Gas town is the cackling mad laughter emitting from someone who knows they are being both insane and prescient simultaneously. Today, it is insane. But I fully expect to be hearing about a very serious thing in the near future about which people will say “gas town was an early attempt at this”

This is the best take I've seen in here.

I've been tinkering with it for the past two days. It's a very real system for coordinating work between a plurality of humans and agents. Someone likened it to kubernetes in that it's a complex system that is going to necessitate a lot of invention and opinions, the fact that it *looks* like a meme is immaterial, and might be an effort to avoid people taking it too seriously.

Who knows where it ends up, but we will see more of this and whatever it is will have lessons learned from Gas Town in it.

I've had to read so far down to get a single non-stupid, ignorant, or inflammatory comment. What's wrong with HN, jeepers. Some actual discussion of the thing itself and not just pearl clutching would be appropriate here.

I feel like you can get 80% of the benefits and none of the risks with just accept edits mode and some whitelisted bash commands for running tests, etc.

This is functionally equivalent to auto approving all bash commands, unless you prevent those tests from shelling put to bash.

It seems easier but in my experience building an internal agent it’s not actually easier long term just slow and error prone and you will find yourself trying to solve prompt and context problems for something that should be both reliable and instantaneous

These days I do everything I can to do straightforward automation and only get the agent involved when it’s impossible to move forward without it

Different people like different things

IMO Those screencasts work because they are painstakingly planned toy projects from scratch

Even without AI you cannot do a tight 10 minute video on legacy code unless you have done a lot of work ahead of time to map it out and then what’s the point

I’m not clear what “just loading the project” even means here - if that’s how many tokens are consumed by system prompt plus Claude.md and MCP tools well that has nothing to do with the size of the project

Can’t confirm or deny comparison with JS but I can second that it write decent elixir

The only problem I’ve ever had was on maybe 3 total occasions it’s added a return statement, I assume because of the syntax similarity with ruby

I’ve found Claude (at least until Opus 4) would routinely fail at writing a bash script. For example it would end an if block with }. Or get completely lost with environment variables and subshells.

But those are exactly the same mistakes most humans make when writing bash scripts, which makes them inherently flaky.

Ask it to write code in a language with types, a “logical” syntax where there are no tricky gotchas, with strict types, and a compiler which enforces those rules, and while LLMs struggle to begin with, they eventually produce code which is nearly clean and bug free. Works much better if there is an existing codebase where they can observe and learn from existing patterns.

On the other hand asking them to write JavaScript and Python, sure they fly, but they confidently implement code full of hidden bugs.

The whole “amount of training data” is completely overblown. I’ve seen code do well even with my own made up DSL. If the rules are logical and you explain the rules to it and show it existing patterns, the can mostly do alright. Conversely there is so much bad JavaScript and Python code in their training data that I struggle to get them to produce code in my style in these languages.

Hah I’m only on the cutting edge part time on the side so my experience has been more like - start thinking about the problem and then 2 or 3 days later new tools come out that solve it for me

i think you have an error there about haiku pricing

> For comparison, Sonnet 4.5 is $3/$15 and Haiku 4.5 is $4/$20.

i think haiku should be $1/$5

Fixed now, thanks.

I’ve been surprised at the lack of discussion about sourcegraph’s Amp here which I’m pretty sure you’re referring to - it started a bit rough but these days I find that it’s really good

So, I tried to sign up for Amp. I saw a livestream that mentioned you can sign up for their community Buildcrew on Discord and get $100 of credits. I tried signing up, and got an email that I was accepted and would soon get the credits. The Discord link did not work (it was expired) and the email was a noreply, so I tried emailing Amp support. This was last Friday (8 days ago.) As of today, no updated Discord link, no human response, no credits. If this is their norm, people probably aren't talking about it because they just haven't been able to try it.

Sorry we missed that email! I don’t know what went wrong there, but I just replied and will figure it out. This is definitely not the norm (and Build Crew is a small fraction of our users).

(I can't edit my old post, but it turned out to be a Discord issue, not an issue with the amp link. Oops!)