[flagged]
Some uncomfortable truths about AI coding agents
41–50 of 122 posts
Re: Some uncomfortable truths about AI coding agents
#42Earlier quoted context omitted.
> Another way to look at this is that AI coding agents take the fun out of a software engineer's job. Completely backwards - the fun in the job should be to solve problems and come up with solutions. The fun in the job is not knowing where to place a semicolon.
> The fun in the job is not knowing where to place a semicolon. If a person needs an LLM to figure where an semicolon goes, a LLM is not going to help them code.
I don't need one to know where it goes, but it certainly is better than I am at never missing one.
Re: Some uncomfortable truths about AI coding agents
#43The skill atrophy point strikes me as tenuous at best. Obviously, the plural of anecdote is not data, but I find myself able to work on projects of greater complexity than I would have been able to otherwise. 90% of my time is spent going back and forth on Markdown files, discussing the architecture, trade-offs, etc. I don't think it's necessarily impossible to use all this newfound power to ship more sloppier code.…
> I find myself able to work on projects of greater complexity than I would have been able to otherwise
Yes. Now turn off the LLM and make an improvement to that code.
Re: Some uncomfortable truths about AI coding agents
#44The section on "artificially low costs" does not make a lot of sense to me. If anything I feel like the costs are inflated for the frontier models, not "artificially low". Easy proof: GLM-5 costs about 1/10 as much as Opus. I'm not going to tell you it's as good as Opus 4.6 -- it's not -- but it performs comparably to where frontier models were 6 months ago. (It's on par with Sonnet 4.5 on leaderboards, though in pra…
The post is factoring in training costs, not just inference.
Re: Some uncomfortable truths about AI coding agents
#45[dead]
Re: Some uncomfortable truths about AI coding agents
#46The section on "artificially low costs" does not make a lot of sense to me. If anything I feel like the costs are inflated for the frontier models, not "artificially low". Easy proof: GLM-5 costs about 1/10 as much as Opus. I'm not going to tell you it's as good as Opus 4.6 -- it's not -- but it performs comparably to where frontier models were 6 months ago. (It's on par with Sonnet 4.5 on leaderboards, though in pra…
The post is factoring in training costs, not just inference.
But I don't need to pay training costs to use GLM-5?
Re: Some uncomfortable truths about AI coding agents
#47> The role change has been described by some as becoming a sort of software engineering manager, where one writes little or no code oneself but instead supervises a team of AI coding agents as if they are a team of human junior software engineers.... > In reality, though, the code review load for software engineers will gradually increase as fewer and fewer of them are expected to supervise an ever-growing number of…
> Another way to look at this is that AI coding agents take the fun out of a software engineer's job. Completely backwards - the fun in the job should be to solve problems and come up with solutions. The fun in the job is not knowing where to place a semicolon.
The fun of the job is building a piece of software that's beautifully written. It's a way of expressing yourself
Re: Some uncomfortable truths about AI coding agents
#48The skill atrophy point strikes me as tenuous at best. Obviously, the plural of anecdote is not data, but I find myself able to work on projects of greater complexity than I would have been able to otherwise. 90% of my time is spent going back and forth on Markdown files, discussing the architecture, trade-offs, etc. I don't think it's necessarily impossible to use all this newfound power to ship more sloppier code.…
> I find myself able to work on projects of greater complexity than I would have been able to otherwise Yes. Now turn off the LLM and make an improvement to that code.
Exactly, this is like watching youtubers code, ie backseat coding. It’s easy to follow along but taking control midway is anything but, especially in a codebase that has been written by an agent
and you don’t have any muscle-memory in.
Re: Some uncomfortable truths about AI coding agents
#49The skill atrophy point strikes me as tenuous at best. Obviously, the plural of anecdote is not data, but I find myself able to work on projects of greater complexity than I would have been able to otherwise. 90% of my time is spent going back and forth on Markdown files, discussing the architecture, trade-offs, etc. I don't think it's necessarily impossible to use all this newfound power to ship more sloppier code.…
Totally agree with this taking on projects of greater complexity. I honestly feel the sloppier code thing is going to die soon. People make mistakes too. Always see people holding the machine to like this totally different standard.