Viewing profile — py4
py4
HN member- Joined
- Tue, Nov 02, 2021, 1:53 AM UTC
- HN karma
- 199
- Public activity
- 98 items
- HN profile
- View on Hacker News ↗
About py4
No profile information was provided.
Recent public activity
-
comment
Comment #49249916
tnx. can you share more about your game experiment?
-
story
Ask HN: How do you learn with LLMs?
I am not happy about GenAI progress affecting my career though I am excited about its application for personalized learning. How do you use LLMs to learn advanced technical stuff b…
-
comment
Comment #49174420
I am not sure. Why do you need domain expertise beyond being able to draft a verifier for the problem? Once you have the verifier, it's just a matter of compute. You can argue that…
-
comment
Comment #48284290
I understand the negative sentiment toward Altman, but just to be fair, how do we define 'lying'? How does his behavior compare to that of the average executive, or even the averag…
-
comment
Comment #48269639
you wait for it to finish then review or give feedback in the meanwhile? if it's the former, i'm curious about what you still do in the meanwhile
-
comment
Comment #48269371
sounds like a plan haha. How is OpenCode vs Claude Code orchestration? have you ever needed to modify the orchestration since it's open source? do you mind sharing more about your …
- story
- story
-
comment
Comment #47527451
I wrote my experience here: https://pooyam.dev/i-miss-coding
- story
- story
- story
- comment
- story
- story
- story
-
comment
Comment #46789958
I was saying it was not commoditized a decade ago, but i feel it's getting commoditized *now*. So you seem to be basically saying SWE is over and it's time to move on to something …
-
comment
Comment #46789862
I honestly think a better title would be "how to stay relevant in LLM era"
-
comment
Comment #46789816
simple example: Claude Cowork was written entirely with claude code
-
comment
Comment #46789764
1. No, implementing well defined requirements were not commoditized a decade ago. You still have to come up with the design and proper (efficient,correct,...) solution that respect…
-
comment
Comment #46787950
i'm trying to see what i can do to stay relevant
-
comment
Comment #46787943
llm training/inference stack
-
comment
Comment #46785504
LLM is not hype. it has made and my colleagues who are NOT working on CRUD, way more productive
-
comment
Comment #46785469
Let's say you want to make an architectural change. There are two options: 1. Ask AI to come up with the different options and let you review it 2. You think about the options and …
-
comment
Comment #46785333
if it's able to do the interesting/engaging part faster than me, i don't see why i should not outsource to it (The same argument as why use LLM-assisted programming at all, you don…