Viewing profile — phito
phito
HN member- Joined
- Fri, Oct 28, 2016, 8:05 AM UTC
- HN karma
- 2,079
- Public activity
- 764 items
- HN profile
- View on Hacker News ↗
About phito
No profile information was provided.
Recent public activity
-
comment
Comment #49206940
It was always easy to copy software (but yes, even easier now). The hard part is competing with the software that you're copying. Software does not exist in a vacuum. They usually …
-
comment
Comment #49110237
Same here, I do not see the point of herdr if you're already using tmux. It's very easy to add hooks to your favorite harness to display a notification in tmux when it's done worki…
-
comment
Comment #49044757
Myeah, the first thing I saw when opening it on mobile is that the top logo is not centered and the menu is not displaying properly ("About" item single on a line with some random …
-
comment
Comment #48844847
At this point it might be easier to point out articles not written by LLM. Most of them are, I just can't bring myself to read them anymore, it feels like a waste of time. I want t…
-
comment
Comment #48844557
Does this apply only to new messages or also to history?
-
comment
Comment #48672123
We do this because we need redundancy. Are there non kubernetes alternatives for HA/redundancy that are worth it?
-
comment
Comment #48512966
What do you mean, companies are already paying for almost good. Coding is indeed serious work and not even Fable is good enough for serious work.
-
comment
Comment #48394132
Also there's a brain, the GPU
-
comment
Comment #48234362
That's a good question... => I didn't think about this, I don't know the answer yet. That's a great question! => I can tell you understood what I explained and used that understand…
-
comment
Comment #48194713
I agree, just like some people decide that they're OK with eating junk food every day, knowing the long term risk. They are free to take it.
-
comment
Comment #48193961
> If I do ask an LLM another question about something small it will offer solutions but doesn’t offer the solution I think makes sense in the architectures I’ve written. This is my…
-
comment
Comment #48177916
I use AI a lot for development, but I am not sure why students should "embrace" the new technology made to take the job they are studying for.
-
comment
Comment #47918654
It's true for all automation we do get more comfort. We build systems so that we humans have as little struggle as possible, not realising that struggle is the only reason for exis…
- comment
-
comment
Comment #47873130
You're wasting a ton of tokens doing that though. Right now you don't realize it because they're being heavily subsidized, but you will understand the point of have good orchestrat…
-
comment
Comment #47753048
OP doesn't seem to be on Mac
-
comment
Comment #47573827
I think their current goal is to capture as much market as they can while they still have the best models, their only moat. Look at Anthropic, they are clearly trying to lock their…
-
comment
Comment #47552057
Less RAM usage doesn't equal better performances or faster software. It actually might mean the opposite, if you're not caching things in RAM.
-
comment
Comment #47435338
While some of the ideas in this do resonate with me (or at least they're entertaining), it's unfortunate that's it's so obviously LLM generated. And some parts of it, like the INTJ…
-
comment
Comment #47425595
Yes they are, but it's still messing up nature. Was just to give some pushback to the venomous parent comment.
-
comment
Comment #47425342
That's really bad... I don't care if people (probably LLM here) do these kind of mistakes in their own personal tooling. But when you're going to distribute it as some sort of libr…
-
comment
Comment #47421634
In a lot of places, most of your electricity is generated by burning coal and gas.
-
comment
Comment #47400847
I think curing GAD will mean changing your personality. There's always going to be a before/after you, that's the whole point. The important part is being able to reliably know wha…
-
comment
Comment #47400583
It also needs to work at least 99% of the time if not more. Not easy to do this with indeterministic models.
- comment