meken

Love the story and the article. The only nit I have with it:

> “His answers are… understandable, and maybe in some ways more digestible than we would get from an expert,” he said.

This does not reflect his actual responses? The interviewer keys off his most emphatic sounding words to keep the conversation flowing, but his answers are generally inscrutable.

He did a great job given the cards he was dealt though.

I was curious to get a sense for the overall "success rate" at a glance, so I uploaded the author's data as a spreadsheet and color-coded the conversations based on length (short=red, medium=yellow, long=green) with the help of Claude:

https://docs.google.com/spreadsheets/d/1VqMF0xWzJMXWNndeY4P1...

It's particularly nice if you zoom out so you can see all the rows at once.

I hope the author doesn't mind - if you do please tell me and I will take it down!

> but part of me wonders if a lot of their success is attributable to the place just being well run in general

That was my sense reading the article - that the author would be running a successful engineering org using any language really.

I’m not sure how that was your takeaway..?

> We retired the “Nerdy” personality in March after launching GPT‑5.4. In training, we removed the goblin-affine reward signal and filtered training data containing creature-words, making goblins less likely to over-appear or show up in inappropriate contexts. Unfortunately, GPT‑5.5 started training before we found the root cause of the goblins.

The prompt is just a short term hotfix/hack because they couldn’t get the proper fix in in time.

There’s a difference between a relationship with a person and an organization. I think the difference is large enough that the analogy doesn’t really hold.

Just some feedback - I would love to see some screenshots in your GitHub READMEs!*

*I saw the second project has a partial screenshot, but not a full one.

> “What’s beginning to emerge is that the problem was maybe easier than expected, and it was like there was some kind of mental block.”

Even if AI never progresses past this point, it still seems like a huge win for math research to “clear the deck” of these.

I love Kernighan’s Law:

> "Debugging is twice as hard as writing the code in the first place. Therefore, if you write the code as cleverly as possible, you are, by definition, not smart enough to debug it"

Wow that's a really good point. The style of the videos did become quite repetitive.

I had so much fun making videos with my mom when it came out. During the first two weeks, we made over 100 cameo videos together - we were constantly running up against the upload limit. It unleashed tons of genuine creativity, joy, and laughter from us.

After those first two weeks though, we just… didn’t use it again. The novelty wore off and there wasn’t anything really to bring us back. That was the real downfall of Sora.

Fascinating. Thanks for the explanation.

> After all, that's how I tend to treat SQL databases early on.

Ah, that’s a very helpful analogy/parallel that didn’t occur to me. Thank you!

I understood it as the latter.

> Current Common Lisp implementations can usually support both image-oriented and source-oriented development. Image-oriented environments (for example, Squeak Smalltalk) have as their interchange format an image file or memory dump containing all the objects present in the system, which can be later restarted on the same or distinct hardware. By contrast, a source-oriented environment uses individual, human-readable files for recording information for reconstructing the project under development; these files are processed by the environment to convert their contents into material which can be executed.

Am I reading this right that people can (and do??) use images as a complete replacement for source code files?

> what is this actually used for

If you're interested in LeetCode, Racket is one of their accepted languages.

I was using Apple Notes for some “math thinking” the other week. A killer feature for me would be an easy way to input various math Unicode characters (I was just copy and pasting them).

Oh, my mistake. I'm using Spacemacs and it looks like it's just using racket-mode..?

https://www.spacemacs.org/layers/+lang/racket/README.html

For sure. I just meant having some motivating purpose to write Racket.

> The biggest downside of Racket is that you can't build up your environment incrementally the way you can with Common Lisp/Sly. When you change anything in your source you reload REPL state from scratch.

I don’t quite understand… I’m using Racket in emacs/SLIME and I can eval-last-sexp, regions, etc.

I learned recently that Racket is an accepted language on LeetCode, which solved the problem “when am I ever going to write lisp in real life…” for me. It’s provided a great excuse.

I have really been enjoying writing it! Paredit and SLIME are addictive.

Get the best of both worlds by having it be Ctrl when held down + pressed with another key and Esc when you press and release it by itself.

Very cool.

Though the 01 column is a bit unsatisfying because it doesn’t seem to have any connection to its siblings.

I’m in a similar camp to the OP. For me, my joy doesn’t come from building - it comes from understanding. Which incidentally has actually made SWE not a great career path for me because I get bored building features, but that’s another story…

For me, LLMs have been a tremendous boon for me in terms of learning.

> But for me, it was missing something I didn't know how to name until I found it: the chance to be technical and connected.

I genuinely throught this was impossible for a very long time. In my SWE roles I’ve mostly felt disconnected and isolated.

I resigned from my last dev job and started working in donut and coffee shops. I loved it.

I’m pursuing Support Engineer roles now hoping it will provide the human focus that was missing prior.

Can relate a lot. I started off as a SWE but am pursuing a support role for similar reasons.

I was wondering the same thing.

Love it.

Only feedback I have is when I click into an image then hit back, it brings me to the top of the page which is kind of annoying. I wish it held my place.

Great, thanks!

Side note - is this post accessible from the site somewhere? I don’t see where you’d find it (along with the C is Best post [1] shared here recently).

[1] https://sqlite.org/whyc.html

I enjoyed the FBAPP acroymn. There should be a modern day equivalent.