I think workplaces will have to allow people time to adapt. So that if your particular skill set is replaced by AI, you have the ability to retrain to a part that isn’t.
Ultimately, large part of many jobs are repetitive, and can be replaced by pattern matching. The other side, creating new patterns, is hard and takes time. So, employers will have to take this into account. They may be long periods of “unproductive” time, or more risky evaluation to try new ideas.
I’m not saying people will be laid off, although this is what the article is about. So, I think people will still be prompting, but if you can prompt an agent and it can happily code away, what are you supposed to be doing ? Watching it do its work ? The only option is that you will have to generate ideas of new work constantly to drive value. This is something that generally happens over time now, but as implementation becomes quicker; idea generation will have to accelerate.
> So, I think people will still be prompting, but if you can prompt an agent and it can happily code away, what are you supposed to be doing ? Watching it do its work ?
Well, what do managers do once they prompt junior developers? ;)
Also, "tell a prompt and wait for it to finish without intervention" is not something that happens even with magical Claud Code.
I'd really like to see some actual theory (and position, people) surfaced that can be laid off due to AI and who and how then actually runs the LLMs in the company after layoffs. I've never been in a company where new work wouldn't fill up the available developer capacity, so I'm really interested in how the new world would look like.
I just had a thought. It used to be that complex C++ systems used to take so long to compile that developers used to go and have a coffee etc. This was before distributed compiling.
Maybe it will return to that, the job will have a lot of waiting around, and “free” time.
I agree with you but there's something ironic about seeing that comment here, especially considering how many jobs tech has replaced in the last few decades without people having the time to retrain.
It’s the responsibility of individuals to continue learning. Choosing, and to be clear, it is a choice, to stop learning can have dire consequences.
We are now a few years into LLMs being widely available/used, and if someone’s chosen to stick their head in the sand and ignore what’s happening around them, then that’s on them.
> I think workplaces will have to allow people time to adapt.
This feels like a very outdated view to me. Maybe we are worse off for that being the case but by and large that will not happen. The people who take initiative and learn will advance, while the people who refused to learn anything new or change how they’ve been doing the job for XX years will be pushed out.
> That's the whole selling point of AI tools. "You can do this without learning it, because the AI knows how"
I'm sure we are veering into "No true Scotsman" territory but that's not the type of learning/tools I'm suggesting. "Vibe Coding" is a scourge for anything more than a one-off POC but LLMs themselves are very helpful in pinpointing errors, writing common blocks of code (Copilot auto-complete style), and even things like Aider/Claude Code can be used in a good way if and only if you are reviewing _all_ the code it generates.
As soon as you disconnect yourself from the code it's game over. If you find yourself saying "Well it does what I want, commit/ship it" then you're doing it wrong.
On the other hand, there are some people who refuse to use LLMs for a wide range of reasons ranging from silly to absurd. Those people will be passed by and have no one to blame but themselves. LLMs are simply another tool in the tool box.
I am not a horse cart driver, I am a transportation expert. If the means of transport changes/advances then so will I. I will not get bogged down in "I've been driving horses for XX years and that's what I want do till the day I die", that's just silly. You have to change with the times.
> As soon as you disconnect yourself from the code it's game over
We agree on this
The only difference is that I view using LLM generated code as already a significant disconnect from the code, and you seem to think some LLM usage is possible without disconnecting from the code
Maybe you're right but I have been trying to use them this way and so far I find it makes me completely detached from what I'm building
> The only difference is that I view using LLM generated code as already a significant disconnect from the code, and you seem to think some LLM usage is possible without disconnecting from the code
It's a gray area for sure and almost no one online is talking about the same thing when they say "LLM Tools", "LLM", "Vibe Coding", "AI", etc so it makes it even harder to have conversations. It's probably a lot like the joke "Have you ever noticed that anybody driving slower than you is an idiot, and anyone going faster than you is a maniac?".
For myself, I'm fine with Github Copilot auto-completions (up to ~10 lines max) and I review every line it wrote. Most often I enjoy it for boilerplate-ish things where an abstraction would be premature but I still have to type out a bunch of boilerplate. Being able to write 1-2 examples and have it extrapolate the rest is quite nice.
I've used Aider/Claude Code [0] as well and had success but I don't love the workflow of asking it to do something, then waiting for it to spit out a bunch of code I need to review. I expect this will improve and I have seen some improvement already. For some tasks it has me beat (speed of writing UI) but most logic-type things I have been unable to prompt it well enough or give it enough/the right context to solve the problem. Because of this I mainly use these tools for one-off, POC, or just screwing around.
I also find things like explanation of errors or tracking down what the root cause of an error are useful.
I am very much _not_ a fan of "Vibe Coding" or anything that pretends it can be "no code"/"low code". I don't know if I'll ever be comfortable not reviewing the code directly but we will see. I'm sure assembly developers swore to never use C, who then swore to never use C++, who swore they'd never use python, and so on and so forth. It's not clear to me if LLM-generated code is another step up or just a tool for the current level, I'm leaning heavily towards them just being a tool. I don't think "prompt engineer" is going to be a thing.
[0] And Continue.dev, Cursor, Windsurf, Codeium, Tabnine, Junie, Jetbrains AI, and more
The difference for me, is that things are changing too fast to keep up. For example, if a large part of your job is taken away seemingly overnight, by a new model, your whole job could change in a heartbeat.
What preparation are you supposed to do for this ? Previously, change was relatively slow and it was reasonable to keep up in your own time. I believe that is no longer possible.
I'm not sure that many people have time to continue learning. Certainly when one is young it is easy, but at some point people are spending their time outside of work building a life, raising a family, etc.
My opinion is that the so called "AI", when applied to programming, is just a clever trick for avoiding the copyright laws.
Despite the fact that a half of century ago there was a lot of talk about "software reuse", that has never happened at the expected scale, but not for technical reasons. It has never happened because the copyright laws have prevented it.
During the early years of electronic computers, there were computer user groups where the programs of general interest were shared rather freely between different companies, in order to avoid the duplication of programming work. This has changed sharply after the appearance of software as a product that can be sold and bought, separately from computer hardware.
Even when there exists an open-source solution it frequently cannot be incorporated in the program you are writing for a company, due to incompatible copyrights. Therefore much of the programming work consists in rewriting with minor variations programs that have been already written countless times before, but at another company or by some individual.
The "AI" that "writes" a program for you just makes a search instead of you for one of the existing solutions, with the additional advantage that it has searched code bases that you would have been forbidden to search, and it produces a program source that has been detached from its original copyright, allowing it to be inserted in a proprietary program of your company.
A program "written" by an AI will have the highest quality when it almost matches some program that has been present in the training set. Whenever the generated program is more distant from a verbatim reproduction, being a combination of several programs or having some random changes, there is a high probability that the AI has introduced some errors, which must be corrected by a competent programmer in order to get a valid programming solution.
A human could have done exactly the same thing as the "AI", replacing most of the programming with searching then doing copy and paste, with a similar increase in productivity, but this would have been punishable by the existing laws, while when the AI does it, this is legal.
If software reuse would have been possible without copyright restrictions, then indeed less programming jobs would have been needed. So with the "AI" workaround against the laws, it is really expected to see a job number reduction in this domain.
Ultimately, large part of many jobs are repetitive, and can be replaced by pattern matching. The other side, creating new patterns, is hard and takes time. So, employers will have to take this into account. They may be long periods of “unproductive” time, or more risky evaluation to try new ideas.