’s not vibecoding, and I assert that these are two conflicting positions and you cannot simultaneously hold both positions

I am also doing my pattern recognition. It seems that a common pattern is people claiming it sped me up by x! (and then there’s no AB test, n=1)

Thanks for sharing, i almost was not sure if the last part was sarcasm. Html itself was the standard, then when it got bloated we got rss. This seems like it’s not a problem of a lack of standards. It’s the company choosing not to promote it.

Your code can’t be both open source and closed source. In the other comment you wrote that he lifted your open source parts. Now you’re saying your code is not open source. People are allowed to copy open source code and you’re not even being consistent about whether your code is open source

Please dont open source your code if you’re going to call people hella sketch for deriving from it. Did he violate your license? Attack that action, not the person doing open source.

I think part of the importance of being a senior engineer is not spreading hype through the industry. This appears to be the guy who just posted all over social media that they just got Claude and redid a year long project in a week, followed by tweets from his eng team clarifying its just “demo” grade.

Martin Fowler.

The flaw in this logic is they are a monopoly. They continue to profit off of the bad user experience, that’s been their business model since day one, and they keep posting growth numbers. I hope they do die, but in the meantime the bad decisions still negatively impact users, and many of them didn’t have a choice.

The other flaw in your logic is assuming that markets are free. A free market is one that is both informed and consents. In this market, there is both misinformation and a lack of consent.

I actually just had to independently tag him on LinkedIn after my son had an issue with his Minecraft account. Their account recovery flow directs you to call on the phone and then when you call on the phone, it directs you to use the account recovery flow. When we went to their Support page we received a stack trace from asp.net. After wasting several hours, we screenshot of the error and tagged him on LinkedIn and filed a credit card dispute.

In my LinkedIn post I questioned if they can’t be trusted with a $30 game license how can we trust them with a multi million dollar copilot rollout? I pointed out that it seems like this is more than just a lack of human support. It is a company that: does not care about their own brand, the up-time of their own systems, their own employees, or their customers.

I question if their goal is to simply extract money under unethical conditions. I question whether they expect the customer to just repeatedly purchased the game every time the company fails to deliver it. I also questioned to him why he has hiring managers bragging on LinkedIn that they expect people to output 1 million lines of code per month, so they can rewrite the operating system in rust, while their systems are off-line.

Some of these don’t really seem like they bypassed any kind of sandbox. Like hallucinating an npm package. You acknowledge that the install will fail if someone tries to reinstall from the lock file. Are you not doing that in CI? Same with curl, you’ve explained how the agent saw a hallucinated error code, but not how a network request would have bypass the sandbox. These just sound like examples of friction introduced by the sandbox.

This is purely anecdotal but at the local mall (Stonetown in SF) they are giving out free rides.

To me, it looks desperate, and poorly executed. I was even waiting outside shake shack for my order, and the sales person approached me to offer me a test drive unsolicited. While I was waiting, I saw groups of people flicking them off and trolling them.

The irony to me - they have paid me $250,000 back for vehicles under lemon law instead of acknowledging and fixing a safety issue in the software, instead labeling it from “bug” to “characteristic”.

Now, they’re approaching me outside a shake shack begging me to accept a test drive, and i bet the issue is still not fixed. BMW driver assistance pro may be more limited but it is boring in the ways you want.

I was really intent on supporting Tesla, but they refused to work with me when I repeatedly raised the safety issue. They just repeatedly returned the car and said it was an expected characteristic for the car to turn left when I’m turning the wheel right.

I suspect they don’t wanna fix the false positive lane departure avoidance because they probably know they would be even more cases of accidental FSD engagement that do result in a collision where it needs to kick in. At the time I was reporting the issue they did not disclose the hidden disabled lane departure state, either.

That’s why you’ve gotta test your tests. Insert bugs and ensure they fail.

As the sibling comments alluded to, it’s not exclusively an AI problem since multiple people can miss the issue too.

It’s wonderful that AI is an impetus for so many people to finally learn proper engineering principles though!

Personally I clicked off because the fonts appear to be something like comic sans, it is a chore to read.

You are underestimating the importance of attention. You can have everything in context and still attend to the wrong parts (eg bad names)

Thanks for framing my physical disability as a skill issue. Injuries i sustained developing my skills beyond what most others were willing to do, but i guess my use of AI to assist my input so i can continue developing totally erases that experience.

I switched to fastmail, it imported all my gmail mail quickly, and it gives me virtual emails.

> Fortunately, once you've toggled Live Plus off, you no longer have to worry about your TV screen constantly being read

Not true, one may still find themselves worrying, especially since the factory reset or software update could add more “features” that we don’t want. Fortunately, once you’ve sworn off buying an LG product, you no longer have to worry.

You could also consider checking out vim, which solved this 50yrs ago ;) in all seriousness, you have terminals, splits, lazygit… so to me, it seems like this is a case of “not invented here”

This reads to me, an angry resident, as an AI generated article that attempts to leverage the chaos that they caused, for marketing purposes — not as any sort of genuine remorse — underscoring why we shouldn’t be banning AI regulation in the USA.

But Claude Code does not, which is the point you have missed

Without even getting into latency, just consider the fact that you could lose the signal altogether

To me, it doesn’t matter how cheap open AI codex is because that tool just burns up tokens, trying to switch to the wrong version of node using NVM on my machine. It spirals in a loop and never makes progress, for me, no matter how explicitly or verbosely i prompt.

On the other hand, Claude has been nothing but productive for me.

I’m also confused why you don’t assume people have the intelligence to only upgrade when needed. Isn’t that what we’re all doing? Why would you assume people would immediately sign up for the most expensive plan that they don’t need? I already assumed everyone starts on the lowest plan and quickly runs into session limits and then upgrades.

Also coaching people on which paid plan to sign up for kinda has nothing to do with running a local model, which is what this article is about

Its a fork of vscode, which has a browser.

Have you considered reducing review noise by using static analysis?

This was very annoying, and made things feel unsafe. Having vehicles stopped blocking visibility when there is no light. Its bad enough we tolerate them stopping and waiting for a pickup and blocking lanes under normal conditions. I had a hard time seeing if there are pedestrians when they’re literally in the cross walk stopped.

With code, even when it looks correct, it can be subtly wrong and traditional search engines don’t sit there and repeatedly pressure you into merging the PR.

Its not mutually exclusive. We write test precisely because expressing a complex application is hard without them. But to your point, we should not wave away applications that cannot be understood with extra tests. I agree.

Doesnt work, place just reverts on mobile safari. Even if it worked this adds steps.

The problem with this black or white framing is it implies competency is a failure. Finding it not useful doesn’t make you wrong, anymore than finding it useful doesn’t make you inexperienced.

This sounds like a comment from someone who has tested it in a limited capacity such as small blog sites or side projects that did not need to be maintained

Plus, if you are skipping tests or telling yourself, you wrote them when they don’t actually verify anything in the first place, then buying into a hype cycle of “the AI writes perfect code“ is unlikely to break the pattern