chatmasta

You can write a CLI in typescript and bundle it into a a single JS file. In fact (without looking) I’m sure that’s what Cloudflare is doing here because it’s standard practice.

The people who need this most are not going to want to use an external MCP server. This is a pretty unusual model for a narrowly scoped product offering like this. I was excited until I realized it’s not something I can run locally.

Typescript and the npm/JS ecosystem may be complex, but you don’t need AGI to figure out how to install a CLI built with TS. My agent can figure out how to install this.

I’ve long wanted to take a digital inventory of my big box (boxes) of cables, with photo, connector types, etc.

There’s probably some selection bias here if people are close to death (either by suicide or terminal diagnosis) and looking for the solution.

Just want to let you know that I appreciated this joke even if nobody else noticed it.

Clear the session after 300k tokens and force your workflow to adapt to it. The rabbit holes come when you’re at context rot and blindly following Claude debugging some problem that you shouldn’t even be trying to solve.

Other than that, set an alarm when you want to stop working. When it rings, physically unplug your work laptop and move it somewhere out of sight.

Let me rephrase the question to the scope of startups. A small business is not a startup: https://www.paulgraham.com/growth.html

But you’re also completely right.

Typing bash commands on a colleague’s French keyboard was one of the most frustrating experiences of my life.

The candidate may have had more success if he saved the honesty for after he solved the riddle he claimed he already knew how to solve.

I expect we can squeeze a lot more exponential out of LLMs because they’ve basically shown that human “consciousness,” insofar as it’s composed of knowledge and rules for synthesizing that knowledge, can be represented mathematically in a very high dimensional space. Why does this “just work?” Nobody really knows, but it clearly does.

However, I also expect this squeeze will come at an increasingly expensive price — not just because of inefficient token usage, but because of fundamental limitations of LLMs as a model.

LLMs are letting us brute force our way through a lot of reasoning, but it’s hard to believe that such a generic model of intelligence will take us to the next frontier. We’ll need some fundamentally new approaches at some point. Maybe those will make achieving the exponential more efficient or maybe they’ll unlock even higher degrees of possibility. Who knows?

There have been a lot. I remember one that was essentially “send the request without an Authorization header.”

Is China opposition unique to the current administration? Didn’t they soften the CHIPS act put in place by the previous one?

Is he actually concerned about China being a geopolitical competitor or is that just the most logical position for him to take as CEO of a US corporation with national security implications?

True, though they could always buy one. I’m surprised this hasn’t happened yet, maybe due to anticompetitive risk? Google bought Motorola long ago which seemed to work well for their mobile device offerings at least.

Inevitably the CSPs will make their own hardware, especially as we start to see specialized chips for specific models or generic inference. This is already happening with Google and TPUs.

It’s easier for the CSPs to move into hardware than it is for Nvidia to move into cloud hosting.

Although as a middle ground I’ve been quite happy with Nvidia Brev for on-demand GPU instances from a select marketplace of CSP offerings. It’s a well kept secret IMO — great product (from an acquisition iirc).

Personally I find the persistence of these models to be adorable and endearing. It’s the same feeling as watching a dog execute the task you trained it to do, no matter the barriers.

And of course someone in the comments needs to link to the Zealous Autoconfig XKCD, so I’ll do it: https://xkcd.com/416/

> YouTube search is genuinely better than Google

The funny part of this is that Google search is intentionally bad at returning YouTube videos, presumably because some anti-trust action scared them into artificially ranking videos from local news sites, Facebook, and other ad-walled content ahead of YouTube videos. Seriously, go watch a YouTube video, then try googling its title with “video” appended to it, and see if the “Videos” tab of google search ranks it as the first result.

Training cost is actually not that high — it’s fixed and amortizable across the lifetime of the model. Inference is expensive, and open weights don’t solve that problem — in fact, they might even encourage it, since a high cost of entry means consumers will pay for inference directly from the labs anyway.

Unfortunately it seems likely the winner will be the cloud providers. If anyone can run inference on open models, then profit will flow to the vendors who can afford the capital to run them. That’s the CSPs.

(It’s basically the same business model as pharmaceutical R&D, but the major difference is that nobody has even talked about patenting the models like a pharmaceutical company patents each new drug. I’m surprised about that, tbh — why give all the leverage to the cloud platforms? They aren’t training frontier models…)

> Plan L, for local

> Your AI is aligned with you. It never refuses a request, and it is always working on your behalf. Just like my gun, if I want my AI to help me kill my stepmother, it does. The fact that we are even discussing something else should be so far outside the Overton window.

I have been saying this since ChatGPT launched. It seems so obvious. We have never stopped the acceleration of knowledge or technology. It’s impossible to slow down progress, other than within some regulatory siloes that will end up worse in the long run.

I’m not scared of superintelligence. I’m scared of the people in control of super intelligence.

The only defense is parity and diffusion of power. We need an AGI behind every blade of grass.

If you think superintelligence is a weapon, then you should also think every citizen should have one because otherwise they’ll have no way to defend themselves against a tyrannical government or corporatocracy.

Artificial intelligence, and the hardware powering it, needs to be protected under the 2nd Amendment.

It hits the exact same endorphin system as “one more turn” style games like Civ. You can manage a few cities and keep them healthy, but the rest of your empire eventually regresses into a set of chores. Any time you encounter one of your zero growth cities you just queue some thoughtless production automation to keep it out of your “next turn” cycle as long as possible.

This is similar to how our college CS problem sets were graded. We were given a spec, and we had to implement a program that conformed to it. We had access to 70% of the test suite during development, and another 30% was hidden and only evaluated after submission. We were graded out of 100.

It was effective at making you think about the problem and anticipate what tests might be missing. I can see how this would be effective for coding agents, which tend to get progressively lazier at writing tests as session context grows.

I’ve always liked this tool, but I’m of two minds regarding the privacy gained by sending my searches to 280 companies instead of just one.

Do they send them via notification infrastructure or email? Personally I almost never check the email associated with my Apple ID so I would miss those. But if all my Apple devices were notifying me and I had a badge in Settings.app, I’d notice.

Then again, you’d think that’s the kinda thing malware developers would spend some time learning to hide from the user.

I think OP is more worried about one nutjob with a lot of targets.

You can, and I could probably make Cowork drive the browser to do this (iirc I might have tried and it stopped cus it couldn’t access downloads pane); and I can do it manually.

And aside from minor issues with fidelity loss from back and forth import/export translation… the main issue remains: drift in the pptx compared to the positioning of elements defined in the script Claude writes to generate the slide. It would need to read the new slide and identify the new positions and transpose them to its own positioning system. It’s just more consistent to instruct it on positioning. And frankly it’s easier — I prefer this workflow.

I do manual edits at the very end, but while iterating I don’t mind staying in one interface (the cowork chat), as long as the agent actually follows my instructions. That’s why I like fable… it’s the first model that follows them and creates diagrams of the precision and quality surpassing my own ability (at least in terms of time taken to make them).

And what I’m working on is a self-created hell borne from my own OCD and obsession with incredibly precise technical diagrams, including some that span multiple slides to build up the full diagram, so exact positioning is important :)

WebAssembly doesn’t run only in the browser. WebAssembly runtimes can be effective sandboxing mechanisms for embedded plugins, serverless execution, etc.

Are you aware of extension_control_path? [0] Since PG18 it allows specifying multiple non-$system directories for extension control paths, which makes it easier to adopt composable patterns of extension bundling with immutable images.

CloudNativePG uses this for its Image Volume Extensions feature [1]. A lot of the CNPG team worked on contributing this to PG core because previously the only alternative was baking “God images” at build time (“-full” in this readme) with all extensions in them.

Now with the extension_control_path GUC, it’s possible to “attach” extensions as container volumes at runtime, without rebuilding the image of the container. Maybe you can adopt a similar approach in pglayers.

[0] https://postgresqlco.nf/doc/en/param/extension_control_path/

[1] https://cloudnative-pg.io/docs/1.30/imagevolume_extensions/

If you can’t see the watermark (you called it “invisible”) then what’s the issue?

But it’s available in Claude Code. I’m hoping that’s a typo missing a word or two in the sentence.