Viewing profile — zbyforgotp
zbyforgotp
HN member- Joined
- Fri, Jul 28, 2023, 8:00 AM UTC
- HN karma
- 54
- Public activity
- 66 items
- HN profile
- View on Hacker News ↗
About zbyforgotp
No profile information was provided.
Recent public activity
-
comment
Comment #48513946
On the flip side if there is a bug in one of my systems I would rather get a detailed bug report from an llm than a user message “xxx does not work”.
-
comment
Comment #48513893
This is so obvious that in practice it doesn’t buy much, but everyone is still propagating that silly news. This is the real malware, a mind virus.
-
comment
Comment #48169164
Too late for fixing it - but of course I meant https://www.qubes-os.org/
-
comment
Comment #48166863
In the limit we want the llm to write the code (like in RLMs).
-
comment
Comment #48166833
We don’t trust llm execution- so we add user approvals. But task decomposition calls for co-recursion between code and prompts. This means that the approvals should be evocable at …
-
comment
Comment #47995897
The idea is that the spec is somehow compressed in comparison to the code.
-
comment
Comment #47995867
You need supporting environment on both sides of the sandbox.
-
comment
Comment #47822243
Frontmatter should now be in the markdown standard.
-
comment
Comment #47206691
I have been struggling with that. Thanks! Let me reword it - natural language lacks a strict semantics - so also programs for the llm machine ( I.e. prompts) cannot have it. LLMs a…
-
comment
Comment #46912300
What is the root cause of this? It is said that AMD is hardware company and neglects software - but recently they issued lots of declarations of becoming software firs now.
-
comment
Comment #46703961
The point is for the agent to have an index of available skills so that it can decide autonomously if it needs to load one. https://zzbbyy.substack.com/p/what-are-skills In my expe…
-
comment
Comment #46673632
At some point evolving software instead of designing it will work. Now the evolutionary pressure leads towards churning more tokens.
-
comment
Comment #46397288
Property is a local low - it applies to a thing that exists in one place. Intellectual property is trying to apply similar rules to stuff that happen remotely - a text is not a thi…
-
comment
Comment #46044214
There is something not right with expecting that artificial intelligence will have the same characteristics as human intelligence. (I am answering to the quote)
-
comment
Comment #46044181
That’s why we need progressive hardening: https://github.com/zby/llm-do/blob/main/docs/concept_spec.md
- comment
-
comment
Comment #45846484
The American labs are paranoid. The secrecy kills innovation. Open Source means ideas can meet and have sex and produce offsprings.
-
comment
Comment #45769565
Destroying high trust society is a lot of fun.
-
comment
Comment #45729786
TLDR: ai changes the economic calculus of software development. It makes automated testing more beneficial in comparison to costs. I think he is right.
-
comment
Comment #45692411
They should just give the user some control over this
- comment
-
comment
Comment #45496535
Just to be precise. The sepsis alarm was not blocking x-ray or antibiotics but rather suggesting them. “”” Agyare had instructed Banerjee to hydrate Sam right away but to wait for …
-
comment
Comment #45369591
The problem is that people gravitate towards more impersonal relationships themselves because it frees them from the complexity of social calculations. We escape small organisation…
-
comment
Comment #44585126
I think our minds don’t use novelty - but salience and it also might be easier to implement.
-
comment
Comment #44440789
Zuck poaches AI devs and places them under Wang - how does that work? Wang doesn’t make impression of being a brilliant researcher or coder just a great deal maker (to put it diplo…