Hacker Newsnew | past | comments | ask | show | jobs | submit | candiddevmike's commentslogin

Tests are just for the bugs you already know about

They're also there to prevent future bugs.

Most MFA solutions can use a FIDO token these days (unless the admins are masochists), which you could keep plugged into your device

Most banking apps here only allow their own app as a 2-factor authentication, not even TOTP is allowed. (I think they make it to increase user engagement.)

The worst one is Mercado Libre, which also requires you to use your phone to "scan" your face every time you log in with a new device. My friends were locked out due to having an allergy or growing a beard. Nowadays, I don't even bother with them... I just shop elsewhere.


I wish Chrome had timers for specific websites on mobile. I hate the all-or-nothing Chrome timer, it's ridiculous and so counter intuitive.

> I wish Chrome had timers for specific websites on mobile.

Chrome does have this feature on mobile, but perhaps not on your mobile.


this is the sole reason i default to Firefox on mobile as it allows extensions. And install a website restriction ext like Leechblock [1].

[1] https://chromewebstore.google.com/detail/blaaajhemilngeeffpb...


I’d also like more control over chrome autocomplete.

Most of the time that I get sucked into a website, it’s because autocomplete and muscle memory got me there without thinking. Every once in a while I’ll clean out my history cache and for a week or so I’ll find myself on the page of google search results for “re” or “fa”


You can hold-press over an autocompleted URL to delete it, which has much less friction than clearing your history.

Agreed, and their setting to turn it off entirely doesn't work on Pixel at all.

Pixel phones (at least) have this.

> to programming like the table saw was to hand-made woodworking

This is a ridiculous comparison because the table saw is a precision tool (compared to manual woodworking) when agentic AI is anything but IMO.


The nature of the comparison is in the second paragraph. It's nothing to do with how precise it is.

> tell it that it's wrong and it'll go, "You're absolutely right. Let me actually fix it"

...and then it still doesn't actually fix it


Sometimes it does... sometimes.

I recently had a nice conversation looking for some reading suggestions from an LLM. The first round of suggestions were superb, some of them I'd already read, some were entirely new and turned out great. Maybe a dozen or so great suggestions. Then it was like squeezing blood from a stone but I did get a few more. After that it was like talking to a babbling idiot. Repeating the same suggestions over and over, failing to listen to instructions, and generally just being useless.

LLMs are great on the first pass but the further you get away from that they degrade into uselessness.


Yeah, when I first heard about "one-shot"ing it felt more like a trick instead of a useful heuristic but with time my experience mimics yours, nowadays I try to one-shot small-ish changes instead of going back and forth.

I've had some luck in these cases prompting "your context seems to be getting too bloated. summarize this conversation into a prompt that I can feed into a new chat with a fresh context. make sure to include <...>".

Sometimes it works well the first time, and sometimes it spits out a summary where you can see what it is confused about, and you can guide it to create a better summary. Sometimes just having that summary in its context gets it over the hump and you can just say "actually I'm going to continue with you; please reference this summary going forward", and sometimes you actually do have to restart the LLM with the new context. And of course sometimes there's nothing that works at all.


I’ve had really good luck with having gpt generate a todo list that’s very, very detailed. Then having Claude use it to check items off. Still far from perfect but since doing that haven’t run into context issues since I can just start a new chat and feed it the todo (the todo also contains project info).

So, I recently have done my first couple heavily AI augmented tasks for hobby projects.

I wrote a TON of LVGL code. The result wasn’t perfect for placement, but when I iterated a couple of times, it fixed almost all of the issues. The result is a little hacked together but a bit better than my typical first pass writing UI code. I think this saved me a factor of 10 in time. Next I am going to see how much of the cleanup and factoring of the pile of code it can do.

Next I had it write a bunch of low level code to init hardware. It saved me a little time compared to reading the reference manual, and was more pleasant, but it wasn’t perfectly correct. If I did not have domain expertise I would not have been able to complete the task with the LLM.


When you argued that it saved you time by a factor of 10, have you even measured that properly? I initially also had the feeling that LLMs save me time, but in the end it didn't. I roughly compared my performance to past performance by the amount of stories done and LLMs made me slower even if I thought I am saving time...

From several month of deep work with LLMs I think they are amazing pattern matchers, but not problem solvers. They suggest a solution pattern based on their trained weights. This even could result in real solutions, e.g., when programming Tetris or so, but not when working on somewhat unique problems...


I am pretty confident. Last similar LVGL thing I did took me 10-12 hours, and I had a quicker iteration time (running locally instead of the test hardware). Here I spent a little more than an hour, testing on real hardware, and the last 20 minutes was nitpicking.

Writing front-end display code and instantiating components to look right is very much playing to the model’s strength, though. A carefully written sentence plus context would become 40 lines of detail-dense but formulaic code.

(I have also had a lot of luck asking it to make a first pass at typesetting things in Tex, too, for similar reasons)


There was a recent study that found that LLM users in general tend to feel like they were more productive with AI while actually being less productive.

presumably the study this very HN discussion responds to.

Heh, yep. Guess I sometimes forget to read the content before commenting too.

> If I did not have domain expertise I would not have been able to complete the task with the LLM.

This kind of sums up my experience with LLMs too. They save me a lot of time reading documentation, but I need to review a lot of what they write, or it will just become too brittle and verbose.


My favourite recent experience was switching multiple times between using a library function and rolling its own implementation, each time claiming that it's "simplifying" the code and making it "more reliable".

I was trying out Copilot recently for something trivial. It made the change as requested, but also added a comment that stated something obvious.

I asked it to remove the comment, which it enthusiastically agreed to, and then... didn't. I couldn't tell if it was the LLM being dense or just a bug in Copilot's implementation.


Some prompts can help:

"Find the root cause of this problem and explain it"

"Explain why the previous fix didn't work."

Often, it's best to undo the action and provide more context/tips.

Often, switching to Gemini 2.5 Pro when Claude is stumped helps a lot.


How do you handle trigger logic that compares old/new without having a round trip back to the application?

Do it in a stored procedure not a trigger. Triggers have their place but a stored procedure is almost always better. Triggers can surprise you.

I don't follow how you would do that in a stored procedure outside of a trigger.

I think instead of performing an INSERT you call a stored proc that does the insert and some extra stuff.

Yes, we already have all of our business logic in postgres functions(create_order, create_partial_payment etc).

Doing the extra work in stored procedures is noticeably faster than relying on triggers.


If you stewarded that much tech debt in the first place, how can you be sure LLM will help prevent it going forward? In my experience, LLMs add more tech debt due to lacking cohesion with it's edits.

It's such a shame this isn't built into shells. There isn't really a security issue here as you have to trust the directory first before it fires.

If an employee was worth X and the company made them worth Y, they should pay them Y to continue having them as an employee. Anything else distorts the labor market.

Now having to pay back training or education if you leave before Z months seems reasonable.


IMO, LLMs are a neat technical phenomenon that were released to the public too soon without any regard to their shortcomings or the impact they would have on society.

It's funny that when OpenAI developed GPT-2, they've been warning it's going to be disruptive. But the warnings were largely dismissed, because GPT-2 was way too dumb to be taken as a threat.

It's a way to get free training data

Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: