extasia

politics really is the mind-killer

For what it’s worth, my second year of PhD was relatively miserable compared to my first and third.

ignore the prestige games, knuckle down and do the best work you can do- it’s more impressive if you succeed at a lower rank institution anyways, imo. And if you want that signalling power you can always plan to go for a postdoc.

Wishing you the best of luck, it can be a lonely path.

I wrote my own agent state machine in pretty much pure async Python (no libs). Running successfully in prod with very few issues.

I use the OpenAI messages spec, and have the messages be an append only list, to make it easy to reason about.

Don’t bother compacting histories imo. worse case just summarise and spin up a new agent with the context.

good luck!

That sucks- I’m sorry you had that experience!

I was considering signing up today, based on this I won’t.

I have had a great experience with gemini-cli, which may interest you: it only requires a google account to setup and you get a decent chunk of gemini 2.5 pro usage for free!

the professor vs PhD mode made me chuckle in your UI.

looking forwards to seeing your agent’s critique of my paper!

A reflection on what I unexpectedly gained when I lost my beloved headphones.

Keen to hear if anybody else has had similar experiences of this phenomenon!

Wisdom is taking your own advice.

Words that I’ve found easier to accept the value of than to extoll. Trying is the first step to failing I guess;)

@dang This person is a bot, read other comments of theirs please.

That’s not mathematically accurate though, is it? We haven’t reduced the dimension of the vector by one.

Pray tell, which dimension do we lose when we normalize, say a 2D vector?

Magnitude is not a dimension, it’s information about each value that is lost when you normalize it. To prove this normalize any vector and then try to de-normalize it again.

Interesting, I hadn’t heard of two tower modes before!

Yes, I guess it’s curious that the information lost doesn’t seem very significant (this also matches my experience!)

This is not quite right; you are actually losing information about each of the dimensions and your mental model of reducing the dimensionality by one is misleading.

Consider [1,0] and [x,x] Normalised we get [1,0] and [sqrt(.5),sqrt(.5)] — clearly something has changed because the first vector is now larger in dimension zero than the second, despite starting off as an arbitrary value, x, which could have been smaller than 1. As such we have lost information about x’s magnitude which we cannot recover from just the normalized vector.