HackerTrans
TopNewTrendsCommentsPastAskShowJobs

zby

no profile record

Submissions

RLM Explained

twitter.com
1 points·by zby·5 bulan yang lalu·0 comments

Dragon Hatchling: Missing Link Between the Transformer and Models of the Brain

arxiv.org
1 points·by zby·9 bulan yang lalu·0 comments

comments

zby
·11 hari yang lalu·discuss
Frankly I just skimmed that article, and still commented, bad me.

I was also confused by the tag menu - I thought they are sections in the article - I completely failed here :(

By the way I have a page with some more sources for the context degradation phenomenon: https://zby.github.io/commonplace/notes/agent-context-is-con...
zby
·13 hari yang lalu·discuss
It is interesting to compare this to LLMs - they also have the bounded context that you can see as the analogue to our working memory. It can contain enormously more bits of information than the 4 things the article says is the capacity of our working memory - but the 4 things can probably be much more complex internally - they are more like 4 pointers probably.

But at some level context engineering is very similar to what this article talks about.
zby
·15 hari yang lalu·discuss
select text and comment on it - then let the llm read all comments
zby
·15 hari yang lalu·discuss
The feature I am waiting for in all of these editors is integrating 'red lining' as a channel for LLM input. This is the best interface for working on a text. https://www.roughdraft.md/ does the core idea pretty well - but is not well integrated with the rest (browsing, etc).
zby
·19 hari yang lalu·discuss
If the action is decided by code based on metadata - then what is really the LLM task? And if you say that it is only the type of action that is decided by code - then this is maybe a mitigation - but the llm still can do a lot of harm. And also it is very limiting - using the llm to decide the action is very useful. This is different from SQL injection - where the action is determined by the code and the injection is really making a code parsing error.

It might still be the way to go - but calling it 'the real solution' is overselling it.
zby
·19 hari yang lalu·discuss
They do predict what injections might be effective - so it is a theory. I don't know how novel it is and it is not very deep (as you noted the general mechanism is quite obvious) - but they do it quite systematically so it is useful.
zby
·24 hari yang lalu·discuss
The video seems to be about mushrooms.
zby
·25 hari yang lalu·discuss
The fact that programmers can be nerd sniped into yak shaving some random libraries is the only thing that keeps Open Source running.
zby
·28 hari yang lalu·discuss
I would love to hear from someone knowledgeable - is that bad for the company or good?
zby
·28 hari yang lalu·discuss
I am open to changing my mind and I am looking forward for answers to your question - but I think it is like a click bait - looks interesting - but not really useful.
zby
·bulan lalu·discuss
I am building my self-hosting llm-wiki system (https://gist.github.com/karpathy/442a6bf555914893e9891c11519...). My approach is to start with a theory of how such systems could work. Then since llms can interpret theory - this theory becomes an executable llm-wiki system itself.

It's called Commonplace: https://zby.github.io/commonplace/
zby
·2 bulan yang lalu·discuss
I think I fixed this in a later revision. Does that persist?
zby
·2 bulan yang lalu·discuss
There is also https://github.com/Dicklesworthstone/pi_agent_rust

I vibed a comparison/review of these two systems using my llm wiki: https://zby.github.io/commonplace/work/pi-agent-zerostack-co...

(the prompt is in https://zby.github.io/commonplace/work/pi-agent-zerostack-co...)
zby
·2 bulan yang lalu·discuss
"In the 890s, having recently converted to Orthodox Christianity, Boris ensured his church would be independent from the Patriarchate of Constantinople." --- I thought Orthodox Christianity was created by the Great Schism in 1054.
zby
·2 bulan yang lalu·discuss
And how they are doing? I think this might be a solid research program - but that blog presented it as some kind of practical approach.
zby
·2 bulan yang lalu·discuss
So no hope for https://xkcd.com/810/?
zby
·2 bulan yang lalu·discuss
First you need to write these specifications and if you say just tell the llm to write them - then how would it be different from just tell the llm to write the program?

I guess you can argue that these are two independent processes so you can combine them to get something more reliable than both - this might be a viable path. But from what I heard writing formal specifications is just really hard - I haven't seen anything practical in this area.
zby
·2 bulan yang lalu·discuss
I concur - it does not make sense to do in llm prompts what can be done in code. Code is cheaper, faster, deterministic and we have lots of experience with working with code.

Especially all bookkeeping logic should move into the symbolic layer: https://zby.github.io/commonplace/notes/scheduler-llm-separa...
zby
·2 bulan yang lalu·discuss
""" we need to build:

    Formal specification layers that agents execute against, not just prompts
"""

It is probably easier to just write that program.
zby
·2 bulan yang lalu·discuss
It is not novel - but with the new models it is just becoming practical.