HN user

d-lisp

305 karma
Posts1
Comments250
View on HN

in Gemini I even have a preamble that basically says "don't be a sycophant". It still doesn't always work.

Using this kind of strategy eventually leads to the LLM recurrently advertising what it just produced as «straight to the point, no fluff, no bullshit». («Here is the blunt truth»).

Of course no matter how the LLM advertise its production, it is too often non devoid of sycophancy.

Sometimes I draw UML-like diagrams when I join a project (and when the project is big enough in such a way my mind melts if I try to keep track of everything), I wonder if there are equivalent representations of such things.

Linear text is perfect to me for documentation, teaching/learning etc...

But also, systems seems to be better digested under the shape of spatial representations (I met a lot of CS persons that fantasized over the possibility of displaying all the files of your codebase in a VR-like environment augmented with visual cues (UML) and I must admit that I would find this unnecessary but comfortable -- and I can imagine applications of this in other domains; imagine a teacher arranging the whole of Kant philosophy as a spatial-visual system referencing positions, comments, etc..). Eyes are cool because you can focus on something while knowing that some available information is there around the zone you are focusing; in a sense, so is the hand, locally, but I imagine (I dont know) it would require some super-human level of braille reading to be able to jump back and forth reading on different fingers, so that's again a probably stupid question to ask to the blind crowd of hn : are you able to do this?

How would they put guards against poisoned data ? How would they identify poisoned data if there are a lot/obfuscated ?

Businesses do business; but there are endavours to make tests be reliability indicators and in some (critical) domains you do write them to perform such a thing. write tests the way test-theory intended; as formal verification.

There is software for which writing code is a design act, and there is software for which you write specs before anything. I don't know if a) they are the same, b) they are different, c) one is better than the other.

To me the formula mystifies things. It should be made clear that it is a simple application of pythagore's theorem,

(i didn't see the video except the beginning to check what was the "mysterious formula".)

As I am involved in more low level stuff, I prefer to read the source than the man pages, and I am very happy with people overcommenting their code as a user of e.g. a lib. On the other hand, it is unbearable to me to see comments on a codebase I am working on. Fortunately, emacs show/hide comments exists, so I find myself overcommenting things.

dangling pointers to raw memory that [are not] cleaned

How do you feel about building special constructs to automatically handle these ?

I think I fear system instability and its consequent (probable) problems.

Sleep does a lot of things, a lot I don't necessarily understand, all the OS layers are stressed at once, and with them a whole lot of other things, bith software and hardware related. Are all the drivers of your system trustworthy, are all the running applications trustworthy ? Are we sure no data loss will occur ? Will you lose audio, wifi, display or excessive battery because of a race condition or an error of some sort in an element of the whole involved stack ?

Most of the time everything is fine, or is it ? Maybe your computer will hit kernel panic after two hours or so, and you will have hard time figuring the real cause and origin.

tldr; I think it scares me because it increase the probability for the system to surprise crash at a very crucial time (while compiling something, in between two saves of a text buffer, during a write to disk...)

Seriously for my part, LLMs incarns exactly the only type of person that can break my nerves. Far too often I spot an hallucination, some bullshit rambling, sycophancy, or ----hughhhhh----- rethorical elements of language that makes me go mad :(.

examples for ---hughhhhh--- inducing stuff :

"I'll be blunt !"

"Here's the ground truth, no bullshit"

"Bottom line : <UPPER CASE EXPRESSION>"

"No fluff, technical, precise, no bullshit, devoid of unnecessary rethorical shapes, <etc..."

"Blunt answer: <bold text>"

"<title> : the hard truth"

I am becoming snob ?

Pragmatically, you can design things to be highly readable for yourself and people that are "like you".

Alignment between the shape and the content is done in a circular fashion : what you see educates you to fabulate about design, once you fabulated enough you begin to say things are bad or well designed.

I often express myself online by writing a bit what goes through my mind, in a joyful and not very attentive manner, and I find it amusing to be barely understandable sometimes (I like the fact you had to use an LLM, lol) because, well, I feel it may bring a certain color to the otherwise often too uniform and immediate/instantaneous world of internet -- So, what I said previously is also mostly what occurs when you let your mind wander;

now, if I rejoin my own person and body, I can agree with you that my culture of good design is about the testimony of the removal of intention, in such a way that I feel content is highly readable, (fictionnaly) devoid of style, and somewhat raw or pure.

But again, at the "philosophical stage" all of this is pure fiction, and with a certain mindset, I am pretty sure I could shift my habits to adapt to what I feel as weird design, ugly, barely readable etc... It would be totally useless and absurd, but I could (given I have no specific perception-related medical conditions) !

We saw the web become a repetition of the same design, and while it IS good design in our "minimalism" addicted brains, I am pretty sure stumbling upon weiiiiird websites makes us great good sometimes, so much that maybe we also start to think about the absurdity of our standards : we arrived to the point in the "lie" where we identify this specific style as "the shape" of our perception, and yes : it become invisible to us, and is good design, but also it is a bit depressing.

My window manager and my emacs/vim/terminal configuration aren't what I call good design. They are highly readable but stratosphere-reaching levels of kitsch (yes ! I WANT to cosplay and feel as if I was writing code for aliens or to fight the matrix at work, and yes that's a bit cringe but at least I am honest with myself).

I don't wish the world and internet to be "more like that" and am ok with the actual state of design. Nevertheless I find that's a bit arbitrary and somewhat boring.

You can only be blind for things you cannot notice.

What you cannot notice is what shapes your "noticement" ability.

The best design is the shape of your perception.

The best design is already implemented in your reception of reality.

The quest for "good design" is a game.

On the other hand, your aesthetical culture and the shape of your perception create a system in which elements are more or less "understandable", "readable", "accessible".

The game of design does not have stable rules and is inconsistent among world populations.

"No design" is impossible, the nature of reality is such that entities are embodied. To be embodied is to be rendered in the game of design.

Ideas are not embodied OR their apparent embodiment in the game of design (electrical information ?) does not contain their content for the observer.

"No design" is perceptually inintelligible.

LLM Year in Review 7 months ago

Indeed, I was probably grumpy at the time I wrote the comment. I do find some truth in it still.

You're right ! The strawman theory is based.

But I think there's more to it, I find dislikable the structure of these sentences (which I find a bit sensationnalist for nothing, I don't know, maybe I am still grumpy).