MAKE NO MISTAKES! DO NOT HALLUCINATE! FIX IT!

I find it's more reliable if you write "you are a highly experienced software engineer".

I start every prompt with "we have been going in circles". It is the shibboleth for anthropic to A/B test you with their secret new model.

what is sad, is that you an take the article, go to any LLM, ask to read and build an system prompt, from the images + text, and then you can replicate his work

I think what's more sad is someone going out of their way to NOT support the artist.

Art is, among other things, a conversation starter. If someone sees an LLM generated thing hanging in the home or office and strikes up a conversation, it goes something like: "Yeah, i saw it online and I ended up ripping it off"...or the person lies to save face (also sad).

Or, the conversation could be "Yeah, these were purchased directly from the artist...I bought them because....". (a much more interesting conversation)

Both of these evoke an emotional reaction with an interlocutor.

Yes, and it’d look like total crap. People eating NY slices, wearing Dolphins jerseys under palm trees in front of mountains.

Yeah, that would be a real scummy thing to do!

LiteLLM's SOC2 auditor was Delve :))

YC company, on forbes, so I guess maybe a bonus, promotions and AI spinoff...

for me is more interesting that Maxime Chevalier-Boisvert left shopify and is doing other stuff, who will carry on with zjit

Max Bernstein is now leading the team. He's also an excellent compiler engineer.

that is great to hear!

You got your reply already. To add: YJIT is the one that does "basic block versioning" (Which was Maxime's thesis) while ZJIT is a more traditional design.

I am confident in that description but don't actually know what it means in practice (yes I've seen papers and talks, but I kinda need not-compiler-engineer to explain it to me.)

As I understand it BBV still holds promise, but the sheer volume of knowledge of more traditional methods might mean it gets better outcomes (also IIRC ZJIT is still lagging YJIT).

I gave a talk about ZJIT and the motivation for the change at RubyKaigi 2025 if people are curious. It's on YouTube.

Thanks for all your work Maxime!

> IIRC ZJIT is still lagging YJIT

It would be nice to have ZJIT on speed.ruby-lang.org!

She's at yasp since Nov 25. Probably earning much more than at Shopify, and can do AI

great and neat project! I would like to ask, where do you see the value here? a lot of tools on memory, context, etc

Thanks. Yes all spaces are crowded.

IMO the value here will be quasi brain-like operations on data that are fast and efficient.

We overuse LLMs which aren’t too fast and very inefficient.

So the value here is being able to support a shift of some workloads from LLM to smart agentic memory.

From IDEs to AI Agents with Steve Yegge

build tng.sh. nobody wants it. will kill it :)

was a fun project to do some rust

because lies. all the people involved in this, the one a C title, tell us about how great is now.