rsanheim

filter is also just filter in ruby - aliased as select (and find_all) on Enumerable.

has Gas Town shipping something in public that can be evaluated without all of this surrounding hype and blogposting?

No.

This post sets up a straw man from the outset, and only gets worse from there.

I understand how we got here, where many experienced programmers, managers, and bloggers only know capital-A Agile as the watered down version sold via certifications, crummy medium posts, and atlassian flavored kanban boards. But that isn't agile.

I can’t even with the pitch into spec driven development as some sort of high watermark of software methodology.

Bragging about loc was silly before ai. Now it’s not only silly, but also makes you look like a huge tool.

Wow. So much hate in the comments here. Of all the funding / equity events lately, I wonder how this one gets so much doubt and distrust from the start.

If this isn’t something to at least root for, in the sense of a small team, novel product, serving a real need, then I dunno what is. You can use jj or tangled and still appreciate improvements to git and vcs on the web in general. Competition amongst many players is a good thing, even if you don’t believe in this one particular vision.

Heaven forbid it isn’t 100M going to a YC alum for yet another AI funding raise.

Yeah /simplify is your friend. That and constrained prompts - “refactor x for simplicity - resulting diff must remove n lines of code. Dont change tests. “

Wait what. For real? I knew their security posture was bad, but this bad??

This has been the case for 15-20 years at least. It’s only now that the horrible experience for regular users is so obvious compared to Linux becoming quite good, and Mac OS ranging from fine to meh.

The continual recall/ai push from Microsoft has not helped at all and is pretty gross. There is a way to do a “recall” style thing that some folks will really want if they can trust it. The msft approach has been the opposite of that.

If you believe this has any long term staying power at MSFT, I have a bridge to sell you paid for with MSFT stock funded by quarterly earnings reports.

Yes. This. Too little too late MSFT.

And it really comes down to $MSFT. If the stock keeps dropping, how long do you think any real commitment to “quality” for a boring, low(no?) revenue product will last? Very little when the ad/partner revenue really starts flowing for “ai focused metrics” that can directly tie to windows surveillance (ie recall).

I’ve found LLM development expands the scope of what I can do to an absurd level. This is what exhausts me.

My limits are now many of the same things that are have always been core to software dev, but are now even more obvious:

- what is the thing we are building? What is the core product or bug fix or feature?

- what are we _not_ building? What do we not care about?

- do I understand the code enough to guide design and architecture?

- can I guide dev and make good choices when it’s far outside my expertise but I know enough to “smell” when things are going off the rails

It’s a weird time

Codex does something sorta magical where it auto compacts, partially maybe, when it has the chance. I don’t know how it works, and there is little UI indication for it.

No. Nope. Agents do just fine with all sorts of CLIs. Old standards, new custom stuff, whatever.

The CLIs I’ve seen agents struggle with are those that wrap an enormous, unwieldy, poorly designed API under one namespace. All of Google Workspace apis, for example.

he favors Codex?

The original name of his ai assistant tool was 'clawdbot' until Anthropic C&D'ed him. All the examples and blog posts walking thru new user setup on a mac mini or VPS were assuming a claude code max account.

I know he uses many llms for his actual software dev.. - right tool for the job. But the origins of openclaw seem to me more rooted in claude code than codex.

Which does give the whole story an interesting angle when you consider the safety/alignment angle that Anthropic pledges to (publicly) and OpenAI pretty much ignores (publicly). Which is ironic, as configuring codex cli to 'full yolo mode' feels more burdensome and scary than in Claude Code. But I'm pretty sure that speaks more to eng/product decisions, and not CEO & biz strategy choices.

But on the nuclear issue, it's not a good sign that he's explicitly saying that this AGI future is a threat to nuclear deterrence and the triad. Like, where do you go up from there? That's the highest level of alarm that any government can have. This isn't a boy crying wolf, it's the loudest klaxon you can possibly make.

This is not new. Anthropic has raised these concerns in their system cards for previous versions of Opus/Sonnet. Maybe in slightly more dryer terms, and buried in a 100+ page PDF, but they have raised the risk of either

a) a small group of bad actors w/ access to frontier models, technical know-how (both 'llm/ai how to bypass restrictions' and making and sourcing weapons) to turn that into dirty bombs / small nuclear devices and where to deploy them. b) the bigger, more scifi threat, of a fleet of agents going rogue, maybe on orders of a nation state, to do the same

I think option a is much more frightening and likely. option b makes for better scifi thrillers, and still could happen in 5-30ish(??) years.

Also many CLIs act differently when invoked connected to a terminal (TUI/interactive) vs not. So you’d run into issues there where Claude could only test the non-interactive things.

Is there a term for AI-fueled dev psychosis? "AI architecture astronaut" ? There should be one if not. Or maybe just AI-fueled hucksterisim...

I recognize 100% that a tool to manage ai agents with long term context tracking is going to be a big thing. Many folks have written versions of this already. But mashing together the complexity of k8s with a hodge podge of lotr and mad max references is not it.

Its like the complexity of J2EE combined with AI-fueled solipsim and a microdosing mushroom regime gone off the rails. What even are all the layers of abstractions here? and to build what? What actual apps or systems has this thing built? AFAICT it has built gas town, and nothing else. Not surprising that it has eaten its own tail.

The amount of jargon, ai art, pop culture references, and excessive complexity going on here is truly amazing, and I would assume its satire if I didn't know Yegge's style and previous writings. Its like someone looked at the amount of overlapping and confusing tools Anthropic has released around Claude Code, and said "hold my beer, hand me 3 red bulls and a shot of espresso, I can top that!".

I do think a friend of mine nailed it though with this quote: "This whole "I'm using agents to write so much software" building-in-public trend, but without actually showing what they built, reminds me of the people selling courses on stock trading or drop shipping."

The amount of get-rich quick schemes around any new tech are boundless. As yegge himself points out in the post towards the end, you'd be surprised what you can pull off with a ridiculous blog post, big-tech reputation, and excessive LOC dev-tools in a hype-driven market. How could it be wrong if it aligns so closely with so many CEOs dreams?

The performance of hardware today is even more mind-boggling compared to what most people (SRE managers, devs, CTOs) are willing to pay for when it comes to cloud compute.

even more so when considered in the context of dev 'remote workstations'. I benchmarked perf on AWS instances that was at least 5x slower than an average m1 macbook, and cost hundreds of dollars a dev per month (easily), and the macbook was a sunk cost!

These exist, typically made by Panasonic or Sony, and cost upwards of 20k USD. HDTVtest has compared them to the top OLED consumer tvs in the past. Film studios use the reference models for their editing and mastering work.

Sony specifically targets the reference with their final calibration on their top TVs, assuming you are in Cinema or Dolby Vision mode, or whatever they call it this year.

_low_type_ is early days still, but I think this approach is clearly the future of ruby typing. If this gets baked into the language for full “compile” time support and minimal performance impact, it will be amazing: https://github.com/low-rb/low_type

Yeah, this is very real, and I think it can inflict paralysis on programmers with a certain level of experience and 'i know better' syndrome. Or even a 'it _might_ be better' type syndrome.

Sometimes, you might really know better, and it doesn't matter. You build the thing with the wrong tools, with a crummy framework, with a product at the end that will probably not succeed. But that is okay, hopefully you learn something and your team and your org learn something.

And if not, that is okay, sometimes its just a job and you need a paycheck and a place to be from 9 to 5.

It was really a blending of multiple genres. Was really ground breaking by for its time.

But …you have to give the MCP the creds somehow. Maybe it’s via a file on disk (bad), maybe via an env var (less bad). Maybe you do it via your password CLI that you biometricly auth to, which involves a timeout of some sort for security, but that often means you can’t leave an agent unattended.

In any case, how is any of this better than a CLI? CLIs have the same access models and tradeoffs, and a persistent agent will plumb the depths of your file system and environment to find a token to do a thing if your prompt was “do a thing, use tool/mcp/cli”.

So where is this encapsulation benefit?

I think the answer is it doesn't fit in any definition of a _good_ monitoring stack, but we are stuck with it. It has largely become the blessed protocol, specification, and standard for OSS monitoring, along every axis (logging, tracing, collecting, instrumentation, etc)...its a bit like the efforts that resulted in J2EE and EJBs back in the day, only more diffuse and with more varied implementations.

And we don't really have a simpler alternative in sight...at least in the java days there was the disgust and reaction via struts, spring, EJB3+, and of course other languages and communities.

Not sure how we exactly we got into such an over-engineered mono-culture in terms of operations and monitoring and deployment for 80%+ of the industry (k8s + graf/loki/tempo + endless supporting tools or flavors), but it is really a sad state.

Then you have endless implementations handling bits and pieces of various parts of the spec, and of course you have the tools to actually ingest and analyze and report on them.

Did not feel LLM written to me - at least not overtly so. LLM editing/assisted perhaps?

It was a fun little post that felt accurate (ie confirmed my own biases ;)) about the current state of LLM models in a silly, but real, use-case.

The continual drive to out "llm written" articles feels a bit silly to me at this point. They are now part of the tools and tech we use, for better or worse. And to be clear, I think in a lot of cases it leans towards 'worse'.

But do you question if a video or photo was made with digital editing or filters or 'ai' tools (many of which we've had for years, just under different names) ? Do you worry about what tech was used in making your favorite album or song?

I get it, LLMs make it easy to produce trash content, but this is not a new problem. If you see trash, call it out as trash on its flaws, not on a presumption of how it was made.

because its a huge hassle that many financial services companies have no incentive to facilitate or make easy or discoverable. And for many folks a job change is a stressful event even in the _best_ of circumstances.

I know when I was laid off a week after covid lockdowns, the last thing I was thinking about was how to roll over my 401k as the market collapsed and I began interviewing and trying not to freak out.

having retirement and health benefits coupled to employment is antiquated and stupid, but changing tax code and finance system around 401ks is probably the least of our problems in the US.

Just...don't use them?

I've use mise happily for many months without using direnv or tasks, and everything I use it for works and is solid. Installs python, ruby, node, does the switching, does the shims, stays out of the way.

direnv and tasks and everything else mise can do is all opt-in.

I wonder what kind of outage or incident or economic change will be required to cause a rejection of the big commercial clouds as the default deployment model.

The costs, performance overhead, and complexity of a modern AWS deployment are insane and so out of line with what most companies should be taking on. But hype + microservices + sunk cost, and here we are.

uhmm... wat?

where was there any mention in the OP of Jobs about diversity or his Syrian background?

Because Claude code does offer particular features. More important than “features” is the fact that it works and does the things you want like 60-70% of the time, with guardrails and practice and attention. Which is way better than competing tools.

Besides that. These tools are changing so fast that to build an agent agnostic tool would be insane given the speed and market pressures right now. Why support roo or cline or cursor cli if it adds 3x engineering cost for 20% more market reach? The reality is there are no standards around the way the actual leading tools work if you wanna build something on Claude/codex/(insert flavor of the week).

Gotta pick your horse and try to hang on, and hope you picked right.