setnone's comments

On: Anthropic surpasses OpenAI to become most valuable AI startup

[setnone]

my take it's because of the naming: Amodei, Claude and Mythos have this money-throwing vibe to it

On: Claude Opus 4.8

[setnone]

Claude's 4.6 - 4.7 transition made me discover codex, and with gpt 5.5 there is no way i'm going back

[cactusplant7374 → setnone]

Codex has been incredibly slow for the past few days. I think OpenAI is running out of compute in the face of increasing demand.

[winwang → cactusplant7374]

My experience has been that 5.4 is slower than 5.5 (confound: I use >512k max context size for 5.4, though it seems slower even below the normal size)

[peder → dakolli]

ha, exactly... like, the % change could be minuscule (or worse, it might only be a perceived difference, the actual quality may have regressed, or the scenario just didn't lend itself to that specific model) but people will be on here proclaiming that they're now shipping 10x the number of PRs.

[setnone → dakolli]

if you go this route don't hold your thoughts on the casino itself

On: Tell HN: Claude 4.7 is ignoring stop hooks

[setnone]

bunch of Tells HN incoming...

On: Tell HN: Claude 4.7 is ignoring stop hooks

[setnone]

> they will usually provide extremely useful information

bold claim, they'll provide bunch of words for sure like in this particular tool's response

On: An update on recent Claude Code quality reports

[setnone]

absolutely agree: non-1M Opus 4.6 on x20 max was peak AGI

now it's back to regular slop and just to check otherwise i have to spend at least $100

On: An update on recent Claude Code quality reports

[setnone]

Good on them for resolving all three issues, but is it any good again?

[alxndr13 → setnone]

for me at least, yes. just wrote it to coworkers this afternoon. Behaves way more "stable" in terms of quality and i don't have the feeling of the model getting way worse after 100k tokens of context or so.

What i notice: after 300k there's some slight quality drop, but i just make sure to compact before that threshold.

On: I am building a cloud

[setnone]

Yeah i feel like it's getting cloudy

On: How do you overcome the "build it and they will come" trap?

[setnone]

It's really hard out there, but trap? who's trapping you?

[entreel → setnone]

Your just trapping yourself lol, by delaying the distribution and just building that is what I mean

[setnone → entreel]

some strong advice here for example

https://news.ycombinator.com/item?id=47667504

On: Show HN: Mediator.ai – Using Nash bargaining and LLMs to systematize fairness

[setnone]

definitely a great use of LLMs

On: Slop Cop

[setnone]

'Add Slop API Key' button is a missed opportunity here