You find growing an incredibly water heavy crop in a place that doesn’t have the water supply to do so a weird comparison? And it’s not even a food that’s needed, so you can’t stand on that either.
Hahahaha yeah, makes sense. Every time I use claude after codex I feel like I’m holding Claude’s hand the entire time. I imagine they have a lot of containing they have to do internally
This is neat to see. US army crops of engineers is a negative “word” to me after growing up in FL and they destroyed so many ecosystems. And the entire Everglades. They’re still at it now. My family has basically spent the past 30 years fighting a ware they put in on our natural creek. It killed the creek, it shrunk the flow to the size of the culvert.
So, It’s neat to see something competent! Imagine if they modeled what cutting off the natural draining to the Everglades would do :p
The existence of negative externalities or tradeoffs does not inherently imply incompetence.
I remember reading that the USACE said the NOLA levees would not adequately protect against a category 5 hurricane but the powers that be didn’t think the added cost for a more robust design was worth the risk. If true, it doesn’t imply USACE was incompetent but that we live in an uncertain world with tough tradeoffs.
> Compounding the problem, labs in China often release dual-use capable models as open-weight. Once a model is open-weight, safeguards that do exist can be removed, making the model available to any state or non-state actor to use for malicious purposes, including the cyber and CBRN misuse those safeguards were built to prevent.
I know it’s super fun to shit on GitHub and everyone’s favorite thing to say is “build a competitor!”
They’re trying to scale from 1 billion commits last year to over 14 billion this year. I have zero desire to try and manage that scaling. Basically being DDOS’d by agents all day now.
> I have zero desire to try and manage that scaling.
Last time I checked, this is called "doing their job".
You are free to choose what company you want to work for, but for github, if they are offering the services, often as paid services, they have an obligation to keep things running which is called SLA. Otherwise people will leave (and are leaving)
I have no idea how that’s what you get from this. I don’t want my project using any tech that decides to take 6 days to rewrite the entire library with AI. That is at its core an engineering decision.
No healthy engineering team is going to do that. And I’d want to distance myself as far as I could from a project that behaves like that.
Which is funny because Anthropic is the SOTA that the DoD has been using for more than 2 years. They already have blood on their hands with helping the Iran attack. He joined it
But it's a self fulfilling prophecy. They need all this stuff because it's a vibe coded app where bugs are randomly introduced, the architecture is overcomplicated and sucks, and stuff is just added for the fun of it.
Do existing companies run entire end-to-end product integration tests on every single change they make to a repo to make sure something hasn't broken? No, they just architect things in a way such that a minor change to something can be tested in isolation. And that can be automated, deterministically and efficiently.
Where I work we can release changes to our production site in minutes almost completely autonomously with high confidence with absolutely zero AI agents in the loop. How did we do it? With lessons learned from the past 5 decades of professional software development experience.
Lets not forget what OpenClaw is at it's core. It's a glorified cron scheduler. Why on earth does any of this effort need to exist. It's not that deep, it's not that complex, it's all AI for AI's sake.
OpenClaw has surprisingly few "dumb" bugs. Is it as stable and secure as the Linux kernel? God no, obviously not. But it has never just crashed for me, for example. Bugs are of the type "X with Y and Z disabled and T turned on - doesn't work", where you're likely one of a few people that have ever tried this combination. Not to mention it can then debug itself and file a bug report, with a bugfix - if you give it a GitHub token.
I run it in a firewalled VM and am very conscious about any tokens I give it access to - so far for all I know this was unnecessary.
PS. for me the core feature of OpenClaw isn't the cron, though that is nice. It's the memory and instant extensibility. Like it takes 5-15 minutes to add an SSH tool where all agent requests go through a manual review, together with a good auto loaded description that just works in all future sessions.
For the few weeks in which I’ve been using it, it has brought down the Raspberry Pi it’s running on several times with extreme resource hogging, local history/memory search is broken due to a trivial bug for which all issues are auto-closed by bits, and it has changed its configuration standards a handful of times in a way that broke my instant messaging access to it, just to name a few gripes.
This is clearly an implementation and not a conceptual issue, as I had none of these issues using the same model with Hermes, for example.
"All that automation allows us to run extremely lean"
He has a different opinion of what it means to be lean than almost everyone else. That's fine, he's allowed to, but it's something you have to understand to make sense of any of his comments on things. He has a radically different set of values to most people.
His team is basically him and two other humans, powering an ambitious well-known project so successful an industry titan ended up acquihiring him/them. That's pretty lean, no?
The ambitious idea is actually giving a chatbot/agent access to a bunch of personal data and having it self-modify its harness and context to some extent.
But it costs $1.3m USD a month to run, not including their salaries. That's the cost of a team of 50-200 staff, depending on where you're hiring.
I don't think there's any way most people would call that lean. It's lean in exactly 1 axis which is people, but no one really cares about that, people is always a proxy for cost.
He said in another thread there's 6 people involved. 6 people for this project doesn't feel lean, without even considering the enormous LLM spend/complexity
Where is that figure from? I would be extremely surprised if that doesn't drop at least an order of magnitude as the hype wears off. Assuming it's even representative of today and not two months ago
If these methods prove successful it isn't going to matter. A user doesn't care if code is 'slop' or artisanal, so long as the app/site/whatever works.
If you can combine autonomous flows (and millions of dollars in tokens) to produce work comparable to a traditional engineering team, then why would the user care which wrote the app/site/whatever?
Yeah, of course hunans will still be writing code in a 100 years. I am certain we still won't have flying cars either.
Agricultural mechanisation didn't eliminate human labor over the 20th century. A huge fraction of the world's farmers have little or no mechanization today, well over a century after the invention of the revolutionary farm tractor.
With apologies to Ada Lovelace, but humanity has been writing code in anger for only like, 80 years? We'll still be at it in a 100 more.
I think you have a fair point. It is possible that LLMs won't scale/advance enough and a fundamentally new approach is needed.
I'm personally just impressed with the rate of improvement and _hope_ that it will continue, and that inference prices will fall (or on-device LLM become more feasible/powerful).
Anyway I appreciate your perspective even though I don't necessarily share it
> People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question:
How would we build software in the future if tokens don't matter?
[...]
All that automation allows us to run this project extremely lean.
Good thing we cleared that up. Another gem from the "if we had self-driving cars, we could just have them cruise on the roads endlessly when not in use and get rid of so much parking space!" school of resource management...
reply