teach

It could! An MCP would actually be great but Slack would prefer to sell us their own AI integration product so (1) they make it difficult and more importantly (2) it's against their terms of service

We pay them a LOT of money every year and they would absolutely notice the indexing at the level we'd need to do to make this work ourselves, so the answer is "because Slack is preventing us".

Slack's approach is NOT good enough, because the version of the Agent that lives in Slack cannot see the context of the Agent that lives inside Cursor on my developer laptop. They might be clones with identical brains, but they can't talk to each other or compare notes.

Just my two-cents as a very much boots-on-the-ground infrastructure engineer. We use LLMs heavily on my team -- to write code and review PRs. Our harnesses and guardrails are very very good so we get extremely high-quality output out of most models.

But getting the humans and agents to talk together is really fragmented right now. It's annoying that the agent with the context in my locally-installed Cursor can't really participate in a Slack conversation about a PR that 'it' principally authored (and which I've signed off on).

This is a real communication problem that we face every day, and eventually someone will solve it well and I will ask our leadership to give them a lot of money.

This is a good clarification but I think the core issue is that Spotify (and Apple Music and Amazon Music and probably others) have chosen a business model in which consumers can listen to basically everything and yet artists do not get paid. The rightsholders suffer too yet they are complicit.

This business model ALWAYS outcompetes any other, and can't be "fixed" imo, because no one will pay per-stream or pay $50 a month.

I think this is a false dichotomy. There's no reason "all music is paid only" is the only option besides the all-you-can-stream for one monthly fee popularized by Spotify.

For example, the other day I discovered a local artist on Instagram. I went to her Bandcamp page and was able to listen to some tracks for free with zero friction. I ended up purchasing the deluxe vinyl, and it was one of my favorite albums that came out last year.

I've done similar with the radio. I went from hearing a track on the radio to purchasing the album on Bandcamp in like ten minutes.

Spotify and the like CAN help with discovery, sure, but that doesn't have anything to do with their business model.

This article is from 2011. Noisetrade was a very cool site for several years, but I don't think it's still operational.

I agree with you that you are never "forced" to pirate; you can simply not listen to the missing album.

But many many many many excellent albums are not available for sale anywhere at any price. They essentially do not exist, except in the hands of a few collectors.

The bands themselves, the creators of said music, want their music to be heard.

The fact that they aren't available for sale or streaming is often because a rich bureaucrat can't be bothered, not for any legal reason.

Although I generally agree with you, it's really hard to make the case that it's not all-or-nothing for him when he literally says

we either live in a world with freedom or we don’t

You're entitled to call things as you wish, of course, but your definition of "vibe-coding" differs quite a bit from mine.

Cars have had remote start with the ability to cool down (or warm up) the car before getting into them for decades before the Tesla was ever invented.

(2012)

I'm quite certain I formally verified that two processes were both able to get into the critical section WITH THE ALGORITHM I WAS VERIFYING, but this was 35 years ago, so details are fuzzy.

Remember that this is long before Wikipedia and even before Google, so I have no idea where I'd have gotten the alleged Baker's algorithm from.

Also you're right that this isn't much of an issue in practice, but that's not what formal verification is about, now is it? :)

I've been following Bob Cringely for nearly 30 years and he's always written like this.

This is almost certainly not AI-generated text, and he's not saying Claude is wrong.

He's saying something different that is probably true (that LLMs can't produce facts, no matter how much they are trained). It is also not that interesting (LLMs hallucinating sometimes doesn't mean they're not useful).

I'll grant you the self-aggrandizement, but he's come by it honestly.

tothineown.self/be/true

So much this.

I actually did take a formal verification course in college. Our final project was to use the techniques we'd been learning to verify some classic critical-section locking algorithm. I chose to verify an implementation of Lamport's bakery algorithm[0] in C (this was the 90s -- a lot of code was still being written in C).

The problem is that Lamport's algorithm makes an assumption that the "ticket number" is unbounded and any finite implementation in C will almost certainly use a value which is limited to 32 bits or so.

So I was able to formally verify that the algorithm fails to protect the critical section if enough processes are kept waiting to overflow the counter. :)

This probably just means that Lamport's algorithm isn't a great choice for such environments, but I'm still bummed that the professor gave me a B.

[0] https://en.wikipedia.org/wiki/Lamport%27s_bakery_algorithm

It's interesting that your experience/workflow is so much different than mine. This (claims to) solve a real problem that I deal with every day.

My company is remote-only, and my coworkers mostly don't live anywhere near me. We see each other a couple of times a day on video chat, but communicate mostly during the day via Slack.

We're also, uh, pretty far along the curve in adopting LLM agents to write good code for us. With a good model and the extremely good guardrails our of specific coding harness, LLMs are writing the majority of our code these days.

So on a typical day I'll grab a ticket off the top of the stack, point my LLM at it, and start working with it to solve the problem. We'll make architectural decisions, etc, create a plan and execute the plan. The feature I shipped most recently cost $19 in tokens and the LLM was churning without my input for like half an hour at one point in the thick of it.

MAYBE if there's a question I'm not sure which way is best I'll post a question in the team chat for my teammates to weigh in on. But a lot of my tickets are done completely autonomously.

Then I'll open a PR, and post a link to the PR in Slack, requesting their review and my teammates will see the implementation for the first time. They sometimes have questions! Often, they'll post these questions in the Slack thread rather than as PR comments, because we're having a fast real-time conversation and GitHub comments aren't a great fit for that.

These questions have answers in the chat log with the LLM that lives on my laptop, but I can't trivially show it to them.

So I end up playing telephone with the LLM -- copying my teammate's questions from Slack to the LLM chat, pasting the answers back, etc

The idea that my coworkers and the LLM and I can all be more easily a part of the same conversation appeals to me greatly

None of this means the Zed team is on the right track. Nor that my team might work better in a different way! But we're too "successful" with this approach for there to be much institutional pressure to change our ways at the moment.

Hope that helps.

For what it's worth, I really enjoyed this read and almost came here to comment "this is the most enjoyable llm-assisted article I've read in a while"

The tells were unmistakable but it still had a human touch, so I for one am glad you published anyway.

In my case it's exactly that. I have a Linux gaming workstation, a work-issued (and managed) MacOS laptop and a Google-branded (Pixel) Android phone.

Bitwarden just works in all those places and the tech was, by all accounts, rock solid. AND I can pay for it instead of trying to leech off some privacy-ambiguous free tier.

Anyone who makes fun of you for feeling things probably isn't anyone you want to listen to, anyway.

Thanks for being human and making ergonomic software for humans.

Yeah this worked for me last night, but I too get a blank screen today.

In the developer console I see a CORS error for an attempt to load an SVG component from a CDN; I wonder if the dev pushed out a bad update

I definitely trust my local LLM where I know the prompt that was used. Even if the code generated ends up being near-identical, it'll be way faster to review a PR from someone or something I trust than from some rando on the Internet

This isn't especially related to the article, but when I was at university my first assembler class taught the Motorola 680x0 assembly. I didn't own a computer (most people didn't) but my dorm had a single Mac that you could sign up to use so I did some assignments on that.

Problem is, I was just learning and the mac was running System 7. Which, like MS-DOS, lacked memory protection.

So, one backwards test at the end of your loop and you could -- quite easily -- just overwrite system memory with whatever bytes you like.

I must have hard-locked that computer half a dozen times. Power cycle. Wait for it to slowly reboot off the external 20MB SCSI HDD.

Eventually I took to just printing out the code and tracing through it instead of bothering to run it. Once I could get through the code without any obvious mistakes I'd hazard a "real" execution.

To this day, automatic memory management still feels a little luxurious.

Maybe should add "with Cloudflare Workers" to the headline

Because hosting a blog inside a subdirectory is like the most trivial webserver thing ever

One could argue that, given how singularly awful it is, GitHub's historical uptime might qualify as "historic".

Dumb question, but if this is "open source" is there source code somewhere? Or does that term mean something different in the world of models that must be trained to be useful?

This is amazing but even as a runner who loves to make my own "processed" food this really reads like a submarine article for the dairy industry.

"I used to be vegan, but you know I just can't liveeeeeeee without that real butter!!!!!!!"

If you never play the original sample, you never have to worry about royalties.

:rollsafe-think-about-it:

I've seen this story making the rounds, but this isn't news, is it?

All self-driving companies maintain teams that make a decision when the cars get confused or stuck, and they report the number of such handoffs to NHTSA.

Is it just that there are teams in the Philippines specifically?

That makes sense to me. I really enjoyed the personal anecdotes and I thought they made the article a lot stronger for me, but a dry gas mask review would have also been an excellent, albeit different, article.

A permanent ban seems strong, but it sure does seem like folks are using flagging as a super downvote in this case