Viewing profile — CjHuber
CjHuber
HN member- Joined
- Mon, Apr 19, 2021, 8:22 AM UTC
- HN karma
- 440
- Public activity
- 183 items
- HN profile
- View on Hacker News ↗
About CjHuber
No profile information was provided.
Recent public activity
-
comment
Comment #48906223
Every good thing is alike, every slop is sloppy in its own way
-
comment
Comment #48905221
Given that codex itself now ships a proxy that wraps the subscription, it seems unlikely https://github.com/openai/codex/blob/main/codex-rs/responses...
-
comment
Comment #48884169
> Probably because the general purpose subagents inherit the parent model only if you don't specify which model should be used
- story
-
comment
Comment #48849708
> Instead of requiring developers to script every step or passing every tool response back through the model, Programmatic Tool Calling in the Responses API can filter large amount…
-
comment
Comment #48830136
but 5.5 was also no major version bump
-
comment
Comment #48829087
> fit a lot more work inside the model's context window before you're forced into a slow and lossy compaction step This is something I never understood. Why the reasoning is not in…
-
comment
Comment #48828897
Well, obviously its true as you can see in the silbing comment. But still interesting how experiences differ. I wonder did you ever use codex in more demanding workflows, because t…
-
comment
Comment #48827857
Interesting to hear people like gpt-5.5. For me it feels smart only at one shot prompts, but if you try to build up session context before doing something it feels magnitudes infer…
-
comment
Comment #48827307
> so you now have to wait in line for hours Interesting, I go there pretty regularly and while It is well visited, I not once encountered a queue there
-
comment
Comment #48795447
I agree, adaptive thinking is a pest and without a minimum thinking budget especially Claude for me currently defaults to not think at all even on max effort. Sequential-thinking w…
- comment
-
comment
Comment #48556410
I think this is a really good cause but I can't help but wonder about the contrast between the puppy analogy and then increasing the friction of installing it by making it a paid t…
-
comment
Comment #48538012
What about GBrain
-
comment
Comment #48525958
Yeah indeed it's very interesting. And the 60k initial context don't even contain the suggested change yet. For me if I don't do this the current models tend to fixate and local pa…
-
comment
Comment #48525395
I'm always a bit confused when people say things like this. 60k token is often more than the initial context I feed the model with. And I don't think I ever had a productive sessio…
-
comment
Comment #48494334
So isn't that just purely security by obscurity then? Would they not rather have someone publicly break it instead of selling a zero day?
-
comment
Comment #48472926
Technically yes
-
comment
Comment #48168322
I‘m glad you didn’t write value
-
comment
Comment #47945060
Are you… explaining the effects of being acquired to Hashimoto?
-
comment
Comment #47884483
It does have an built in documentation subagent it can invoke but that doesn’t help much if they don’t document their shenanigans
-
comment
Comment #47884410
This is exactly what also confused me. I had the exact same prompt in Claude code as well, and the no option implies you can also keep the whole history. But clicking keep apparent…
-
comment
Comment #47881826
No of course it’s unrealistic for them to hold the cache indefinitely and that’s not the point. You are keeping the session data yourself so you can continue even after cache expir…
-
comment
Comment #47880732
I think it’s crazy that they do this, especially without any notice. I would not have renewed my subscription if I knew that they started doing this. Especially in the analysis par…
-
comment
Comment #47673983
I‘d much rather have it go slooower and check more. Why faster it’s way too fast