How are these differebt in your mind? The history is the history.

Or do you mean - each agent has a chance to think after every turn?

Well they can be watching all the action and thinking the whole time as the action leads up them, just like we do in poker. To me it's different, subtly perhaps.

For my implementation, I'm passing in the current hand's action history (e.g. Player 1 raises to $X preflop, Player 2 calls, Player 3 calls. Flop is A B C, Player 2 checks, etc) whenever the action is on the player.

Your idea of having it being passed in real time and having the LLM create a chain of thoughts even if action is not on them is interesting. I'd be curious to see if it would result in improved play.

Because humans are interesting creatures that do unexpected things.

The cut in the demo (12:18) is very odd and makes me wonder if it’s real.

Sounds like an incredible period. Do you miss it at all?

I’ve had phases of my life where I was lucky to have periods of absolute and undisturbed focus (grad school, summers during college, etc.). It’s easy to forget how valuable that type of focus time is until it goes away!

Oh sure, lots of things to miss about that time... startup vibes, underdog causes during the worst of the Bush years, and work that ranged from the Mac stuff to Linux/BSD backend admin, PHP dev, introduction of the tech team to SVN/version control, even some music composition for a video. And close work with a bunch of folks on the team who now have their own Wikipedia pages, as well as high-profile clients. My boss left eventually in mid 2005 to go work for (then Senator) Obama and personally interviewed him for / produced his podcast, posted to his Flickr, and that sort of thing.

The commuting... not so much. Moved into DC proper after that year, which itself was a great adventure. Leaving the house at 5:30-6:00am and returning at 8:30-9:00pm was no way to live.

I have no clue how you’re running your agents or what you’re building, but giving the raw password string to a the model seems dubious?

Otherwise, why not just keep the password in an .env file, and state “grab the password from the .env file” in your Postgres skill?

I am thinking of distributing skills that I build to my clients. As my clients are mostly non-technical users I need this process of distribution to be as easy as possible. Even adding a .env file would probably be too much for most of them. With skills I can now finally distribute my logic easily, just send the raw files and tell them to put it into a folder - done. But there is no easy way for them to "setup" the credentials in those skills yet. The best UX in my opinion would be for Codex (or Claude, doesn't matter) to ask for those setup-parameters once when first using the skill and process the inputs in a secure manner, i.e. some internal secret storage

That’s exactly what I do.

Wow that’s far more impressive than I expected. I want a laptop with this for programming…

It seems like he’s saying that he could create an album and add a rule saying “add all pictures of John and Jan”

I can still conjure the theme song in my head!

N.B.,

> "Subjects were historically trained mostly in the underscore identifier style and were all programmers."

I have AGENTS.md symlinked to CLAUDE.md and it works fine in my repos.

But I can’t speak to it working across OS.

Confirm on a new clone that if you modify a file that the other is updated.

I thought git by default treats symlinks simply as file copies when cloning new.

Ie git may not be aware of the symlink.

git very much supports symlinks. Although depending on the system config it might not create actual symlinks on Windows.