alxndr

But not one of the cranks being behind the chainring… interesting

Thanks, it makes me chuckle too. It also serves as an indicator of how much it's adhering to what I've laid out in the file, sorta like how Van Halen's rider specified a bowl of M&Ms with all the brown ones removed — if the band found brown M&Ms, they'd know to tell the crew to double-check everything else the venue is supposed to provide; if Clod starts using 1st-person pronouns, then I'm a little more skeptical of what it's presenting as absolute truth...

Unfortunately I don't think I have any other funny suggestions. I do ask Clod to always follow a specific format when it's authoring Git commits including the "robot face" emoji as the first character, which brings a little levity to a commit history when it's otherwise being very serious about the contents of the commit message.

https://github.com/alxndr/dotfiles/blob/9356bb9960e63/claude...

Ha, good catch, thank you. I must have been thinking of "inflammable"...

I'm more irked by the sentence-structure patterns it continually uses... here's my list:

https://github.com/alxndr/dotfiles/blob/3d099dbf86da9/claude...

Punctuation lover here, and it's really disappointing that my use of em-dashes is now considered an AI tell... Even though I use them differently from how LLMs do, the distinction is subtle unless you're a grammar nerd.

IIRC I experienced this confusion the most when reading commit messages and documentation authored by Claude in my repos. Now that I've managed to convince it to stop using first-person pronouns, I haven't gotten tripped up by its prose.

I think a second-order effect is that my installation of Claude writes with a less-personal perspective, which I'm also finding a little easier to understand.

...or we call it an overused catch-phrase.

I did something like this in my global `CLAUDE.md`...

https://github.com/alxndr/dotfiles/blob/272475280d84e/claude...

It can be tricky for humans to interpret the meaning when Generative AI uses first-person pronouns (e.g. "I", "me", "my", "myself"), so to avoid the confusion whenever you would use a first-person pronoun, always use the jocular name "Clod" instead of a pronoun like "I" or "me" or "my". (Can have fun with English grammar and turn "myself" into "Clodself"!)

Before printing any of your reasoning or narrative to the human user, replace all instances of "me" and "I" (referring to Claude) — including within contractions like "I'll" and "I'm" — with the name "Clod".

500 error when requesting the individual Job Description pages...

  ⟫ curl -I https://www.getfwd.com/careers/
  HTTP/2 200

  ⟫ curl -I https://www.getfwd.com/careers/job/5128202007/
  HTTP/2 500

Location: Oakland, California

Remote: Yes (or hybrid/on-site in San Francisco or East Bay)

Willing to relocate: no thanks

Technologies: JavaScript, TypeScript, NodeJS, Elixir, Python, Ruby

Resume: https://alxndr.github.io/resume

Email: alxndr@gmail.com

Darkly funny that Pangram 3.3.1 thinks "100% of this text is AI generated"

I’ve had to talk to company lawyers about specific commits. Case was settled afaik

As a member of that group of 1300+, I'm wondering if there's something specific you're looking for which no one has addressed?

"The great enemy of communication, we find, is the illusion of it" —William H. Whyte

I have been trying to convince Claude to use "Claude" instead of first-person pronouns, and only recently have gotten it to say stuff like "Claude'll go ahead and take care of that now", but it's very inconsistent (shocking).

This is the approach I’m taking, along with being much more verbose than my normal style with comments in the code and commit messages (including snippets of the prompts/insights that inspired the change).

[…] the knowledge base isn’t just for research. It’s a context engineering system. You’re building the exact input your LLM needs to do useful work. […] there’s a real difference between prompting “help me write a design doc for a rate limiting service” and prompting an LLM that has access to your project folder with six months of meeting notes, three prior design docs, the Slack thread where the team debated the approach, and your notes on the existing architecture.

Noticed that and was wondering, thanks for the explanation. Does this imply that human-people need to go “vouch” for the flagged comments to bring them back into HM’s good graces?

I think if you treat it like a coworker who you respect, it will speak to you like a coworker who respects you, but will still make some idiotic mistakes...

Yesterday it was showing a hint in the corner to use "/btw" but when I first tried it I got this same error. About ten minutes later (?) I noticed it was still showing the same hint in the corner, so I tried it again and it worked. Seemed to be treated as a one-off question which doesn't alter the course of whatever it was already working on.

FWIW archive.org has a lot of live music as well

Is this synonymous with AI-assisted coding now??

IMHO they’re starting off harder this year!

Isn’t this already (slowly) happening?

That’s not how defamation laws work.

Counterpoint: DARE didn’t scare me away from drugs at all, and in fact taught me how to do the more common ones and what “street names” to ask for at an age where I wasn’t otherwise being exposed to that knowledge.

In the first decade of this millennium, writing JS was a pretty frustrating, and JQuery papered over a lot of the nastiness.

https://alxndr.blog

infrequent posts, tech-focused mostly, sometimes about human languages or nerdy jokes...

Maybe the distribution is relative to the company's Eng org?

How much effort/development have they put in to the spam detection on Gmail?