Unfortunately, I don’t know what data I can share, so I’ll err on the side of caution and share none 🙂. But I suppose I can share a little more general insight:
Modern “agentic” (yeah I’m tired of that word too) techniques, patterns, and tools, paired with modern LLMs allow for much more autonomy than what was available a year ago.
Are agents faster than skilled engineers per task? No, not in most cases. But they allow engineers to scale horizontally, knocking out many tasks in parallel.
That’s the performance gain: Foster autonomy for horizontal scaling. Build/optimize projects’ AGENTS.md and SKILL.md files[1].
Agents can work for some long runs (some engineers even run them overnight), given a safe environment/project with guardrails — mostly the same guardrails that human engineers have had for years: Statically typed languages, TDD, good test coverage, code reviews (both agents and human[2]), CI pipelines, etc.
They still need human engineers to operate them; the workflow is just different now, and there’s a learning curve for it.
Whether we like it or not (personally, I miss the old days), this is just how it is now. We have not even reached the peak yet. This is the least autonomous that agents will ever be.
The bigger the repo, the more important this probably is. Structure them so they don’t bloat the context windows with unnecessary info. ↩︎
I usually wait for the AI agent review cycles to settle first — no need to spend human engineering time on potential slop that will probably get fixed autonomously. ↩︎
You’ve been given evidence that people cannot trust their own perceptions of what these agents do, and you replied by telling a bunch of stories about why you think you personally can trust your perceptions. My 12-year-old did the same thing when I tried to explain this to them.
Engineers being spread thinner to manage a wider number of tasks whilst reviewing shitty LLM noise that they didn’t write is inevitably going to make horrible code that’s impossible to maintain and will cost massive amounts of time and resources in the long run.
And the idea that it allows more things to be done is just a bunch of “it makes you faster” assessments in a trenchcoat.
Agentic or not, they still have zero fidelity. Fidelity can only come from an internal model of reality that the network is comparing its inputs to, and I’m pretty sure you don’t get that without AGI.
The data we have till this point shows that they don’t help, they only create an illusion of helping. And until you can show that that has fundamentally changed, then you have to assume that the improvements you’re seeing are just improved illusions.
You’ve been given evidence that people cannot trust their own perceptions of what these agents do, and you replied by telling a bunch of stories about why you think you personally can trust your perceptions. My 12-year-old did the same thing when I tried to explain this to them.
You asked for data. I (probably) can’t give you the data, so I gave you what I could: a few things gleaned from both objective data (collected from a significant number of engineers) and my own anecdotal experience. You are free to disregard it, and I wouldn’t even blame you. There are lots of fools on the internet, and there’s a decent chance that I’m just another one 🙂.
Engineers being spread thinner to manage a wider number of tasks whilst reviewing shitty LLM noise that they didn’t write is inevitably going to make horrible code that’s impossible to maintain and will cost massive amounts of time and resources in the long run.
This was true a year ago. Even like seven months ago.
Hell, even three months ago, I would have agreed with you a LOT more than I do today – mostly because I was just forced learn these things more in-depth quite recently. “Shitty LLM noise” is a very early part of the learning curve. In a way, it’s similar to “Hello world.” Discard it and figure out how get more useful results.
In many companies that have adopted AI, engineers are still responsible for their code. Any slop in the codebase is the fault of the engineer that introduced it (and the engineer[s] that reviewed it), regardless of whether it’s hand-written or generated. So far, I have not seen anyone merge unmaintainable, “shitty LLM noise” into enterprise codebases – that would be very risky. (It probably happens in other places like Microsoft, I just haven’t seen it myself. It would be unacceptable.)
Anyway, you’ll see all this eventually, when some data gets published. I’d gain nothing by convincing anyone of this, so I won’t try 🙂.
This is just a statement of faith in your ability to judge these things accurately. Nowhere in here do I see any evidence that you’ve even considered that the reason you’ve changed your attitude towards the tech is that it’s just gotten so good at fooling people that it’s finally got you.
You don’t gain much from trying to convince me, but you could gain a lot from being more sceptical. People invented science to address the fact that our intuitive understanding doesn’t always reflect reality.
Science and the collection of objective data stops us from doing this:
There are a bunch of things that our brains just don’t understand intuitively, so we need to check our intuition against measurement. There’s no shame in that, but when it’s pointed out, then you have a chance to check yourself.
But you don’t seem to understand that. When you say:
Anyway, you’ll see all this eventually, when some data gets published.
you are demonstrating that you are the perfect mark for this stuff, because you are not reflecting on your own thought process to see where it might be failing you.
This is just a statement of faith in your ability to judge these things accurately. Nowhere in here do I see any evidence that you’ve even considered that the reason you’ve changed your attitude towards the tech is that it’s just gotten so good at fooling people that it’s finally got you.
Yet in all of your replies, you seem to have assumed early on that I’ve been fooled, based on outdated data. Do you just assume that newer data just doesn’t exist anywhere, and I’m lying about it? (To be clear: I wouldn’t blame you. There’s an old proverb: “Believe nothing you hear, and only half of what you see,” or something like that.)
you could gain a lot from being more sceptical
Another assumption that I wasn’t skeptical.
Anyway, the rest of your reply continues with the assumption that there was no data or objectivity on my part, so I won’t keep beating a dead horse. Just wait for newer data. It might be old by the time you see it, but still useful.
Edit: I suppose the number of recent layoffs might be useful (or at least interesting) data. Suddenly many different, unrelated companies had too many engineers – quite a contrast to the engineer shortage just a few years ago. Correlation ≠ causation and all, but interesting nonetheless.
And even for complex coding projects like the ones studied, the researchers are also optimistic that further refinement of AI tools could lead to future efficiency gains for programmers. Systems that have better reliability, lower latency, or more relevant outputs (via techniques such as prompt scaffolding or fine-tuning) “could speed up developers in our setting,” the researchers write. Already, they say there is “preliminary evidence” that the recent release of Claude 3.7 “can often correctly implement the core functionality of issues on several repositories that are included in our study.”
Claude 3.7 was released in February 2025. Also, I highly doubt 3.7 was good enough to make engineers more productive, overall (though I don’t have data on those old models). Relative to the speed of evolution of LLMs, harnesses, and people’s skills in using them, the data behind this article is ancient.
Edit 3:
In that article you shared, they link to the study in the second paragraph. Follow that link, and you’ll see this at the top:
Update: In February 2026, we published new data on the productivity impact of late-2025 AI tools.
There were selection effects in the follow-up study, but seemed worth mentioning anyway.
Anyway, you’ll see all this eventually, when some data gets published.
That is not a skeptical position.
And my point is that given that the data shows objectively that it does fool people - even subject matter experts - it is reasonable to believe that effect continues until proven otherwise. We know it’s a feature of LLMs, and the fact you continue to push on with your blind faith undisturbed by this knowledge is truly alarming.
In the follow up study, first of all I want to point out that it’s not definitive that it made them faster, the error bars include regions where they were slowed down. And none of this includes the long-term effects of poorly made, unmaintainable code that was farted out in bulk by an overworked engineer who didn’t have time to properly review code that they didn’t write and don’t fully understand.
It also doesn’t include the effects of long term exposure to LLMs reducing their solo effectiveness. If you only measure the immediate delta, then it could look like the LLM is helping when actually it’s just making people dependent.
And the selected dev quotes are also alarming in light of that information:
“I’m torn. I’d like to help provide updated data on this question but also I really like using AI!” — a developer from the original study early-2025 when asked to participate in the late-2025 study.
“I found I am actually heavily biased sampling the issues … I avoid issues like AI can finish things in just 2 hours, but I have to spend 20 hours. I will feel so painful if the task is decided as AI-disallowed.” — a developer from the new study noting selection effects when choosing what tasks to include in the study.
“my head’s going to explode if I try to do too much the old fashioned way because it’s like trying to get across the city walking when all of a sudden I was more used to taking an Uber.” — a developer from the new study noting selection effects when choosing what tasks to include in the study.
These quotes don’t demonstrate that LLMs actually help, only that they are addictive, which we already know to be true. If you’ve ever tried to talk to an addict about their problem you’d recognise this language.
Especially the quote that they could do something in 2 hours with an LLM that would take 20 hours alone. That can’t be true, that person is definitely wrong about the effect of the LLM. If it were really that effective, LLM companies would be clamouring to show the data that proves how effective their products are. Why aren’t they?
The fact this data is so hard to find and so hard to fund when there are so many billions being dumped into this field should tell you something, it should be deeply disturbing, but you just carry on fully convinced that you’re right and that there’s nothing to what I’m saying, even though you admitted you would’ve agreed just 3 months ago. Again, if you can actually show that the difference is so dramatic, then show it. You’re not though. You’re just convinced that you don’t need to re-evaluate what you believe. That doesn’t say good things about where your head’s at.
If you truly weren’t trying to convince me, you could just stop. I don’t know what you’re trying to prove by continuing.
Unfortunately, I don’t know what data I can share, so I’ll err on the side of caution and share none 🙂. But I suppose I can share a little more general insight:
Modern “agentic” (yeah I’m tired of that word too) techniques, patterns, and tools, paired with modern LLMs allow for much more autonomy than what was available a year ago.
Are agents faster than skilled engineers per task? No, not in most cases. But they allow engineers to scale horizontally, knocking out many tasks in parallel.
That’s the performance gain: Foster autonomy for horizontal scaling. Build/optimize projects’
AGENTS.mdandSKILL.mdfiles[1].Agents can work for some long runs (some engineers even run them overnight), given a safe environment/project with guardrails — mostly the same guardrails that human engineers have had for years: Statically typed languages, TDD, good test coverage, code reviews (both agents and human[2]), CI pipelines, etc.
They still need human engineers to operate them; the workflow is just different now, and there’s a learning curve for it.
Whether we like it or not (personally, I miss the old days), this is just how it is now. We have not even reached the peak yet. This is the least autonomous that agents will ever be.
The bigger the repo, the more important this probably is. Structure them so they don’t bloat the context windows with unnecessary info. ↩︎
I usually wait for the AI agent review cycles to settle first — no need to spend human engineering time on potential slop that will probably get fixed autonomously. ↩︎
You’ve been given evidence that people cannot trust their own perceptions of what these agents do, and you replied by telling a bunch of stories about why you think you personally can trust your perceptions. My 12-year-old did the same thing when I tried to explain this to them.
Engineers being spread thinner to manage a wider number of tasks whilst reviewing shitty LLM noise that they didn’t write is inevitably going to make horrible code that’s impossible to maintain and will cost massive amounts of time and resources in the long run.
And the idea that it allows more things to be done is just a bunch of “it makes you faster” assessments in a trenchcoat.
Agentic or not, they still have zero fidelity. Fidelity can only come from an internal model of reality that the network is comparing its inputs to, and I’m pretty sure you don’t get that without AGI.
The data we have till this point shows that they don’t help, they only create an illusion of helping. And until you can show that that has fundamentally changed, then you have to assume that the improvements you’re seeing are just improved illusions.
You asked for data. I (probably) can’t give you the data, so I gave you what I could: a few things gleaned from both objective data (collected from a significant number of engineers) and my own anecdotal experience. You are free to disregard it, and I wouldn’t even blame you. There are lots of fools on the internet, and there’s a decent chance that I’m just another one 🙂.
This was true a year ago. Even like seven months ago. Hell, even three months ago, I would have agreed with you a LOT more than I do today – mostly because I was just forced learn these things more in-depth quite recently. “Shitty LLM noise” is a very early part of the learning curve. In a way, it’s similar to “Hello world.” Discard it and figure out how get more useful results.
In many companies that have adopted AI, engineers are still responsible for their code. Any slop in the codebase is the fault of the engineer that introduced it (and the engineer[s] that reviewed it), regardless of whether it’s hand-written or generated. So far, I have not seen anyone merge unmaintainable, “shitty LLM noise” into enterprise codebases – that would be very risky. (It probably happens in other places like Microsoft, I just haven’t seen it myself. It would be unacceptable.)
Anyway, you’ll see all this eventually, when some data gets published. I’d gain nothing by convincing anyone of this, so I won’t try 🙂.
This is just a statement of faith in your ability to judge these things accurately. Nowhere in here do I see any evidence that you’ve even considered that the reason you’ve changed your attitude towards the tech is that it’s just gotten so good at fooling people that it’s finally got you.
You don’t gain much from trying to convince me, but you could gain a lot from being more sceptical. People invented science to address the fact that our intuitive understanding doesn’t always reflect reality.
Science and the collection of objective data stops us from doing this:
There are a bunch of things that our brains just don’t understand intuitively, so we need to check our intuition against measurement. There’s no shame in that, but when it’s pointed out, then you have a chance to check yourself.
But you don’t seem to understand that. When you say:
you are demonstrating that you are the perfect mark for this stuff, because you are not reflecting on your own thought process to see where it might be failing you.
Yet in all of your replies, you seem to have assumed early on that I’ve been fooled, based on outdated data. Do you just assume that newer data just doesn’t exist anywhere, and I’m lying about it? (To be clear: I wouldn’t blame you. There’s an old proverb: “Believe nothing you hear, and only half of what you see,” or something like that.)
Another assumption that I wasn’t skeptical.
Anyway, the rest of your reply continues with the assumption that there was no data or objectivity on my part, so I won’t keep beating a dead horse. Just wait for newer data. It might be old by the time you see it, but still useful.
Edit: I suppose the number of recent layoffs might be useful (or at least interesting) data. Suddenly many different, unrelated companies had too many engineers – quite a contrast to the engineer shortage just a few years ago. Correlation ≠ causation and all, but interesting nonetheless.
Edit 2: I just noticed this paragraph in that link you shared:
Claude 3.7 was released in February 2025. Also, I highly doubt 3.7 was good enough to make engineers more productive, overall (though I don’t have data on those old models). Relative to the speed of evolution of LLMs, harnesses, and people’s skills in using them, the data behind this article is ancient.
Edit 3:
In that article you shared, they link to the study in the second paragraph. Follow that link, and you’ll see this at the top:
There were selection effects in the follow-up study, but seemed worth mentioning anyway.
It wasn’t an assumption:
That is not a skeptical position.
And my point is that given that the data shows objectively that it does fool people - even subject matter experts - it is reasonable to believe that effect continues until proven otherwise. We know it’s a feature of LLMs, and the fact you continue to push on with your blind faith undisturbed by this knowledge is truly alarming.
In the follow up study, first of all I want to point out that it’s not definitive that it made them faster, the error bars include regions where they were slowed down. And none of this includes the long-term effects of poorly made, unmaintainable code that was farted out in bulk by an overworked engineer who didn’t have time to properly review code that they didn’t write and don’t fully understand.
It also doesn’t include the effects of long term exposure to LLMs reducing their solo effectiveness. If you only measure the immediate delta, then it could look like the LLM is helping when actually it’s just making people dependent.
And the selected dev quotes are also alarming in light of that information:
These quotes don’t demonstrate that LLMs actually help, only that they are addictive, which we already know to be true. If you’ve ever tried to talk to an addict about their problem you’d recognise this language.
Especially the quote that they could do something in 2 hours with an LLM that would take 20 hours alone. That can’t be true, that person is definitely wrong about the effect of the LLM. If it were really that effective, LLM companies would be clamouring to show the data that proves how effective their products are. Why aren’t they?
The fact this data is so hard to find and so hard to fund when there are so many billions being dumped into this field should tell you something, it should be deeply disturbing, but you just carry on fully convinced that you’re right and that there’s nothing to what I’m saying, even though you admitted you would’ve agreed just 3 months ago. Again, if you can actually show that the difference is so dramatic, then show it. You’re not though. You’re just convinced that you don’t need to re-evaluate what you believe. That doesn’t say good things about where your head’s at.
If you truly weren’t trying to convince me, you could just stop. I don’t know what you’re trying to prove by continuing.