back
user profile
helloplanets
2,648karma·541submissions·September 15, 2020
recent activity (541 total)
comment
What do you mean?
comment
You can create tools without using MCP for OpenCode: https://opencode.ai/docs/custom-tools/ …
comment
> particularly because its UX affordances are reminiscent of a slot machine’s: you pull the lever, you get a reward (a solution to your coding problem.) I hope the field moves out of the TUI with p…
comment
I'd just imagine that leaving the platform would come before adding something like this to their codebase. With GitHub recently changing their GitHub Copilot data collection from opt in to opt ou…
comment
I thought we already were sliding down the slippery slope here.
comment
This isn't about me in any way. If something in your software is intentionally malicious or damaging, it's malware. Doesn't really matter what the reasoning for including the malicious …
comment
Some comments from the dev on the GitHub thread: > It's as much "active destruction" as telling someone to eff themselves. > Funny to have GenAI proponents talk about "delibe…
comment
If you use API billing, you can use them from anywhere. But using Claude Code with a Max subscription is massively cheaper for programming. You should never use Claude models for programming through A…
comment
Did this get hugged to death? Not loading for me at all.
comment
That sort of countermeasure system could be done without AI as well. The problem is that it's illegal. No Castle Doctrine in cybersecurity afaik. Interesting variation on that could be AI that bu…
comment
So... You've never had a bad interview. Congrats!
comment
More straightforward to talk about the hardware directly. Full Kimi K2.6 needs an 8x H200 node to run and serve around 20 heavy users. You can rent an 8x H200 node for around $30/hr. I'd ima…
comment
Instead of worrying about the implications on HN, I'd rather worry about the implications on you as a consumer of HN. I wouldn't be comfortable creating a bubble inside of a bubble, but to e…
comment
Thank you for linking this! It's great. :)
comment
The usual way of measuring a trait would basically be measuring N amount of people on a specific thing, and the distribution based on that. But if you take 1 person, and N amount of specific things…
comment
This seems to be anchored around optimizing your intelligence to be a competitive advantage. Life as a competition of minds. For example: > Improbable lives have fewer competitors > The more yo…
comment
https://github.com/torvalds/AudioNoise > The python visualizer tool has been basically written by vibe-coding. I know more about analog filters -- and that's not saying m…
comment
Nano Banana is one of the most used image gen models
comment
Not about money, but knowledge. The frontier of the field is no longer accessible through arXiv or research papers only. One thing is that the companies are holding on because of competitive advantage…
comment
Karpathy left OpenAI in 2017 for Tesla, came back from Tesla in 2023 and left again in 2024. So pretty sure the original poster is talking about 2017.