Discussion

From the Trenches

solomatov: Is there any publication which demonstrates that the improvement is really 10x?

rvz: > The industry calls this “10x productivity.” I call it what it is: a system that generates output at machine speed and forces humans to process it at biological speed.The question is can you tolerate the amount of PRs thrown at you per day on top of reviewing the exponentially growing mess of code that continues to double every hour and being paid less for it.Just learn to say no and leave. Why do you tolerate the increasing comprehension debt that is loaded on to you.You will never get that time back. Just give it to someone else that thinks it is worth maintaining that slop for less.

aanet: I feel this is not discussed enough. I can attest to this 100%.Just the past weekend, I was talking with a very senior engineer (~distinguished engineer at a very large tech co) who basically said he's working 8-8-6 (8 am - 8 pm, 6 days/week), "writing code" (more like supervising 8-15 agents) for a product demo in 2 weeks, which otherwise would have taken at least 1 quarter's worth of time with a small team. He's zonked out, fwiw. There are no junior engineers in the team ¯\_(ツ)_/¯, most having been laid off a few months ago.The toll it takes, and the expectations of AI-driven productivity, have only increased dramatically. At some point, the reality will hit the remaining engg team. Not sure if the company or its leadership realizes, but so far, it's all-AI, all-the-time, human cost of productivity be damned.

solomatov: > more like supervising 8-15 agentsHow do they do it? (My own record is 5 agents, but it is not typical). Do they use gastown or something?

fhub: There is a decent chance this is a temporary problem.1. Companies will build better simulation/testing environments for AI to prove changes before the PR.2. AI agents will have modes where they refuse to move beyond planning until the requirements are strong enough to do (1)

kakacik: Somebody doesnt know how to regulate their pace, and then various burnout symptoms happen.Not everybody pushes themselves like that, nor should, its anything but healthy and sustainable. In my experience it takes... rather obsessed people, ocd or similar traits, maybe 2 out of 10 intensity of their disease. Highly functional, smart, yet unbalanced.Llms just allow this spiral to go further, while human limits remain the same. Each of us creates our own path, dont mess it up just because you can. Your employer doesnt care much about you at the end, just another cog in machine but health once damaged may not bounce back, ever

sumeno: Given the research cited in the article it seems bigger than an anecdote about one guy who doesn't know how to do work life balance70%+ saying that AI has increased their workload AND that they are burning out because is it.

onemoresoop: And sometimes they do build interesting things but also leave a trail of destruction behind them. It reminds me of ‘moving fast break things’.

ggm: It's like "decimate" -you would think 10x had literal force, but it's more figurative. It just means "moar"(decimate had specific literal intent. Now it's just a force modifier like bigly)

TuringNYC: I can attest to this. Ultimately I dont think it is possible to 10x output systems with AI and actually keep the traditional quality controls (yet.)IMHO you just need two stacks -- systems where you can play fast and loose and 10x output. And systems where quality matters where you can perhaps 1.5 or 2x. That is still a lot of output.

aetherspawn: … how are you getting actual usable output at that scale? I have to baby my AI in 1 minute increments or it just doesn’t arrive at the correct solution at all.Using Codex 5.2

strange_quark: I mean, why do you think people are burning out?

zthrowaway: Can definitely attest to this. The frequency of outages at my company have increased drastically the past year, especially ever since incorporating agentic development. I’m seeing all of the dev best practices go out the window. We have a few vibe coders that are posting 15-30 PR’s per day. It’s way too much for us to review. We’re not a big shop. I think we’re going to have to hire more people just to review code across the industry. And those people will have to know how to actually write software otherwise what are they even reviewing. Maybe the models will get so good they never make a mistake. Doubt it.

strange_quark: If if this person really is a distinguished engineer, then they are part of leadership and it's their responsibility to set realistic expectations. Leadership knows this, they just don't care and won't care until the job market improves.

azinman2: I often have 10+ running in parallel. I’m attacking parallel problems that aren’t interdependent. Sometimes adding additional products can bring me up to 15+.Gotta have really good test harnesses so they can largely fix themselves.

solomatov: But how do you cover such amount of multi tasking? Could you give an example? I mean what kind of tasks allow such a parallelization?

peterashford: The literal meaning was removing 1/10

teaearlgraycold: People pushing dozens of PRs per day need to learn to prioritize tasks, and balance a bit more towards quality over quantity.

morkalork: And maybe spend some time doing reviews for other developers. And if they aren't qualified to be, then maybe spend that time becoming qualified rather than pumping out more slop.

zetanor: A watched pot never boils. A watched vibe coder never 10x-es.

hgoel: Using vibe coding for frequent PRs seems insanely reckless.In my scientific computing environment, the majority of my vibe coded output goes to one-off scripts, stuff that is not worth committing (correcting outputs, one-off visualizations, consistency checks), and anything worth committing gets further refined to an extent that it pretty much can't be considered vibe coded anymore. It's simply too risky, any bugs would propagate down to decision making for designing new, expensive instruments.I imagine that the cost and trust risks in enterprise environments are similar, so this seems very reckless.

stackskipton: Most people don't care. Leadership is demanding feature, feature, feature. IC are worried about losing their jobs and outages rarely cost most business actual money. So garbage gets shipped, outages rise, everyone is burned out but since they can't find another job, they remain.

teaearlgraycold: I love vibe coding for little tools like that. Tools which can have their outputs quickly validated, and then throw them away. Like a jig in woodworking.

bensyverson: I wonder if the PR workflow is just unsustainable in the agentic era. Rather than review every new feature or bug fix, we would depend on good test coverage, and hold developers accountable for what they ship.The result might be more faulty code getting merged, but if you already have outages and can't review every PR, is there currently a meaningful benefit to the PR workflow?

01HNNWZ0MV43FF: Diogenes carrying a lamp, looking for good test coverage

htrp: context switching across the entirety of the feature surface for an appYou could easily have agents to work on login page, messaging feature, database/data model update, recommender system, backend api, etc

solomatov: But you have to keep it in your head, and remember all stuff at the same time. How is it possible to track, and do reviews one after another? Or are these pretty long running agents?

pants2: I really think that software in general is getting buggier, with ChatGPT/Claude being some of the buggiest software I use. I constantly run into quality issues there and I've reported at least a dozen bugs to ChatGPT this year. One kicker I found recently was that Codex PR Reviews, once turned on for a repo, cannot be turned off - I got escalated to engineering who confirmed that they forgot to add a feature to disable code reviews.

ok_dad: I love it. I was getting burnt out due to ADHD or autism burnout but with AI tooling I’m able to work a full week without burnout. I think the kind of burnout I get is helped with these tools, but since I’m not neurotypical it’s different from the burnout people are getting from doing too much.I do see “task expansion” happening often though. If I can do the full feature rather than doing baby steps I’ll often do that now, because wrangling code is easier.

mynameisash: Yeah, it's all well and good to say somebody doesn't know how to regulate their pace, and it's another thing for your manager to tell your team that you need to be using a squad of agents constantly. To have a weekly stand-up that is specifically and solely for the purpose of talking about your "AI wins" for the week. To be told that you will be evaluated on how much you're using AI for your job.When your manager and your company regulate your pace for you with the understood threat that not using AI will risk your job, you don't really have much of an option.

sharts: Maybe it’s time to have multiple agents and models review the PRs and also provide context for easier human review. That and lots more focus on robust testing.There’s no way velocity will decrease now that upper management is obsessed with AI.

PradeetPatel: The proposed industry solution is to use agents to review PRs, as not to slow down the velocity of delivery...My current workplace is going through a major "realignment" exercise to replace as many testers with agents as humanely possible, which proved to be a challenge when the existing process is not well documented.

ryan_n: So you essentially trust the output of the model from beginning to end? Curious to know what type of application you're building where you can safely do that.

Madmallard: Sounds like people need to speak up to management

speak_on: So far in my experience the 10x output is achieved through various code migrations (improving component types, adding unit tests, etc) - all changes that have a very obvious scope limit. After that is done, I don't know what 10x is going to look like... generating code faster is a small part of the process in most companies, and the rest of the cross-functional process is not seeing a 10x improvement.

ed_balls: Due to prolonged stress, which lack of control is the main contributor e.g. you have expectations, you cannot control variable x,y,z, which leads to stress, which over long period of causes burn out.

strange_quark: In case it wasn’t obvious, I was being facetious. You can’t just let the AI rip without putting effort into constructing good input and verifying the output and expect anything good to happen, which is what the gp was asking.There’s no secret into how people are getting “10x”, or at least claiming to, they’re just working more.

chii: In this situation, you raise the issue with management, with a paper trail that Cover Your Ass, that the pace is unsustainable and bugs will continue to accumulate faster than it can be fixed. Make sure that you are not responsible for it and ensure this is known by all (including management).You then continue to vibe code as instructed by management. No burnout because you are not responsible anymore.

ricketycricket: "Hey Claude, did Claude do a good job?"

sgarland: I did an experiment today, where I had a new Claude agent review the work of a former Claude agent - both Opus 4.6 - on a large refactor on a 16k LOC project. I had it address all issues it found, then I cleared context, and repeated. Rinse and repeat. It took 4 iterations before it approached nitpicking. The fact that each agent found new, legitimate problems that the last one had missed was concerning to me. Why can’t it find all of them at once?

sublinear: This is the way. There's nothing inherently wrong with using AI as long as it's used responsibly.I highly doubt there are any managers or executives who care how AI is precisely used as long as there are positive results. I would argue that this is indeed an engineering problem, not an upper management one.What's missing is a realistic discussion about this problem online. We instead see insanely reckless people bragging about how fast they drove their pile of shit startup directly into the ground, or people in denial loudly banging drums to resist all forms of AI.

lopsotronic: The fact that anyone in leadership would ever think this is even remotely possible - given my experience in the general state of requirements / contracts / integrations / support - makes me bleed from my earholes just a little bit.It's starting to just feel a little like an excuse to call everyone on deck for "a few weeks trying 9-9-6". But even then the lack of traction isn't between the eyeballs and the deployment. You'll still be spinning wheels in that slippery stuff between what a customer is thinking and what the iron they bought is doing.

aanet: Honestly, I dont know. I could be mistaken about the exact number of agents - but not wrong about fact of AI-driven workflows which is heavily automated, and goes on for hours.He's one (small) step from distinguished engineer, with 20+ patents to his name, and is an embedded programmer (largely C/C++) with 30+ years of experience in the field; and I've known him for nearly as long, so I put a lot of credence to his words.But we don't usually talk work; he's the guitarist in our band :) [I'm the bass] So we mainly chill over music + beer. And lately, it's been less chill ¯\_(ツ)_/¯

basilgohar: The job market under our Great Leader has taken away a lot of this agency. Software engineers have gone from having the pick of the market for themselves to becoming (perceived as) next to disposable.

spaqin: That's a very American-centric point of view; the job market worldwide for developers is getting tougher and tougher.

storus: Management wants to get rid of people; they want to have their "wish-machine" that does what they say without any need to deal with nerds or ethical issues.

cadamsdotcom: You can write your own linters for every dumb AI mistake, add them as pre-commit checks, and never see that mistake in committed code ever again.. it’s really empowering.You don’t even have to code the linters yourself. The agent can write a python script that walks the AST of the code, or uses regex, or tries to run it or compile it. Non zero exit code and a line number and the agent will fix the problem then and rerun the linter and loop until it passes.Lint your architecture - block any commit which directly imports the database from a route handler. Whatever the coding agent thinks - ask it for recommendations for an approach!Get out of the business of low level code review. That stuff is automatable and codifiable and it’s not where you are best poised to add value, dear human.

hexaga: You're expecting it to be a person. It's not.It is more like a wiggly search engine. You give it a (wiggly) query and a (wiggly) corpus, and it returns a (wiggly) output.If you are looking for a wiggly sort of thing 'MAKE Y WITH NO BUGS' or 'THE BUGS IN Y', it can be kinda useful. But thinking of it as a person because it vaguely communicates like a person will get you into problems because it's not.You can try to paper over it with some agent harness or whatever, but you are really making a slightly more complex wiggly query that handles some of the deficiency space of the more basic wiggly query: "MAKE Y WITH NO ISSUES -> FIND ISSUES -> FIX ISSUE Z IN Y -> ...".OK well what is an issue? _You_ are a person (presumably) and can judge whether something is a bug or a nitpick or _something you care about_ or not. Ultimately, this is the grounding that the LLM lacks and you do not. You have an idea about what you care about. What you care about has to be part of the wiggly query, or the wiggly search engine will not return the wiggly output you are looking for.You cannot phrase a wiggly query referencing unavailable information (well, you can, but it's pointless). The following query is not possible to phrase in a way an LLM can satisfy (and this is the exact answer to your question):- "Make what I want."What you want is too complicated, and too hard, and too unknown. Getting what you are looking for reduces to: query for an approximation of what I want, repeating until I decide it no longer surfaces what I want. This depends on an accurate conception of what you want, so only you can do it.If you remove yourself from the critical path, the output will not be what you want. Expressing what you want precisely enough to ground a wiggly search would just be something like code, and obviates the need for wiggly searching in the first place.

jart: [delayed]