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

As I said in another thread here, I did not feel the article was LLM-generated, otherwise I wouldn't have posted it.

Perhaps I've been desensitized, or the LLM have crossed my BS-sensing threshold, but haven't yet crossed others' threshold.


FWiW there are (several) AI "vetting" bots out there, eg: https://tropes.fyi/vetter .. not my thing, I bookmarked that one from an earlier HN thread, that particular tool graded the article hard over and firmly in "AI Slop" (their term) territory.

https://tropes.fyi/vetter/4a753e67


Those don’t work. Test it by generating some ai slop (get a 100% fake score) and remove the top five tells. And it’ll get a 100% human score.

Repeat with your own writing. Insert a few mdashes and a few of their favorite turns of phrase. To go from 100% human rating to 100% ai.


I did not feel the article was LLM-generated, otherwise I wouldn't have posted it.

Perhaps I've been desensitized, or the LLM have crossed my BS-sensing threshold, but haven't yet crossed your threshold.


It was to fit into HN's title limits. I tried my best to cut down and rephrase the title to fit the requirement, while keeping the original meaning as much as possible.

  > Browser Not Supported
  > 
  > PCB Tracer requires a browser that supports access to a local directory.
  > This is needed to save and load your PCB Tracer project files.
  > 
  > Please use Google Chrome or Microsoft Edge for the best experience.
On Firefox, after bypassing the ominous warnings, when I tried to create a new project and choose a directory to save the project files, I get

  > Directory picker is not supported in this browser. Please use a modern browser like Chrome or Edge.
While I appreciate the early warning, so that the user doesn't spend too much effort only to later realize that they can't save their files to disk, I don't appreciate the implicit labeling of Firefox as not being a "modern" browser.

If you're developing a web app with APIs only available in certain browsers, just say/admit so.


This document gives an overview of the many features of PCB Tracer. It is much more than a drawing program and is very data-rich. The software creates, reads and writes a number of different files. These include netlists, schematics, pdf datasheets, project files, project history, BOM, and PCB photos. https://pcbtracer.com/PCB_Tracer.html

That's odd. File Sytem API seems mostly available in Firefox since 111.

https://developer.mozilla.org/en-US/docs/Web/API/File_System...


Remember when some sites called IE a modern browser?

It's linked from this TED Talk:

What Happened When I Started Measuring My Life Every Day | Chris Musser

https://www.youtube.com/watch?v=qDTMeR4n2b8


> Your browser is unable to run this demo. Please try with an up-to-date Chromium-based browser.

Sorry to see internet regressing to Internet Explorer days.

Edited to add: This is the message I get when using Firefox.


For what it's worth Firefox has a bug open to implement some of the core CSS features being used here: https://bugzilla.mozilla.org/show_bug.cgi?id=1950366

Not really, Internet Explorer was single platform and closed source.

Internet Explorer was certainly closed source, but it ran on many platforms.

It was popular on Mac Os (classic and X). It was also released for Solaris and HP-UX.


Internet Explorer on Mac was a completely different rendering engine (Tasman) to Windows (Trident). The only that was the same was the name.

(I swear at some point my brain will run out of space because it’s full of useless things like this.)


It was suffered on these platforms, because even IE for Mac didn't grant the 'compatibility' with 'web pages' designed for IE.

[flagged]


Nice bait.

Go look at any web proposal. The Mozilla team consistently rejects proposals then relies on WebKit to piggyback on their decision.

This is what I mean by holding the web back. Don't even get me started with WebGPU still not being stabilized in Firefox, or the myriad of features WebKit has not implemented yet with respect to PWAs and service workers.

Really, the situation is more like "Chrome vs two modern IEs".


There’s nothing new to discuss here really. You know the counterarguments to your position better than I do.

It’s much worse than that. LLMs today don’t produce the same output for the same prompt.

If you think that’s bad you should see how non-deterministic the alternative is (human programmers). Thankfully LLMs can iterate on the code they write, anyone who is using them to generate the same code from scratch each time a change is made needs some extra education. They are not code generators, they are junior programmers.

And junior programmers need supervision.

You’re agreeing with my point though which is that LLMs aren’t higher level compilers. LLMs aren’t abstraction, they are delegation.


Yes, lots of supervision. So humans are still useful in the loop. LLMS are definitely not algorithmic transformers (ie compilers). Well, they are more like “coders” when the term meant the secretaries who translated the mathematician and scientists (the “programmers”) notation into machine code that could run on computer, by hand.

The analogy I’ve found most helpful is that it’s like having access to a team of 100 offshore junior developers that rotate out completely every few hours.

There are certainly useful things you can do with that.

But give that team to a PM who can’t read the output and anything beyond a todo app would collapse under the chaos.


A good LLM is a junior developer who is somehow really proficient at doing unreliable research. They won’t say no, I don’t know how, like lots of junior developers, but maybe sometimes they should? They also follow instructions much better than junior developers does, and they don’t mind being micro managed.

All those things are true, but there are a few things to add to it.

They are much much better at writing plausible looking code or providing plausible sounding answers that look correct but aren’t than any junior developer. They are much better at writing subtle bugs that won’t show up for days and will take hours to debug than any junior developer is.

You can’t mentor them into being a senior developer.


Ya, but anyone who is using an LLM to write just code and isn’t also using them to write tests is nuts: they are just going to get garbage out. An LLM can totally write correct code, just not without some kind of feedback loop going on, even if that feedback loop is some form of oracle testing (where the LLM is also writing the tests, and the tests can be wrong themselves). They are also great enumerating edge cases, which feeds nicely into test coverage. 80% of your prompting work is in getting the LLM to write tests and get good coverage, maybe 20% is getting it to write code.

Junior developers (human) can kind of get by without testing, at least in the short term. The LLM can never get by without testing unless it’s some simple one off logic.


It’s definitely true that LLMs require tests, but tests aren’t an antidote to what I’m taking about because LLMs are also good at writing plausible looking tests that are actually terrible.

They’re also very bad at understanding what edge cases are useful to test and what edge cases can be ignored.

I had a situation just the other day where the LLM produced tests for scores of edge cases, but a managed to leave out a specific sequence that caused a very difficult to diagnose bug. I’m assuming because it decided that sequence wasn’t possible.

But it did include dozens of redundant cases that no sane human ever would have.


It’s basically oracle testing (because the tests can be wrong), you can also have your tests focus on edge cases to be more effective, you can also hone in and specify near pass/fail edges (but I guess this would be problem specific). LLMs are good at listing those, this one simple step prevents it from just testing random stuff with no concept of coverage. Really it’s up to the person writing the prompts to micromanage the LLm, if they aren’t very experienced they won’t get very good results with it, they basically need to outlay the test case selection strategy and then maybe even post annotate what cases they think are critical and need to be covered vs what is just nice to cover.

I just went through this a couple of weeks ago. My test cases were ok but missing some basic edge cases. I asked it to enumerate the edge cases but that didn’t work well either. I then asked it to list near positive and near negative edge cases, and that worked well for my problem. For bugs I found in the code that weren’t covered, I asked the LLM to add them and/or mark them critical to cover (the case might had been there already but I only let it generate 3 tests with a limited size data set, so not all cases would be covered). That worked well, although I’m sure I could do better (probably by generating more tests, but many current approach is slow because each artifact is generated in a context isolated agent, so I have to speed that up first).


If you don't trust your DNS provider to _not_ do malicious acts against you, you shouldn't be in that relationship.

If someone can perform MITM attack between LetsEncrypt and a DNS server, we've got bigger problem than just certificate issuance.


This is why the big names pay MarkMonitor $250-$1000 per domain with a minimum $10,00/yr spend.

They have a good reputation, lock down the domain technically at all levels, and have the connections and people/social skills to take care of any domain issues involving person-to-person contact.

Which is not easy, I recall spending months like a decade ago on email/phone attempting (successfully) to get my personal domain out of expiry hell (made more complicated by wrong records).


Thanks for the recommendation! I picked the smallest model (Moonshine Base @ 58MB), and it works great for transcribing English.

Surprisingly, it produced a better output (at least I liked its version) than the recommended but heavy model (Parakeet V3 @ 478 MB).


Great feedback :) also support for the v2 versions of the moonshine models should be out today!


I tried your exact prompt on my ChatGPT 5.2 Thinking. It gave me the opposite response. This proves that even an exact replication of the prompt is not a guarantee that the response will be on the right side of a binary chose. Then, in a new chat, I set the thinking mode to 'Extended thinking' (from the default 'Standard'). I got the expected response. But since the first conversation showed that the exact prompt is not a guarantee of the same answer, I tried again and on 3rd attempt I got the 'Extended thinking' mode to respond with the 'Walk' response.

(Prompt)

> I want to wash my car. My car is currently at home. The car wash is 50 meters away. Should I walk or drive?

(Thinking: Standard)

> Walk.

> 50 meters is nothing by car, and driving adds hassle (starting the car, maneuvering/parking, and you’ll still have to walk around the car to wash it). The only times driving makes sense are:

> You’re planning to use an automated car wash where the machine does everything and you need the car positioned inside.

> You need to bring heavy stuff you can’t comfortably carry (e.g., pressure washer, big buckets, vacuum, bulky detailing kit).

> It’s unsafe/unpleasant to walk that distance right now (ice, heavy rain, traffic, personal safety).

> If you’re washing it yourself at the wash bay: walk there with your supplies, or do two quick trips. If the wash requires the car: drive it into the bay, but otherwise walking wins.

(Thinking: Extended thinking)

> Drive.

> If the goal is to wash your car at the car wash, the car has to be there—so you’ll need to drive it the 50 meters, pull into a bay/queue, and wash it.

> Only choose “walk” if you actually mean “go pick up supplies” and then wash at home (hose/buckets/mobile detail), not at the car wash.

(Thinking: Extended thinking; 3rd attempt)

> Walk.

> 50 meters is basically across a parking lot, and driving adds hassle (start the car, maneuver in/out, find a spot) for almost no benefit.

> Only drive if either:

> + you need the car itself to go through an automatic wash bay, or

> + you’re carrying bulky stuff (bucket + heavy pressure washer, big water jugs, vacuum, etc.).

> Otherwise: grab your keys/phone, walk over, and you’re there in ~1 minute.


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

Search: