Shameless plug: indeed, instead let the other person's claude talk directly to yours and figure things out. I've been working on a framework to enable this, https://aweb.ai (OSS, https://github.com/awebai/aweb). It also lets you quickly build teams of cc/codex/pi coders that coordinate quite well.
Don't be a meat proxy
641–650 of 786 posts
Re: Don't be a meat proxy
#642I deal with this all day long at work and it’s exhausting. People almost acting like no one has thought of it “I asked Claude what happened, and it spit out this 300 line response. Can you read it for me and see if it’s right?” What kills me is you might expect this from a busy high level manager that doesn’t really understand the technical details and they just point the AI to an error they got. They don’t know how…
> People almost acting like no one has thought of it
Everyone at my job uses LLMs to code, all day long. People still ask me "why does this bug happen" and I use Claude to find out and the answer is almost always straightforward, and when its not I raise a discussion with the team. The calculus isn't "can I prompt an LLM to find out," it's "do I have a solid enough mental model of the part of the codebase to prompt an LLM specifically enough, and also understand if the LLM is hallucinating or not."
> How can someone serious even think that’s ok.
I think this is a culture issue. I think every org is different, but we had a similar ramp up at our company. First we trialed cursor. Then some people were committing slop. Then we were like "llms are no excuse for slop." Then we got our skills and context good enough to not require close review. And then everything became LLM driven and now we have become "meat proxies" where everyone asks LLMs to fix things that are part of unfamiliar parts of the codebase and then asks someone else familiar to review the fix. We're tending towards a solution to this because I dont think its a good usage of resources but every org will come up with their own culture and solution to this.
Re: Don't be a meat proxy
#643Earlier quoted context omitted.
With the recent wave of posts about Claude rewriting entire codebases from Zig/Electron to Rust/Swift, I can't help but question the prompter's actual confidence in the final result. Gaining a thorough understanding of the generated output still demands an enormous amount of effort. I suspect the reality is that most people just chain a few review agents together, and if they output "LGTM", the code gets committed an…
> The foundational knowledge is lost, meaning that even if we do look at the code, we won't understand it anyway. but this is similar to a lot of other technical fields that have width and depth. People would not understand assembly any more and blindly trust the output of the compiler. People now can only design a part of a CPU, and not the entirety. Chip manufacturing is so complicated that there's probably no sing…
God the "compiler abstraction" argument is so tired, why does anyone even remotely thinks its accurate anymore
Re: Don't be a meat proxy
#644Earlier quoted context omitted.
Would you be OK with someone looking up the answer on the internet?
You mean like when juniors would copy paste Stack Overflow without verifying or even understanding it? No. We hated that too. Actual research is, of course, fine.
I see a possible misunderstanding on my part here.
My experience has typically been that engineers respond, "Claude said..." and then say what they think about it. If people are really receiving just a straight dump of AI response from their colleagues, then yeah, I would be disappointed too.
But, I have no problem receiving from a colleague, "Claude says ..., but I don't know what to make of it." The embedded space can be really hard, so I don't fault someone for feeling clueless about something. I feel that way every time I get handed something new to work on which I have zero experience with.
Re: Don't be a meat proxy
#645Worse, don’t be a “meat shield” either!
https://www.danstroot.com/posts/2026-04-16-ai-meat-shields
Re: Don't be a meat proxy
#646Earlier quoted context omitted.
Sure, but even worse, is the state-of-the-art: they use a cli agent and the "copy-paste, try to run, paste error, try to run" loop is called "Agentic engineering." Now we have to believe they're 10/10? I see no difference there except speed at the cost of whatever little understanding may have been gained by the manual inspection between steps.
Any competent developer knows there are limits to prompting. Personally I've found LLM's suck at multi-threaded applications. (Because I've been tempted by the ~agentic loop~ and been burned. Then I hand code the core logic and all is well). Woe to the developer who tries to prompt their way through this.
Skill issue /s
But seriously, lots of apps are just glorified NextJS apps which have tons of training data. Something like rust would likely churn out nonsense that compiles eventually but isn't optimal.
Re: Don't be a meat proxy
#647While I managed to avoid it for a long time, using generative AI to drive my day to day work life while resisting the pressure to become a meat proxy, I will admit that since joining an "AI native" startup I have become one. Whenever I'm trying to triage 20 different urgent things all day, every day, the economics of personalizing every message just isn't there anymore. It's not realistic. I do still try to way to filter down every AI-generated message into something digestible, but I feel like I'm in a mutually assured destruction type scenario where I can only survive the tidal wave of slop with more slop. I think we're in uncharted territory here in terms of the kind of workload generative AI can drown you in, especially when it's being used without strong discipline.
I do still think there are still places where being a meat proxy is legitimately okay or even desirable, such as PR comments. If everyone's code is generated by AI, and AI will ultimately be the primary consumer of the PR comments, it seems reasonable to me to allow AI to write the comments. Maybe I've just lost my mind though.
Re: Don't be a meat proxy
#648On social media, I saw the much more vulgar “Learned engineering just to become the condom between Claude Code and prod” And that (re)framing helped as well to think about the “what are we even (left) doing” as an industry
It's interesting to me, I have never once felt this. I have basically just been excited by using AI for coding. I've been a software engineer for 15 years and before that a physics PH.D. student (and 1 year professional scientist) who focused largely on computational work. I love programming and I've felt reinvigorated by the introduction of AI and developing systems around it. I tend to think it's just different per…
I enjoy and use AI a lot both for personal projects, but also at work. I think that feeling of “we’ve become claude code babysitters” is a lot more prevalent in larger teams and/or in work environments where … most people have resorted to claude coding all the time.
You can’t not claude code if everyone else is pushing to main (or opening prs which get ai reviewed), and once your days become mostly prompting and ai code review, you start remembering the days (mere months ago) where work did not feel or look like this at all.
The condom image is both an exaggeration, but is also almost a too-accurate depiction of what work has become - very rapidly - for many people.
I’m sure people were also very excited to get their first cars after years of riding on horses. It doesn’t mean new kinds of pollution (and accidents) are not happening, or that we don’t miss horse riding haha
Cheers
Re: Don't be a meat proxy
#649Earlier quoted context omitted.
Here's my plan: It's gotten to a point where if I see valid `code` in responses I assume it's AI junk output and I scold the commenter.
Just FYI, scolding people causes them to resent you. Take great care when giving negative feedback. Courtesy costs you very little and gains a lot.
This doesn't mean that you can't give negative feedback. But, I tend to make suggestions/requests rather than calling someone out.
If you're a manager, part of the job is telling someone that they aren't meeting standard, and that's how I would phrase it. Tell them what the expectation is and ask them to work on meeting it.
Scolding, calling out, or even yelling at people should be consigned to the past. It's unnecessary and counterproductive.
Re: Don't be a meat proxy
#650Earlier quoted context omitted.
I’m not a developer, but when I watch devs whose work process is prompt, copy-paste, try to run, paste error into code, try to run, etc. I can’t help but think they’re unskilled. There’s no brain engagement, no understanding of the bigger picture, just being a worse slower agent.
I think the worst is when they are skilled. You're basically describing my work day. My job went from interesting, highly skilled work to mostly horrible brain rot over the past year. It's depressing and I don't know a way out. Other then a complete career change, throwing away 30 years of experience and a matching salary.
Maybe it's because my org gave us permission to fail and make mistakes, but I transitioned to AI driven development pretty quickly and am having fun learning how to best drive the AI to produce good quality code, with harnesses and patterns to prevent mistakes and a process to learn and rollback. It's a different kind of engineering now. I find myself thinking more product level and system level than if else branches. I think I've been able to upskill in ways that I wouldn't have been able to if I were still writing code by hand, mainly because I have the bandwidth to do so now.
I only have 10 years of experience, so I'm not trying to say that your lived experience is invalid, but personally I figure if this is the way the industry is heading then I may as well try to learn how to thrive within the new environment.