vok

The examples:

https://www.dangermouse.net/esoteric/piet/samples.html

The last one is astonishing: "Okay, this one is really wild. Piet J. (yes, that's his real name) was browsing art in a small gallery and saw a work which reminded him of a Piet program. He spoke to the artist, who claimed to know nothing about the language. Piet took a photo of the artwork (left), converted it into a clean image file using close colours from the Piet palette (right), and tried running it.

It ran!..."

Corrected link: https://www.youtube.com/watch?v=nO9aot9RgQc

Well, o3-mini-high just successfully found the root cause of a seg fault that o1 missed: mistakenly using _mm512_store_si512 for an unaligned store that should have been _mm512_storeu_si512.

I think that "Good Forth programmers arrange things so that they flow on the stack" has analogs in other languages. For example, arranging things in J so that short tacit expressions naturally provide the functions you need.

There's interesting discussion with the authors here: https://www.alphaxiv.org/abs/2408.10234

This "Computer use" demo:

https://www.youtube.com/watch?v=jqx18KgIzAE

shows Sonnet 3.5 using the Google web UI in an automated fashion. Do Google's terms really permit this? Will Google permit this when it is happening at scale?

With the right font (e.g. http://viznut.fi/unscii/) and line spacing, braille characters work fine with an even distribution of pixels and no gaps.

These strategies seem immediately practical. If you want to go beyond zero-shot for LLM coding, you may not need a complicated agent architecture - just start with escalation, retry, and warming.

APPS has 3 subsets by difficulty level: introductory, interview, and competition. It isn't clear which subset Claude 3 was benchmarked on. Even if it is just "introductory" it is still pretty good, but it would be good to know.

Beautiful. Try typing:

2 3 + 4 5

in the upper-left, under "kyte/k".

There has been a programming competition for the Manchester Baby, producing some quite nice demos: http://curation.cs.manchester.ac.uk/digital60/www.digital60....

Related: https://news.ycombinator.com/item?id=36486490

Vera Molnar is still active at age 98+.

https://en.wikipedia.org/wiki/Vera_Moln%C3%A1r

https://dam.org/museum/artists_ui/artists/molnar-vera/curren...

https://www.artnews.com/art-news/reviews/pioneering-computer...

Push has remained active for genetic programming, and there's recent work comparing program synthesis with language models vs. PushGP: https://arxiv.org/pdf/2304.10423.pdf

This looks promising. For me, it successfully scraped a webpage that Bing Chat would not. A couple comments: (a) preserve newlines in the output (I'm trying to get a CSV output), (b) the output length appears to be truncated - too short for my application.

There's an active F-91W watch hacking project (with somewhat different goals) here:

https://www.crowdsupply.com/oddly-specific-objects/sensor-wa...

The emergence of host-parasite coevolution parallels what happened among the programs that inhabited the original Tierra artificial life experiment: http://tomray.me/pubs/alife2/Ray1991AnApproachToTheSynthesis...

Bitshift Variations in C Minor. Really gets going after a while: https://soundcloud.com/robertskmiles/bitshift-variations-in-...

There are at least two excellent 32-byte x86 machine language Game of Life demos:

https://www.pouet.net/prod.php?which=85485

https://www.pouet.net/prod.php?which=88201

The article expresses disappointment that a <40 character APL program mostly just demonstrates "why Game of Life is perfectly suited to solving in APL". But it seems harder to argue Game of Life is "perfectly suited" to solving with low-level x86 machine language.

Does anyone know of other places where the word "flow" is used like this?:

> Good Forth programmers arrange things so that they flow on the stack.

I think this concept of "flow" applies elsewhere, for example when creating tacit programs in J. But I haven't seen "flow" used like this anywhere except this article.

"SAT solvers became a billion-dollar industry" Does anyone have a reference for this?

The article notes benchmarks which can use AVX512, but none of the CPUs tested support AVX512.

I also like that I can incorporate plots into my plain-text notes files.

LuaJIT uses DynASM, which is also stuck (e.g. no AVX-512). It would be great to see DynASM development continue.

"The human evaluation results indicate that the response generated from DialoGPT is comparable to human response quality under a single-turn conversation Turing test."

Paper here: https://arxiv.org/abs/1911.00536

A favorite Alan Perlis quote that's not included here: "If Shakespeare were alive today, he’d be a programmer, and he’d be writing one-liners in APL."

https://www.jsoftware.com/papers/APLQA.htm

Actually, UNSCII is also what I’m looking for in Termius (for drawille).

Parity Computing, Inc. | Senior Data Scientist | San Diego, CA | Onsite | https://www.paritycomputing.com/careers/

Parity Computing has been providing intelligent automation systems to science, technology and medicine (STM) publishers, academic/industry researchers, and healthcare organizations for almost 20 years. Parity achieves industry leading accuracy for applications in large-scale entity disambiguation and profiling, real-time clinical decision support, and predictive modeling for precision medicine.

We are looking for a Data Scientist with 6-14 years of experience, especially in NLP and Text Analytics, to be part of a small team that identifies, develops and maintains models for applications in science, technology, and medicine.

Send resumes to jobs@paritycomputing.com

"If Shakespeare were alive today, he’d be a programmer, and he’d be writing one-liners in APL." — Alan Perlis