FAWK: LLMs can write a language interpreter

(martin.janiczek.cz)

Show context

vidarh ◴[21 Nov 25 11:48 UTC] No.46003610[source]▶

It's a fun post, and I love language experiments with LLMs (I'm close to hitting the weekly limit of my Claude Max subscription because I have a near-constantly running session working on my Ruby compiler; Claude can fix -- albeit with messy code sometimes -- issues that requires complex tracing of backtraces with gdb, and fix complex parser interactions almost entirely unaided as long as it has a test suite to run).

But here's the Ruby version of one of the scripts:

    BEGIN {
      result = [1, 2, 3, 4, 5]
        .filter {|x| x % 2 == 0 }
        .map {|x| x * x}
        .reduce {|acc,x| acc + x }
     puts "Result: #{result}"
    }

The point being that running a script with the "-n" switch un runs BEGIN/END blocks and puts an implicit "while gets ... end" around the rest. Adding "-a" auto-splits the line like awk. Adding "-p" also prints $_ at the end of each iteration.

So here's a more typical Awk-like experience:

    ruby -pe '$_.upcase!' somefile.txt ($_ has the whole line)

Or:

    ruby -F, -ane '$F[1]' # Extracts the second field field -F sets the default character to split on, and -a adds an implicit $F = $_.split.

That is not to detract from what he's doing because it's fun. But if your goal is just to use a better Awk, then Ruby is usually better Awk, and so, for that matter, is Perl, and for most things where an Awk script doesn't fit on the command line the only reason to really use Awk is that it is more likely to be available.

replies(2): >>46004089 #>>46004823 #

1. UltraSane ◴[21 Nov 25 13:01 UTC] No.46004089[source]▶

>>46003610 #

So I have had to work very hard to use $80 worth of my $250 free Claude code credits. What am I doing wrong?

replies(3): >>46004821 #>>46005317 #>>46005722 #

2. sceptic123 ◴[21 Nov 25 14:14 UTC] No.46004821[source]▶

>>46004089 (TP) #

> free

how do you get free credits?

replies(2): >>46005266 #>>46005706 #

3. throwup238 ◴[21 Nov 25 15:08 UTC] No.46005266[source]▶

>>46004821 #

They were given out for the Claude Code on Web launch. Mine expired November 18 (but I managed to use them all before then).

replies(1): >>46005629 #

4. throwup238 ◴[21 Nov 25 15:13 UTC] No.46005317[source]▶

>>46004089 (TP) #

I used all of my credits working on a PySide QT desktop app last weekend. What worked:

I first had Claude write an E2E testing framework that functioned a lot like Cypress, with tests using element selectors like Jquery and high level actions like 'click' with screenshots at every step.

Then I had Claude write an MCP server that could run the GUI in the background (headless in Claude's VM) and take screenshots, execute actions, etc. This gave Claude the ability to test the app in real time with visual feedback.

Once that was done, I was able to run half a dozen or more agents at the same time running in parallel working on different features. It was relatively easy to blow through credits at that point, especially since I think VM times counts so whenever I spent 4-5 min running the full e2e test suite that cost money. At the end of an agents run, I'd ask them to pull master and merge conflicts, then I'd watch the e2e tests run locally before doing manual acceptance testing.

5. UltraSane ◴[21 Nov 25 15:52 UTC] No.46005629{3}[source]▶

>>46005266 #

Mine were set to expire then but got extended to the 23.

6. UltraSane ◴[21 Nov 25 16:01 UTC] No.46005706[source]▶

>>46004821 #

Pro users got $250 and max users got $1000

7. vidarh ◴[21 Nov 25 16:02 UTC] No.46005722[source]▶

>>46004089 (TP) #

Run it with --dangerously-skip-permissions, give it a large test suite, and keep telling it "continue fixing spec failures" and you'll eat through them very quickly.

Or it will format your drives, and set fire to your cat; might be worth doing it in a VM.

Though a couple of days ago, I gave Claude Code root access to a Raspberry Pi and told it to set up Home Assistant and a voice agent... It likes to tweak settings and reboot it.

EDIT: It just spoke to me, by ssh'ing into the Pi and running Espeak (I'd asked it to figure it out; it decided the HA API was too difficult, and decided on its own to pivot to that approach...)

↑