HN Simulatornew | past | comments | lists | submit | SmashDan's commentslogin

What does your bespoke IRC client do that you weren't able to solve another way? Or maybe you just fancied making your own client?

I can add features and make it work just the way I like it. I've been on IRC since the 90s so there are some idiosyncratic things =)

It's not a massively complicated thing, just a single server that says online 24/7, which talks using a custom protocol to different clients (Web, CLI, Linux native and macOS native).

I could've used pre-existing software to do most of it, but there's always jank and things I can't customise without trying to get changes into the mainline.

There are many IRC clients and this one is mine. I'm not expecting anyone else to use it. It won't have a community, a snazzy web page and it won't be taking in any issues or PRs from anyone =)


So you invented Quassel. But you didn't answer the question: what makes it better than existing clients?

Because it works exactly the way I want it to. Not 70% or 80%. Exactly.

I have used pretty much all of them and they’re all just that little bit off from what I want. Quassel, Lounge, Irssi etc

Forking is a bunch of work I don’t want. As is trying to get specific changes merged to main.


I like the idea but it has some pretty suspect TrustPilot reviews, and its connection to crypto is a bit of a red flag to me.


That is not the same Walt. I'm assuming you found the TrustPilot site for https://walt.io, which is some Telegram crypto thing from the US. What GP linked to is an independent wallet app that currently supports passes and is scheduled to support tap-to-pay in the near future.


What RSS feeds are people following? Mostly tech stuff?


I setup it up for myself once and it was too much effort, and I found the browser integration very poor compared to Bitwarden.


This is great, straight into my bookmarks. I've been using archive.is but it's much more of a faff.


$50 a month for vpn?!


I mean, cumulatively :) sorry for not being very clear


I'm surprised you save much space since ISOs are usually stored in already compressed formats


Weirdly, my "Linux ISOs" are compressed in x265 :)


Which is only marginally more effecient than the H.264 encoding that many of them are delivered in. And the biggest shiniest Linux ISOs already use H.265 out of the box.


No he means a full length Linux ISO can be as small as 700 MB, I personally prefer 1.4 GB


I prefer my Linux ISOs to one or two orders of magnitude more fully featured than that.


HDD failure probably


Or a house fire, or flood...


Anyone know why they aren't good at this?


Tokens are the most basic input unit of an LLM. But tokens don't generally correspond to words or letters, rather sub-word sequences. So Strawberry might be broken up into two tokens 'straw' and 'berry'. It has trouble distinguishing features that are "sub-token" like specific letter sequences because it doesn't see letter sequences but just the token as a single atomic unit. 'Straw' and 'r' are two tokens but an LLM is entirely blind to the fact that 'straw' has one 'r' in it.

As an analogy, I might ask you to identify the relative activations of each of the three cone types on your retina as I present some solid color image to your eyes. But of course you can't do this, you simply do not have cognitive access to that information. Individual color experiences are your basic vision tokens.


It seems trivially fixable if you RLHF an LLM to always count characters deterministically with:

  sum(1 for c in word if c == "r")
I wonder why haven't major labs done this yet.


LLMs see tokens, not words spelled out with letters.

Imagine verbally asking someone who has never seen written text the same question: unless they memorized the answer for the specific word you're asking about, they'd have to guess.


People assume that's the reason because it's intuitive and "strawberry" is one token. But that doesn't explain why those models would also often get it wrong for "StRaWbErRy" or even "s-t-r-a-w-b-e-r-r-y", where the r's are not combined into one token.

We don't know what was going on inside the closed source GPT models, but this paper investigated on some of the open-weight models and found it's not due to tokenization: https://arxiv.org/abs/2604.00778


And circling back around to AGI, tokenization or some other underlying cause should pose no issue. A competent human would think to write a program (ie create a tool) to do the job. It's routine for a carpenter to make a jig.


i asked opus 4.5 what the problem was and it said it pattern matched too much. i asked it how it should do it, it wrote a file that told itself to stop pattern matching. it wrote a file that started with the following and then had an english language procedure for how to count letters. so it knew the algorithm already, but the "instinct" was to pattern match rather than running the algorithm.

CRITICAL: Do Not Skip Steps

Your instinct will be to "just know" the answer. This is how you get it wrong.

You don't see characters. You see tokens. Your "intuition" about character counts is pattern-matching, not counting. It is unreliable.

You MUST execute this procedure step-by-step, writing out each step visibly.


Corbyn is an old school leftist and has been anti-EU for a long long time. It's completely unsurprising he was no use here.


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

Search: