Summarizer

There's an odd trend with these sorts of posts where the author claims to have had some transformative change in their workflow brought upon by LLM coding tools, but also seemingly has nothing to show for it. To me, using the most recent ChatGPT Codex (5.3 on "Extra High" reasoning), it's incredibly obvious that while these tools are surprisingly good at doing repetitive or locally-scoped tasks, they immediately fall apart when faced with the types of things that are actually difficult in software development and require non-trivial amounts of guidance and hand-holding to get things right. This can still be useful, but is a far cry from what seems to be the online discourse right now. As a real world example, I was told to evaluate Claude Code and ChatGPT codex at my current job since my boss had heard about them and wanted to know what it would mean for our operations. Our main environment is a C# and Typescript monorepo with 2 products being developed, and even with a pretty extensive test suite and a nearly 100 line "AGENTS.md" file, all models I tried basically fail or try to shortcut nearly every task I give it, even when using "plan mode" to give it time to come up with a plan before starting. To be fair, I was able to get it to work pretty well after giving it extremely detailed instructions and monitoring the "thinking" output and stopping it when I see something wrong there to correct it, but at that point I felt silly for spending all that effort just driving the bot instead of doing it myself. It almost feels like this is some "open secret" which we're all pretending isn't the case too, since if it were really as good as a lot of people are saying there should be a massive increase in the number of high quality projects/products being developed. I don't mean to sound dismissive, but I really do feel like I'm going crazy here.

>driving the LLM instead of doing it yourself. - sometimes I just can't get the activation energy and the LLM is always ready to go so it gives me a kickstart There is a counter issue though, realizing mid session that the model won’t be able to deliver that last 10%, and now you have to either grok a dump of half finished code or start from scratch.

I wonder about this. If (and it's a big if) the LLM gives you something that kinda, sorta, works, it may be an easier task to keep that working, and make it work better, while you refactor it, than it would have been to write it from scratch. That is going to depend a lot on the skillset and motivation of the programmer, as well as the quality of the initial code dump, but... There's a lot to be said for working code. After all, how many prototypes get shipped?

> To be fair, I was able to get it to work pretty well after giving it extremely detailed instructions and monitoring the "thinking" output and stopping it when I see something wrong there to correct it, but at that point I felt silly for spending all that effort just driving the bot instead of doing it myself. This is the challenge I also face, it's not always obvious when a change I want will be properly understood by the LLM. Sometimes it one shots it, then others I go back and forth until I could have just done it myself. If we have to get super detailed in our descriptions, at what point are we just writing in some ad-hoc "programming language" that then transpiles to the actual program?

> I’ve been wanting to develop a plastic -> silicone -> plaster -> clay mold making process for years, but it’s complex and mold making is both art and science. It would have been hundreds of hours before, with maybe 12 hours of Claude code I’m almost there (some nagging issues… maybe another hour). That’s so nebulous and likely just plain wrong. I have some experience with silicone molds and casting silicone and other materials. I have no idea how you’d accurately estimate it would take hundreds of hours. But the mostly likely reason you’ve had results is that you just did it. This sounds very very much like confirmation bias. “I started drinking pine needle tea and then 5 days later my cold got better!” I use AI, it’s useful for lots of things, but this kind of anecdote is terrible evidence.

I’m working on a solo project, a location-based game platform that includes games like Pac-Man you play by walking paths in a park. If I cut my coding time to zero, that might make me go two or three times faster. There is a lot of stuff that is not coding. Designing, experimenting, testing, redesigning, completely changing how I do something, etc. There is a lot more to doing a project than just coding. I am seeing a big speed up, but that doesn’t mean I can complete the project in a week. (These projects are never really a completed anyway, until you give up on it).

As others have said, the benefit is speed, not quality. And in my experience you get a lot more speed if you’re willing to settle for less quality. But the reason you don’t see a flood of great products is that the managerial layer has no idea what to do with massively increased productivity (velocity). Ask even a Google what they’d do with doubly effective engineers and the standard answer is to lay half of them off.

At my work I interview a lot of fresh grads and interns. I have been doing that consistently for last 4 years. During the interviews I always ask the candidates to show and tell, share their screen and talk about their projects and work at school and other internships. Since last few months, I have seen a notable difference in the quality and extent of projects these students have been able to accomplish. Every project and website they show looks polished, most of those could be a full startup MVP pre AI days. The bar has clearly been raised way high, very fast with AI.

> if it were really as good as a lot of people are saying there should be a massive increase in the number of high quality projects/products being developed. The headline gain is speed. Almost no-one's talking about quality - they're moving too fast to notice the lack.

> ... but also seemingly has nothing to show for it This x1000, I find it so ridiculous. usually when someone hypes it up it's things like, "i have it text my gf good morning every day!!", or "it analyzed every single document on my computer and wrote me a poem!!"

Completely agree. However I do get some productivity boost by using ChatGPT as an improved Google search able to customize the answer to what I need.

> The C compiler that Anthropic created or whatever verb your want to use should prove that Claude is capable of doing reasonably complex level of making software. I don't doubt that an LLM would theoretically be capable of doing these sorts of things, nor did I intend to give off that sentiment, rather I was more evaluating if it was as practical as some people seem to be making the case for. For example, a C compiler is very impressive, but its clear from the blog post[0] that this required a massive amount of effort setting things up and constant monitoring and working around limitations of Claude Code and whatnot, not to mention $20,000. That doesn't seem at all practical, and I wonder if Nicholas Carlini (the author of the Anthropic post) would have had more success using Claude Code alongside his own abilities for significantly cheaper. While it might seem like moving the goalpost, I don't think it's the same thing to compare what I was saying with the fact that a multi billion dollar corporation whose entire business model relies on it can vibe code a C compiler with $20,000 worth of tokens. > The problem is people have egos, myself included. Not in the inflated sense, but in the "I built a thing a now the Internet is shitting on me and I feel bad" sense. Yes, this is actually a good point. I do feel like there's a self report bias at play here when it comes to this too. For example, someone might feel like they're more productive, but their output is roughly the same as what it was pre-LLM tooling. This is kind of where I'm at right now with this whole thing. > The "open secret" is that shipping stuff is hard. Who hasn't bought a domain name for a side project that didn't go anywhere. If there's anybody out there, raise your hand! So there's another filtering effect. My hand is definitely up here, shipping is very hard! I would also agree that it's an "open secret", especially given that "buying a domain name for a side project that never goes anywhere" is such a universal experience. I think both things can be true though. It can be true that these tools are definitely a step up from traditional IDE-style tooling, while also being true that they are not nearly as good as some would have you believe. I appreciate the insight, thanks for replying. [0]: https://www.anthropic.com/engineering/building-c-compiler

From the linked project: > The reality: 3 weeks in, ~50 hours of coding, and I'm mass-producing features faster than I can stabilize them. Things break. A lot. But when it works, it works.

It's like CGP Grey hosting a productivity podcast despite his productivity almost certainly going down over time. It's the appearance of productivity, not actual productivity.

The difference is a real engineer will say "hey I need more information to give you decent output." And when the AI does do that, congrats, the time you spend identifying and explaining the complexity _is_ the hard time consuming work. The code is trivial once you figure out the rest. The time savings are fake.

It has nothing to do with power. I just want to build bigger, cooler things, faster.

I liken it to being an author. You want to write a book about people's deepest motivations. Formative experiences, relationships, desires. Society, expectations, disappointment. Characters need to meet and talk at certain times. The plot needs to make sense. You bring it to your editor. He finds you forgot to capitalise a proper noun. You also missed an Oxford comma. You used "their" instead of "they're". He sends you back. You didn't get any feedback about whether it makes sense that the characters did what they did. You are in hell, you won't hear anything about the structure until you fix your commas. Eventually someone invents an automatic editor. It fixes all the little grammar and spelling and punctuation issues for you. Now you can bring the script to an editor who tells you the character needs more development. You are making progress. Your only issue is the Luddites who reckon you aren't a real author, because you tend to fail their LeetGrammar tests, calling you a vibe author.

If you look at his github you can see he is in the first week of giving into the vibes. The first week always leads to the person making absurd claims about productivity.

>Somehow 90% of these posts don't actually link to the amazing projects that their author is supposedly building with AI. Maybe they don't feel like sharing yet another half working Javascript Sudoku Solver or yet another half working AI tool no one will ever use? Probably they feel amazed about what they accomplished but they feel the public won't feel the same.

The article made it seem that the tool made them into the manager of a successful company, rather than the author of a half finished pet project

Grifters gotta grift. There is so much money on the line and everyone is trying to be an influencer/“thought leader” in the area. Nobody is actually using AI for anything useful or THEY WOULDNT BE TALKING ABOUT IT. They’d be disrupting everything and making billions of dollars. Instead this whole AI grift reads like “how to be a millionaire in 10 days” grifts by people that aren’t, in fact, millionaires.

Did they even end up launching and maintaining the project? Did things break and were they able to fix it properly? The amount of front-loaded fondness for this technology without any of the practical execution and follow up really bugs me. It's like we all fell under the spell of a terminal endlessly printing output as some kind of measurement of progress.

Very likely part of their bots output. The ultimate goal isn’t to make useful things, but to “teach” others how to do it and convince them how successful they can become.

AI is all facade

> “hey remember that conversation about birds? Send an email to Steve and ask him what he thinks about it” Isn’t the “what he thinks about it” part the hardest? Like, that’s what I want to phrase myself - the part of the conversation I’d like to get their opinion on and what exactly my actual request is. Or are people really doing the meme of sending AI text back and forth to each other with none the wiser?

>I used to have way too many ideas but no way to build them all on my own—they just kept piling up. But now, everything is different. This has been a significant aspect of ai use as well. As a result a feel a little less friction with myself, less that I am letting things slip by because, well, because I still want a nice balance to work, life, leisure, etc. I don’t want to overstate things, it’s not a cure all for any of these things, but it helps a lot.

It is already known as Ai psychosis and ai productivity porn

> My productivity did improve, but for any given task, I still had to jump into the project, set up the environment, open my editor and Claude Code terminal. I was still the operator; the only difference was that instead of typing code manually, I was typing intent into a chat box. > Then OpenClaw came along, and everything changed. > After a few rounds of practice, I found that I could completely step away from the programming environment and handle an entire project’s development, testing, deployment, launch, and usage—all through chatting on my phone. So, with Claude Code, you're stuck typing in a chat box. Now, with OpenClaw, you can type in a chat box on your phone? This is exciting and revolutionary.

These are the same people who a few years ago made blogposts about their elaborate Notion (or Roam "Research") setups, and how it catalyzed them to... *checks notes* create blogposts about their elaborate Notion setups!

Midwits love this kind of stuff. Movie critics heap praise on forgettable movies to get their names and quotes on the movie poster. Robert Scoble made an entire career in tech bloviation hyping the current thing and got invited to the coolest parties. LinkedIn is a word salad conveyor belt of this kind of useless nonsense. It's a racket never ends.

There seem to be a lot of posts like this as of late. I truly can't decide if the authors actually believe what they've written or if it's some preposition of themselves to be included in the hype cycle of AI FOMO or what. It feels very cringe as I read it. As if to say OpenClaw has somehow been such a pivotal change in their life, so monumental, that it's an epiphany that has changed them forever. Maybe it's just the fact that I've been surrounded by automation for many years and also using it with agents or LLMs for the past couple that I just don't feel like this is a true sentiment of what actually exists. It feels placed, it feels targeted and it feels like a huge lie. I guess you could also call it low effort marketing.

I’m working on a product related to “sensemaking”. And I’m using this abstract, academic term on purpose to highlight the emotional experience, rather than “analysis” or “understanding”. It is a constant lure products and tools have to create the feeling of sensemaking. People want (pejorative) tools that show visualizations or summaries, without thinking about the particular visual/summary artifact is useful, actionable or accurate!

True, but it does have the cottage industry of influencers selling their vault skeleton and template/plugin packs for unlocking maximum productivity… same as notion. And Evernote, to an extent, before that.

And how to properly use your Day-Runner before that (c1996). Productivity hacks sell because humans want silver bullets.

Yeah, but so does many other good things. Exercise is generally a good thing, so is decent quality food, meditation, philosophy, healthy relationships, etc. Those are things that also have a cottage industry of influencers who are selling their “thing” about how you should do it. The problem there is the influencers and their culture not the food or working out, etc. It only becomes problematic if the “good” thing also indulges in the hubris of influencers because they view it as good marketing. Like when an egg farm leans in “orange yolk”

Yeah, after getting burnt out on Evernote I just use basic markdown files for my notes. I never bother with anymore features beyond "write to file" or "grep directory for keywords" because I know I'll personally not benefit from them. The act of writing notes is what is useful to me, retrieving the notes are hardly ever useful.

Hah, I read that as well and made a big "hmmmmmmmmm" sound... The last time I talked to someone about OpenClaw and how it is helping them, they told me it tells them what their calendar has for them today or auto-tweets for them (i.e., non-human spam). The first is as simple as checking your calendar, and the second is blatant spam. Anyone found some good use cases beyond a better interface for AI code assistance?

> how it is helping them This should be the opening for every post about the various "innovations" in the space. Preferably with a subsequent line about the manual process that was worth putting the extra effort into prior to the shiny new thing . I really can imagine a better UX then opening my calendar in one-click and manual scanning. Another frequent theme is "tell me the weather." One again, Google home (alexa or whatever) handles it while I'm still in bed and let's me go longer without staring at a screen. The spam use-case is probably the best use-case I've seen, as in it truly saves time for an equal or better result, but that means being cool with being a spammer.

I think a sizable proportion of people just want to play "large company exec". Their dream is to have an assistant telling them how busy their day is, all the meetings they have, then to go to those meetings and listen to random fluff people tell them while saying "mmh yeah what a wise observation" or "mmh no not enough synergy here, let's pivot and really leave our mark on this market, crunch the numbers again". I can't come up with any other explanation for why there seems to be so many people claiming that AI is changing their life and workflow, as if they have a whole team of junior engineers at their disposal, and yet have really not that much to show for it. They're so white collar-pilled that they're in utter bliss experiencing a simulation of the peak white collar experience, being a mid-level manager in meetings all day telling others what to do, with nothing tangible coming out of it.

Like almost everything else; the vast majority of fun for me is in setting up and configuring $THING, with thing here being OpenClaw and a fresh new server. After that I realize I have nothing to do with it and destroy the instance only to create a new one to try out some other self-hosted $THING

If my aim was to be a manager, I would have graduated a business university. But I want to have my hands and head dirty of programming, administering, and doing other technical stuff. I'm not going to manage, be it people or bots. So no, sorry. And 99% those AI-created "amazing projects" are going to be dead or meaningless in due time, rather sooner than later. Wasted energy and water, not to mention the author's lifetime.

if 90% is good enough, you are a winner to try your idea and fail fast. if you want to reach 91 or more, AI is a slop and hype to burn our pensions and contribute to vastly to global warming and cognitive decline consumerism evolution