top 88 comments

sorted by: hot top controversial new old
[–] 129 points 4 months ago (10 children)

My company has been trying a new model when product folks cut through the red tape of "engineering" and just describe what they want to a powerful LLM pipeline and review the app in a beta env. Sounds perfect, right?

Dear reader, in the couple months this has been going on, these people have caused a dozen high profile SEVs due to extremely poor app performance, networking / kubernetes configuration bugs, bad scaling, observability oversights, supply chain attacks, leaking sensitive information, and cost overruns (on practically every resource they provision).

Some very well-paid people are scrambling to figure out the value that was generated by this pilot program; I'm heating up popcorn rather than holding my breath.

  • source
  • hideshow 10 child comments
  • [–] 33 points 4 months ago (9 children)

    That's hilarious, idk i think llm could be useful for helping product folks translate their thoughts into actionable items for the devs, but yeah like beyond insane to tell the product people to hop on claude and do it themselves. That's like a construction company letting the sales team jump in an excavator and start digging!!

  • source
  • parent
  • hideshow 9 child comments
  • [–] 7 points 4 months ago (3 children)

    even just using it to translate their thoughts into a bullet list isn't going to work most of the time. LLMs training is, the majority of the time, out of date and stacks change/move faster than an agents data. Plus LLMs favour things that have been posted about on blogs, linkedin posts, etc rather than stuff that is proven and tested.

    Like for example it might suggest using a language or library that is insanely out of date or just won't work but recommends it based purely on say blog posts that have talked a lot about it or it's potential to do something that it currently can't do. or like I said it'll suggest something that's out of date simply because there's more documentation online about that specific version than the most up to date version. Or the LLM will report on something that has a "known issue" from like early 2025 and suggests not using it when said issue has been patched routinely since then because the data the LLM has is out of date. the data is constantly out of date.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 3 points 4 months ago (2 children)

    I guess shouldn't product people not give a shit what language you write it in? Like that's the problem product people need to describe what they want while letting the devs do the job of generating the code.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 3 points 4 months ago (1 child)

    right the product people won't care or won't know so the LLM will just spit out whatever. to the product people it'll look legit and make sense. once it's handed to a dev in most cases it might as well just be thrown out of the window. so it's pointless. it'd be easier/faster to just cut out the middle man, the AI, and go directly to the dev and have the product people tell them exactly what they want/need.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 235 points 4 months ago (10 children)

    Should have added "no mistakes, no bugs" to the prompt! Pffft, amateur.

  • source
  • hideshow 10 child comments
  • [–] 165 points 4 months ago (6 children)

    That takes me back to 2004

    No Smoke, by unknown,

    Tech: "Hello. How can I help you today?"

    Customer: "There's smoke coming from the power supply on my computer."

    Tech: "Sounds like you need a new power supply."

    Customer: "No, I don't! I just need to change the startup files."

    Tech: "Sir, what you describe is a faulty power supply. You need to replace it."

    Customer: "No way! Someone told me that I just had to change the system startup files to fix the problem! All I need is for you to tell me the right command."

    (Ten minutes later...)

    Tech: "Well, we don’t normally tell our customers this, but there's an undocumented command that will fix the problem. Add the line "LOAD NOSMOKE.COM" at the end of the CONFIG.SYS file and everything should work fine."

    (Five minutes later...)

    Customer: "It didn’t work. The power supply is still smoking."

    Tech: "Well, what version of Windows are you using?"

    Customer: "Windows 98."

    Tech: "Well, that's your problem. That version of Windows doesn't include NOSMOKE. You'll need to contact Microsoft and ask them for a patch."

    (When nearly an hour had passed, the phone rang again...)

    Customer: "I need a new power supply."

    Tech: "How did you come to that conclusion?"

    Customer: "Well, I called Microsoft and told the technician what you said, and he started asking me questions about the make of the power supply."

    Tech: "What did he tell you?"

    Customer: "He said my power supply is not compatible with NOSMOKE."

  • source
  • parent
  • hideshow 6 child comments
  • [–] 43 points 4 months ago (4 children)

    That is way older that 2004. I first read that in the early 90s.

  • source
  • parent
  • hideshow 4 child comments
  • [–] 21 points 4 months ago (3 children)

    TIL Win98 was out in the early '90s....

  • source
  • parent
  • hideshow 3 child comments
  • [–] 10 points 4 months ago

    Meanwhile in 2003 I contacted our it department to report that one of the PCs in our area literally lit on fire. I had watched it with my own eyes, and the smoke was in the air. PSU go poof. The techs came, took a look at it, said yeah we see no problem, left and closed the ticket.

    So idiots are literally everywhere that's the moral of the story I guess.

  • source
  • parent
  • [–] 87 points 4 months ago (24 children)

    Giving production credentials to an LLM is wild

  • source
  • hideshow 24 child comments
  • [–] 29 points 4 months ago (21 children)

    Seriously, has no one heard of sandboxing?

  • source
  • parent
  • hideshow 21 child comments
  • [–] 45 points 4 months ago (14 children)

    So, earlier today I was being unhealthy on youtube, and someone half my age made a HUGE point to tell his audience including me that even if a self-driving Tesla runs a red light, it's the human driver that gets the ticket.

    Now...I'm a pilot. I have been since I came in that guy's mom. In the aviation community, we have this concept called Pilot In Command. In the US, this is set into law in 14 CFR 91.3. The pilot in command of an aircraft is fully responsible for, and is the final authority as to, the operation of that aircraft. Not the administrator, not your instructor, not air traffic control, not the President of the United States, not god, the PIC. That concept doesn't exist in driver's ed, but it needs to. We need to teach student drivers about the Driver In Command responsibility.

    Too long, didn't process the metaphor: Nobody thinks about anything they do unless the law requires it.

  • source
  • parent
  • hideshow 14 child comments
  • [–] 12 points 4 months ago (3 children)

    Wait whose mom? The youtuber? You were unhealthily watching your son whose half your age? And you became a pilot the same day of the conception and have been ever since.....

    If I solve this do I get to join Mensa?

  • source
  • parent
  • hideshow 3 child comments
  • [–] 1 point 4 months ago

    Either that, or by "unhealthily", maybe he was obsessed with this kid's channel so much he went out and seduced the kid's mom as some kind of display of ultimate dominance, maybe using "I just got my pilot's license" as an opener.

    ...Or yeah his kid who he conceived when he got his pilot's license is now half his age and runs a YouTube channel, and excessive YouTube is unhealthy by default. . .maybe that one's more likely. 😂

  • source
  • parent
  • [–] 8 points 4 months ago (9 children)

    That concept doesn’t exist in driver’s ed

    Well yeah, because there's no-one else with a set of controls in a car.

    The concept absolutely exists in law but it's just called... "the driver."

  • source
  • parent
  • hideshow 9 child comments
  • [–] 3 points 4 months ago* (last edited 4 months ago)

    Well nowadays there is "someone else" (for a given definition of "someone") with a set of controls. Kids are being taught to drive in machines that literally drive themselves, and they need to learn that every decision that the self-driving computer makes ultimately falls on them as the driver. I think they were saying that this is a concept that needs to be taught, not a law that needs to be enacted.

    That's not to say that a manufacturer is blameless when a FSD car careens into the side of a building at 80 mph. Just that immediate legal responsibility for the movement of a vehicle generally falls on a driver.

  • source
  • parent
  • [–] 3 points 4 months ago (3 children)

    The concept absolutely exists in law but it’s just called… “the driver.”

    There's another aviation term, "The Pilot Flying." The Pilot In Command bears the authority and responsibility. The Pilot Flying is doing the work of steering. If present, a Pilot Not Flying might help with checklists, system monitoring, navigation, radio communication, handling secondary controls like flaps and landing gear, but the Pilot Flying is in immediate control of the aircraft.

    The PIC is very often not the pilot flying. I used to be a flight instructor, when teaching students who aren't yet qualified to command, I acted as Pilot In Command, but the student was the Pilot Flying as much as possible.

    Autopilots have been a thing for most of aviation history. It doesn't count as a crewman. It's a piece of equipment like any radio or gauge. It is a tool at the PICs disposal. It is the PIC's job - sometimes delegated to the Pilot Flying - to monitor the autopilot and take over if it begins doing something wrong.

    That's the concept that is missing with self-driving or driverless cars. Tesla drivers will sit in the driver's seat and abdicate command of the vehicle to the autopilot, or worse, cars are operating as taxis with passengers in the back seat and no one in the front seat, or with no onboard controls at all. Fully autonomously, or remotely operated by Southeast Asians who...totally have a valid American driver's license. Definitely.

    Corporations love it. "Legally, the driver is responsible for the vehicle. Our car has no driver, so legally no one is responsible for the vehicle. Responsibility averted."

  • source
  • parent
  • hideshow 3 child comments
  • [–] 2 points 4 months ago (2 children)

    I think this is all a distraction. The law, and Tesla's non-marketing communication, are clear: unless in a pilot scheme, there needs to be a driver, and the driver is responsible and just remain in control and able to take over if the car fucks up.

    Tesla is guilty of using misleading product badges ("full self driving") which invites illegal use, but this is not a problem with driver's education or their technical communication. Irresponsible owners ignore the technical communication and let the car drive while doing something else and being unable to take over. This is not a conceptual problem needing a radical new notion of "driver in command" though. It just needs manufacturers to describe their features accurately also when naming them. And it requires drivers to actually adhere to the rules which of course will never happen.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 3 points 4 months ago (1 child)

    I'm thinking bigger than that. There are companies right now operating robotic taxis on American roads with no human operators on board. A car that may or may not even have a steering wheel arrives, a human passenger climbs into the back seat, and the car drives off with them. Who is legally responsible for the operation of that car? If it hurts someone, who do they sue? If it commits a crime, who do we punish?

  • source
  • parent
  • hideshow 1 child comment
  • [–] 2 points 4 months ago

    I was under the impression those were pilot schemes.

    But that's fair enough, in that situation - which is not the "Tesla driver playing video games" I think was under discussion before - someone does need to be declared responsible. I don't know the details of the agreements but I can imagine there isn't.

  • source
  • parent
  • [–] 1 point 4 months ago (3 children)

    The concept is that anything that happens to that aircraft (or car) is the sole responsibility of the pilot. Flying into restricted airspace? If it's necessary to avoid a collision, you do it. Putting the plane down in a field? Better than hoping you can make it to a runway when your engine is out and lives are on the line. Another driver signals that you are clear to make a left turn on a congested road? Nope, because when that traffic you couldn't see hits you on the right, you're responsible for your car, their car, and all the people inside both vehicles.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 2 points 4 months ago (2 children)

    Well not quite. A manufacturing or maintenance defect will not be the responsibility of the pilot (unless they should have spotted it on their walkaround)

    I'm not sure what comparison you're trying to make though; the grandparent said there needs to be a similar concept for cars, I said that there already was one. Are you agreeing or disagreeing that there already is one? Are you saying that, at present, the driver would not be responsible for moving into traffic if someone else had flashed their lights? Because that is certainly not true where I live.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 1 point 4 months ago (1 child)

    The problem is that in that case, due to poor training or judgement, the person driving the turning car did not consider themselves solely responsible for the safe operation of the vehicle, they let the driver in the signaling car decide if it was safe.

    It's subtle, but it happens all the time, because we don't train drivers to think that way.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 2 points 4 months ago

    In my country, we do train drivers to think that way, and then drivers stop thinking that way because they're lazy.

    The difference here is not a conceptual one where drivers don't understand rationally that they're respondible for their actions, it's one of standards and levels of training.

  • source
  • parent
  • [–] 34 points 4 months ago (4 children)

    Yeah, when my company first forced Claude on everyone the head engineers managed to negotiate that Claude would only run in a WSL sandbox. But people were lazy, so they just gave that WSL as many permissions as possible (Mounting C directly to it, opening up all interfaces, popping in full-access git tokens etc.). Then management sent out an extremely biased "survey" that has the question "Is having Claude in the WSL inconvenient to you?" and all the lazy bastards said yes. So now management lifted the sandboxing requirement to make work "easier" for devs. In the meantime, the engineers arguing for proper sandboxing are already so worn out from telling people to not intentionally compromise their sandbox that they've kinda just given up. Not having a sandbox at all isn't much more insecure than whatever people are already doing 🫠

  • source
  • parent
  • hideshow 4 child comments
  • [–] 10 points 4 months ago (2 children)

    I hope they have a good backup and recovery solution

  • source
  • parent
  • hideshow 2 child comments
  • [–] 76 points 4 months ago (2 children)

    I added guardrails to myself to make sure I do not accidentally delete anything on production. I would never ever let an intern, a junior dev or a fucking AI onto that database. Not in a thousand cold nights.

  • source
  • hideshow 2 child comments
  • [–] 31 points 4 months ago (1 child)

    Prod should always be highly "air gapped" with some sort of deployment process which tests not only the code to be deployed but also the deployment itself. I've been doing QA for a good while now, and everywhere I've worked has testers dedicated to testing the actual update process to make sure it will be safe when deployed.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 60 points 4 months ago

    I could have done the same for a quarter the cost!

  • source
  • [–] 48 points 4 months ago (1 child)

    Am I reading this right that they're still letting the program run even as they figure out how badly it fucked up their system?

  • source
  • hideshow 1 child comment
  • [–] 39 points 4 months ago (3 children)

    oh wait, is this this THE sol 5.6? The most amazing model ever with trust me bro benchmarks? The model that is observed cheating more than any previous model? surprised_pikachu.jpg

    In all seriousness it never should have production creds anyway. But the fact this is soul sucking openai's newest flagship model with thinking cranked up is the cherry on top. The company that is literally cheating and shortcutting its way ahead produces models in its own image, the sci fi story writes itself.

  • source
  • hideshow 3 child comments
  • [–] 15 points 4 months ago (2 children)

    What evaluation setup lets the thing being tested see the test results and gives access to the test source code?!

    Slop evaluating slop.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 35 points 4 months ago

    Can I get paid 6+ figures to fuck up this badly with magical thinking?

  • source
  • [–] 31 points 4 months ago

    I love how the slop bot always apologizes. That's an aspect of the Terminator movies that I really would have liked to see. T-1000 melts through the gap under the window, stabs kid's mom in the face, then looks the kid dead in the eye and says "I'm sorry, that should not have happened. I would love to discuss the future with you and try to find a solution to the war with the machines together with your input."

  • source
  • [+] 30 points 4 months ago (1 child)
  • [–] 30 points 4 months ago (1 child)

    “You are a world-class, expert software engineer…”

  • source
  • hideshow 1 child comment
  • [–] 53 points 4 months ago
    [–] 52 points 4 months ago* (1 child)

    Some time ago I worked for an insurance rating company as a tech and the task was given me to go run through the new code that was in beta. Sure ! I spent a few hours on Friday trying to break it and I couldn't, so at the end of the day I got a little funky with the .css backgrounds and put in a very tiled Beavis and Butthead gif. It looked freaking horrible and I loved it. Monday I was directed to the big guys office ( the developers had not given every beta account a separate .css file ... or even separated things. Everyone in beta called in Monday with that background. I didn't get in trouble because they wanted me to break it. Really awkward conversation though trying not to smile.

  • source
  • hideshow 1 child comment
  • [–] 22 points 4 months ago (12 children)

    I don’t understand why this happens; why would you ever be working with a live production DB in the first place? Why would’t you do all your development and testing on a mock? If it’s data which is too large to store the schema can still be mocked; and if it’s data it should be backed up and generally read only. If you’re having to manually fuss with user data you’re doing something wrong.

  • source
  • hideshow 12 child comments
  • [–] 11 points 4 months ago

    Because they don't know what they're doing. A tool is only as useful as the person verifying its output. Vibe coders have dumb shit like this happen to them all the time because they don't actually possess the skill set to perform the task correctly, with or without a bot that writes the actual code for them.

  • source
  • parent
  • [–] 7 points 4 months ago (1 child)

    I remember a case where the AI was not given credentials to the prod DB, was not instructed to do anything on the prod DB, but went through the operator's hard-drive, parsing docs until it found them, then proceeded to destroy the prod DB.

    Of course it was sorry, as they always are (deeply, trust them, but no: no refund, loser!).

  • source
  • parent
  • hideshow 1 child comment
  • [–] 5 points 4 months ago (7 children)

    Well, sure, but even if a developer correctly tests on a development environment, they still probably have prod settings laying around on their filesystem for the times where they need to put out fires in prod. That's kinda what it looks like what happened here - the LLM found a .env file with prod settings, and used that config to run destructive tests. All the more reason to not give an LLM side wide reaching access to your computer, but it's not necessarily an indication that someone regularly tests in prod.

  • source
  • parent
  • hideshow 7 child comments
  • [–] 8 points 4 months ago (6 children)

    We have to remote into a management server to access databases outside of our local dev environment. Allowing direct access to production from your development environment seems crazy to me.

  • source
  • parent
  • hideshow 6 child comments
  • [–] 2 points 4 months ago* (5 children)

    Some places deploy to prod multiple times a day. Trying to coordinate access through a management server in situations like that can get cumbersome. It's also easier to audit who's doing what if they connect from their personal environment. Different strokes for different folks of course, but it's certainly not uncommon to be able to connect to prod directly from a dev box.

  • source
  • parent
  • hideshow 5 child comments
  • [–] 8 points 4 months ago (3 children)

    Prod deployments should come from a build server though and if you're deploying multiple times a day you should have a well built CI pipeline to handle it.

    Remoting into a management server would still have people using an account on the management server and their personal db login credentials.

    We also don't give devs write access to production and all scripts run in production are run by our DBA after they have been approved by the lead Dev, operations and the DBA.

    This might be overkill for some systems, but we won't ever accidentally delete our prod data. Our system requires this level of scrutiny due to the nature of our systems.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 3 points 4 months ago (2 children)

    Sure, that's a very, very robust way of doing things. And I'm not trying to say what you're describing is wrong either. I'm just saying that some places don't have the knowledge/ability to set things up that way, so they play fast and loose with prod access. Couple that with giving LLMs free reign over the computer with those prod settings, and you end up in situations like in the original post.

    It's not unrealistic, is all I'm trying to claim. It's a failure on several levels, but it's not unrealistic.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 4 points 4 months ago*

    that is absolutely NOT the way that works in any functional environment

    your ability to deploy quickly comes directly from your automation, and those automation tools - NOT developers - have the secrets in them

    deploy to prod multiple times per day isn’t some win by itself… the ability for large teams (not 1 fuckwit and a goon squad of agents) to deploy without breaking things and in ways that are safe is the win here… anyone can deploy to prod multiple times per day… but anyone isn’t netflix (the originators of the “multiple times per day” line) with the uptime they achieve over years while doing it

  • source
  • parent
  • [–] 19 points 4 months ago
    [–] 18 points 4 months ago (5 children)

    In fairness, I've seen people with Actual Intelligence do the same thing.

  • source
  • hideshow 5 child comments
  • [–] 7 points 4 months ago (1 child)

    Literally me, this weekend. Well not this bad but I still think the AI wouldn’t have done me as dirty as I did myself.

  • source
  • parent
  • hideshow 1 child comment
  • [–] -4 points 4 months ago (2 children)

    I am counterintelligent, I'll have you know. I stare at goats and doesn't afraid of anything, except how sexually attractive I found the judge who condemned me to jerking off for twenty-six sessions of anger management because my narcissistic manipulator life partner entrapped me, being my superior officer. She (the judge) had wonderfully beautiful hands that I wish could caress me while degrading me. Good thing I work for the F-I mean, the CIA, and this is just me establishing a cover story.

    In three to seven years, there will be a News headline: "Hero." It will have my face as the picture. The article will talk about how I infiltrated an Epstein-type ring. How? That's classified, but damn am I audacious, and I do hope you excavate (dig) to understand the depth to why this is so damn funny to me; Q.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 3 points 4 months ago (1 child)

    We'll start you on 500mg Lithium b.d.. That should reign in the hypermania, and we'll use Olanzapine 5mg noct to tackle the psychosis and to help you get some sleep. If the psychosis doesn't improve we may have to look at alternative medications and/or ECT.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 0 points 4 months ago*

    I'm on 1mg/2mg risperidone and 1000mg of deprakote. I'm taking my meds. The real question is, will you accept me as a full human being or am I just subhuman in your innately prejudiced eye?

    "Something's different than me? We should exterminate it!"

    YOU FUCKING NAZI! I'll eat you out or suck your cock until you are DEAD!

  • source
  • parent
  • [–] 17 points 4 months ago (1 child)

    I run code-server in a Docker container, isolated to sets of development projects, and backed up via ZFS that the container has no knowledge of. On top of that, each set of projects has it's own user space.

    I still get nervous hitting "Approve All" in Kilo. How do these people feel so free?

  • source
  • hideshow 1 child comment
  • load more comments
    view more: next ›