Viewing profile — Klathmon
Klathmon
HN member- Joined
- Fri, Jan 30, 2015, 9:33 PM UTC
- HN karma
- 13,861
- Public activity
- 3,738 items
- HN profile
- View on Hacker News ↗
About Klathmon
Recent public activity
- comment
-
comment
Comment #49117557
I'm actually finding Luna to be an extremely strong model in practice. I almost exclusively use it with xhigh or max effort, but when run like that it's been an incredibly cheap li…
-
comment
Comment #48826686
I feel like we have the technology to prevent a car from starting if the driver is significantly impared, but "solving" addiction, cancer, and heart disease are much harder problem…
-
comment
Comment #48799748
If they're using a static threshold of 200 views and there aren't many of these left it could pull them all out of that category. It could obviously be fixed but I was more curious…
-
comment
Comment #48799376
How many of these images are there? I cycled through a few and ended up hitting at least one duplicate [1] that I do actually enjoy (but I can't find the name of it now that I refr…
- comment
-
comment
Comment #48785322
AES is so cheap with hardware acceleration that I could see an argument that it prevents casual sniffing of the traffic. Personally I think the false sense of security would outwei…
-
comment
Comment #48785302
Yeah it wouldn't have changed this specific case but still why use it? It's slower even without AES NI!
- comment
-
comment
Comment #48781816
Is there any valid reason to still be using 3DES in 2026? It was formally deprecated in 2018 and has been surpassed in just about every single way by AES long before that. At this …
-
comment
Comment #48780893
I also have no idea what I'm talking about, but to me this seems closer to the "caveman mode" that some people use to compress info into fewer tokens. Going through the image token…
-
comment
Comment #48779796
That's like saying quantization isn't real because the frontier labs aren't using it in their production inference. This is a lossy process, it produces worse results. It might be …
-
comment
Comment #48693693
But it's not just him, it's the entire party aggressively supporting him and everything he does.
-
comment
Comment #48638315
There are also cases where breaking a "rule" is the right thing to do. I've had several instances where I told the model to do something that was accidentally impossible if taken a…
-
comment
Comment #48554038
I've been pretty damn happy with codex and vscode. Between the codex app, cli, and vscode extension there are options for most ways of working
-
comment
Comment #48459778
This is what I'm advocating for. Give each dev's AI agent its own identity with its own access controls and tokens and everything. It helps solve both the access control and attrib…
- comment
-
comment
Comment #48179231
> I don't see 'grandma' building here own calendar app via Claude Code that reminds her of the family birthdays. If you think of apps in the traditional sense I think I agree with …
-
comment
Comment #47942531
In our internal metrics you can see a clear increase in PRs and CI runs in general that tracks with agentic coding adoption, and it's significant, so I absolutely buy that GitHub w…
-
comment
Comment #46566558
There have been a few instances, IIRC there was an Apollo mission that had a head cold spread among the whole crew. But that's unlikely to be the case here because they've been up …
- comment
-
comment
Comment #45938249
And if you like it, picking up any QMK or ZMK compatible keyboard would let you do it in firmware too!
-
comment
Comment #45787757
Should you never use a calculator because you want to keep your math skills high? There are a growing set of problems which feel like using a calculator for basic math to me. But a…
-
comment
Comment #45786770
> For code modifications in a large codebase the problem with multi-shot is that it doesn't take too many iterations before I've spent more time on it. I've found voice input to co…
-
comment
Comment #45786731
If the LLM is able to handle it why do you need to maintain those specific skills?