vrotaru · HackerTrans

4 dagen geledendiscuss

Just curious, can prefill be run on a machine with a mighty GPU and decode on Big Unified Memory Box?

If the prefill produces results the size of several GBs, that is probably not realistic.

vrotaru

9 maanden geledendiscuss

Here is my experience.

Claude did generated a rather good template for what I needed. It did not compile at first but I copy-pasted the errors and it fixed them.

Not all was good, though. It used literal bullets instead of `-` required for lists, but on whole the experience was positive.

It had taken me less time to fix the template than it would been taken to write it from scratch.

Something which Claude was good at. I throw him a crude ASCII "art" representation of what I want and get the right Typst code back.

vrotaru

10 maanden geledendiscuss

Sorry for harping on it, but I think this clearly reflects the difference between 2 approaches to storing knowledge, lossy but humongous, and lossless but limited.

LLMs - Lossy highly compressed knowledge which when prompted "hallucinates" facts. LLMs hallucinations are simply how the stored information is retrieved.

Memory (human in this case) - Extremely limited, but almost always correct.

Just an observation. No morals.

vrotaru

10 maanden geledendiscuss

There is a podman-compose which works almost as drop-in replacement.

Almost because most common commands work, but I have not check all.

And almost, because for some docker-compose.yaml which you downloaded/LLM generated you may need to prepend `docker.io/` to the image name

vrotaru

11 maanden geledendiscuss

That is a good questions and I guess we have good progress since Plato whose definition was - A man is a featherless biped.

But I think we still do not know.

vrotaru

11 maanden geledendiscuss

To some degree *all* LLM's answers are made up facts. For stuff that is abundantly present in training data those are almost always correct. For topics which are not common knowledge (allow for a great variability) you should always check.

I've started to think of LLM's as a form lossy compression of available knowledge which when prompted produces "facts".

vrotaru

12 maanden geledendiscuss

Well, not exactly convince. I was curious what will happen.

If you are curious it was a question about the behavior of Kafka producer interceptors when an exception is thrown.

But I agree that it is hard to resist the temptation to treat LLM's as a pear.

vrotaru

12 maanden geledendiscuss

You should always check. I've seen LLM's being wrong (and obstinate) on topics which are one step separated from common knowledge.

I had to post the source code to win the dispute, so to speak.

vrotaru

12 maanden geledendiscuss

So what is your pick?

* AI is the next electric screwdriver * AI is THE steam engine.

My pick is that the AI is not THE steam engine.

vrotaru

vorig jaardiscuss

> Oberon also doesn't seem to be actively developed anymore

That's pretty much it, for maybe 10+ years now. There was a successor project BlueBottle with some promise, but it did not deliver. Later it was renamed to A2. Surprisingly, it did not help.

https://en.wikipedia.org/wiki/A2_(operating_system)

IMO the authors of BB/A2 bet heavily on XML/Java hype, and were trying to make Oberon more like Java. The result was something without much internal consistency and not very usable.

Not being able to use a major browser and not having the resources to write one from scratch did not help either.

Then some of the major figures of this project left. And that was it.

There are some hobbyists and some small businesses which use it for niche projects and that is all

vrotaru

vorig jaardiscuss

It happens. It shows you the right suggestion, and if you keep typing it assumes that you meant something else and displays other suggestion.

Good for slow typers, not so much for quick ones.

vrotaru

2 jaar geledendiscuss

Maybe web.skype.com will be better? Just a guess.

Anyway, that's how I use Skype when I still have to use it. Which is about once a month.

vrotaru

2 jaar geledendiscuss

The are LLVM Caleidoscope (toy compiler) in both Haskell and OCaml

https://github.com/sdiehl/kaleidoscope https://github.com/arbipher/llvm-ocaml-tutorial

The Haskell one is a nice one. Can say nothing about the OCaml one since I found it using a google search.

I've had a try at implementing an Caleidoscope compiler in OCaml but did not finish it. But it was fun to write.

vrotaru

2 jaar geledendiscuss

I guess Modula-3 was doing it as well.

Records were structurally typed. But you can "braid"(?) a record and that will make it nominal type.

vrotaru

2 jaar geledendiscuss

You know what else is self-cleaning?

   /dev/shm

The advantage being that it does not even touch the disk.

vrotaru

2 jaar geledendiscuss

Just an example.

Should teachers be judged on how a pleasant life they live, or how good they teach?

vrotaru

2 jaar geledendiscuss

Stop optimizing for consumers, start optimizing for producers.

Maybe, you want to rethink that.

vrotaru

2 jaar geledendiscuss

lsattr - for reading attributes chattr - for setting them

You need the `i` attribute. But this is filesystem dependent. Anyway protecting the `sudo` binary from package managers is a so-so idea.

vrotaru

2 jaar geledendiscuss

So, in order to write a new browser you first have to write (as a training exercise) a new OS.

Not the fastest way, but it seems to work. Best wishes to Andreas.

vrotaru

2 jaar geledendiscuss

Guess so. Unfamiliar with Zig. The point is that not a "all or nothing" strategy for a compilation unit.

Debugger writers may not be happy, but maybe lldb supports all conventions supported by llvm.

comments