Author | Lightnews

Daniel Mewes @dmewes.com · 2d

I have to admit the mechanism behind cable impedance and impedance matching never really clicked for me, despite being a licensed radio amateur for 20 years.
...until I watched this video by AlphaPhoenix - it's such an amazing visualization of what's going on in a cable! youtu.be/RkAF3X6cJa4?...

What does "impedance matching" actually look like? (electricity waves)

YouTube video by BetaPhoenix

youtu.be

1 3

Daniel Mewes @dmewes.com · 3d

Claude Haiku 4.5 outperforms Sonnet 4 in some coding benchmarks (such as SWE-bench Verified). This is exciting, since it's 1/3 the price.

However, in my actual use, I've found it to be a bit underwhelming compared to Sonnet 4 (not to mention Sonnet 4.5).

What has been your experience with Haiku?

Daniel Mewes @dmewes.com · 3d

It is off by default. You have to enable it from what I've read.

2

Daniel Mewes @dmewes.com · 4d

Duh, if she enabled the browser memories feature, of course it will do that. It's not like they're hiding it, it's one of the advertised features and afaik can be turned off.

1 2

Daniel Mewes @dmewes.com · 4d

This is so true.
I think almost nobody is talking about symbolic GOFAI these days, so I'm not concerned about that.
But all of ML being re-branded to AI lately, while AI has simultaneously been made synonymous with generative AI in many places, has led to so much confusion.

Ethan Mollick @emollick.bsky.social · 4d

The fallout from the fact that data science/classical machine learning & generative AI are both called "AI" has been remarkably broad & persistent

Policy addresses the wrong harms, companies have been confused about who should lead efforts, hiring is misguided, academic discussion is often muddled.

Daniel Mewes @dmewes.com · 16d

If you can read this, that means I tried and it worked.

1

Daniel Mewes @dmewes.com · 18d

The fact that I can point a coding agent to an arbitrary open-source software and have it implement some missing feature in a few minutes is wild. The one-shot implementation quality might not be sufficient for merging it upstream, but it's quite often enough for my one-off use.

1

Daniel Mewes @dmewes.com · 18d

The age of single-serving, disposable (simple) software is here. I now frequently have LLMs write software for me that I use exactly once.
Often to convert some data or create visualizations, but also one-off new features to add to some open-source application that I only want to use once.

1

Reposted by Daniel Mewes

thebes @vgel.me · 21d

new blog post! why do LLMs freak out over the seahorse emoji? i put llama-3.3-70b through its paces with the logit lens to find out, and explain what the logit lens (everyone's favorite underrated interpretability tool) is in the process.

link in reply!

8 47 210

Daniel Mewes @dmewes.com · 21d

We just released a beta of such a product last week 🤞https://imbue.com/sculptor-announce/
Runs Claude Code in Docker containers with some special collaboration sauce.

2

Daniel Mewes @dmewes.com · 22d

We might open source Sculptor in the future, but aren't quite ready for it yet. (between us though, it's written in Python and not obfuscated, so you can also just look at its code)

2

Daniel Mewes @dmewes.com · 24d

Ah, interesting. I haven't thought of that.

1 2

Daniel Mewes @dmewes.com · 24d

Unfortunately I don't think they're made uncomfortable by the rituals, but by Leo criticizing Trump's deportation policy. They just have to latch on to random things now to present the pope in a bad light.

1 3

Daniel Mewes @dmewes.com · 25d

Interesting that Sonnet 4.5 is a lot more expensive than Sonnet 4 in this eval. I assume it generates more tokens for the same problem?

2

Daniel Mewes @dmewes.com · 26d

Today we're releasing Sculpture, an AI coding tool that combines async agents with the ability to collaborate with agents locally.

It also comes with built-in verifiers to automatically check the quality of AI written code. More to come! imbue.com/sculptor-ann...

A picture of @kanjun.bsky.social making an excited gesture, with the label "developers, developers, developers" written over it.

1

Daniel Mewes @dmewes.com · 27d

Yeah I feel like LLMs are such a cool tool for diving into unfamiliar languages. Both for answering questions, but also for generating example code at various levels of complexity. I've recently been trying to learn some Lisp again, including by vibe coding some. bsky.app/profile/dmew...

Daniel Mewes @dmewes.com · Sep 22

I used AI vibe coding tools to port Anthropic's API client to Common Lisp: github.com/danielmewes/...
It was a very quick and fun mini project that taught me a thing or two about Lisp. Use it at your own risk.

GitHub - danielmewes/anthropic-sdk-cl-port: An AI-written port of the Anthropic client SDK to Common Lisp.

An AI-written port of the Anthropic client SDK to Common Lisp. - danielmewes/anthropic-sdk-cl-port

github.com

1 1

Daniel Mewes @dmewes.com · 27d

Ah yeah. I have never written Cobol myself, but happened to have listened to this podcast just a week ago. youtu.be/Rdm3fgxbLOE?... So I recognized some of the structures when I looked at your webserver.

Episode 60 - COBOL Never Dies

YouTube video by Advent Of Computing

youtu.be

1 1

Daniel Mewes @dmewes.com · 27d

Oh, I see you used Claude to write it... Either way, maybe you still heve a sense of the above from reviewing its code?

1 1

Daniel Mewes @dmewes.com · 27d

Very cool! Was there anything in the structure of Cobol that you found made it challenging, or just a lack of suitable libraries? (I'd guess it's not a great language for parsing, but then neither is C, is it?)

1 1

Daniel Mewes @dmewes.com · 27d

When I first read your summary, I thought you had changed the log prop sampling so it could never sample the stop token for 10 hours. I wonder if that approach would give similar behavior or something different. In that case, there would be no countdown time or user messages at all.

1 3

Daniel Mewes @dmewes.com · 27d

Cool experiment! I agree that it might reveal something about a model's ability (tendency?) to seek novelty when it can't make progress with one approach.

1 1

Daniel Mewes @dmewes.com · 28d

Ah, that makes sense

1

Daniel Mewes @dmewes.com · 28d

Maybe just unsubscribe from Listifications?

2

Daniel Mewes @dmewes.com · Sep 25

You could say the exact same about source code though.

1 4

Daniel Mewes @dmewes.com · Sep 22

I used AI vibe coding tools to port Anthropic's API client to Common Lisp: github.com/danielmewes/...
It was a very quick and fun mini project that taught me a thing or two about Lisp. Use it at your own risk.

GitHub - danielmewes/anthropic-sdk-cl-port: An AI-written port of the Anthropic client SDK to Common Lisp.

An AI-written port of the Anthropic client SDK to Common Lisp. - danielmewes/anthropic-sdk-cl-port

github.com

1