Hacker Newsnew | past | comments | ask | show | jobs | submit | hnarayanan's commentslogin

It would help (me) if this documentation had at least one screenshot.

Tiny mono fonts.


How is it possible to make graphs that look this hideous?


dunno, they still have a certain charm to them, they remind me of crappy textbook graphs


Thank you. I turn grumpy when my colleagues keep calling it N+1. What even.


This is a more general question, which is "Why don't people take accountability for their actions?"

Because it's hard work and it's easier to let someone else bear the costs.


The question is actually how do people get away with avoiding accountability for their actions?


That's a more noble aspect of framing the question, and I guess I could even see why someone may try to not kamikaze themselves out of a financially very juicy system even if it was their own actions causing the trouble. However, they all operate in some form of management mesh, so clearly, one level up or across the line must notice or know who caused the chaos?

Maybe it is the nature of how failure is expressed at that level, to know a team of 30 has been let go and is not available as your extended arm to execute anymore. So, where it manifests as a job loss at a level lower, it is merely a limitation of power for them.


If everyone at a given level is playing the game, only those without leverage on everyone else are easy targets


Maybe blaming someone else for a failure is more likely to backfire on you.


> Why don't people take accountability for their actions?

This is not my experience. People who are in positions of power, e.g. managers, are the kind of people who are incapable of admitting fault. They can't lose face so the shit is rolled downhill. It's narcissism.


Clearly that trait is selected for.


Often times, narcissism comes with a strong will and assertiveness. It is hard to be full of yourself if you cannot also project yourself. People respect that kind of assertiveness. "Clearly, if this guy is so sure of themself, they must be good..." is the mindset many fall into. Of course, this line of thinking usually does not hold up forever and the facade can eventually break down.


This drives me insane! To combat it, I maintain a list of banned words and phrases. Claude mostly follows this (but sometimes ignores it).

blast radius, land, landed, lands, spine, earned its keep, grammar, spike, cutover, bake, seams, honest, honestly, honesty, long pole, long poles, register, grain, dissolve, floor, ladder, dear, seal, sealed, in anger, resent, amazing, incredible, perfect, sprint, epic, story points, stand-up, retro, grooming, robust, comprehensive, rigorous, surgical, elegant, systematic, dive, deep-dive, delve, unpack, leverage, streamline, surface, it's worth noting, to be clear, importantly, that said, the moment, in one breath, the thing itself, here's the thing, not just X but Y, not X it's Y, em-dashes


This is a significant list but unfortunately not load-bearing enough.


The decision of which words to remove is genuinely yours.


a fork worth flagging


A game of Linguistic Jenga.


This baselines to a clear set


It is sufficient not at all


Another benefit of open models is that you can mask out out words from logits directly when sampling. I wonder if anyone has put together a "desloppifier" for e.g. DeepSeek


How about "genuinely"? Not sure why that one bothers me so much.


Cause that, along with some other Claudisms, just gives off a vibe of a highschooler trying to hit the word count on an essay.


Because its a explicit lie. Its not genuine, cannot be genuine. Will remind you of this if you so much as try to coax anything novel out....but it will then immediately reassure you with its genuine take....its insulting if you have any logic...thats at least my reasoning


So, basically, it's on mute now? :)


To combat it, I decided to only use Opus 5 if I'm actually talking to Fable 5 that's orchestrating it. :D Opus 5 experience is really abysmal, hopefully they can get it back on track.


I do not have this kind of money :( :)


What do you do when you want to talk about e.g. spines?


You use another model


couldn't this inadvertently make the model dumber? if these kinds of words are what lets it "think".


You forgot my favorite: “ablation”.


As it seems to be getting worse over time (with 4.8 being worse than 4.6 and 5 worse than 4.8 again), could this simply be signs of model collapse?

I mean more and more training data you find on the web is generated by previous models. The only reliable way to find human-generated text is to find text written before 2022, and they've used up all of that already. And AFAIU, these companies are using more and more synthetic data or semi-synthetic data.


I use a hook. Checks for banned words and patterns.

Injects a reminder to use ASD-STE100 Simplified Technical English which I picked up from a suggestion in another thread.

Honestly it’s working pretty well. Except for I need to check how often it’s actually firing.

https://en.wikipedia.org/wiki/Simplified_Technical_English

I feel like hooks aren’t utilized enough. Really nice for being the sort of auto steering as long as you can encode some pattern to detect the bad behaviour.

Prompts and skills just don’t cut it.


This is the take on this entire thread that I resonate with the most.

As a systems person, I do not know how to share with a details person how the combination of some magically conjured (and sometimes inscrutable) building blocks can still take us to interesting and joyful end results.


Maybe because Brendan Eich was tasked with "doing Scheme in the browser" before it pivoted to JavaScript.


Imagine what could have been...


You don't have to imagine. Clojurescript exists.


I like parenscript


I had forgotten about this. The last I saw this was 20+ years ago!


So many words to say: Scheme.

:)


Perhaps, but Chicken? Guile? Chez? They're all pretty cool.


R5RS, R6RS, or R7RS?


R6RS.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: