Hacker Newsnew | past | comments | ask | show | jobs | submit | redrove's commentslogin

So this is basically vCluster[0] but Rancher branded?

[0] https://github.com/loft-sh/vcluster


Thanks. I knew I'd seen this idea before but couldn't remember the project name.

Closely related in pupopse, yes. Branded? no.

also kcp

Nothing, but he got to plug his vibe coded startup that he advertises in the about section.

It’s 128b dense model. Good luck getting more than 3t/s out of a mac. It doesn’t matter if it fits or not.

You could run it on a single Mac Studio with M3 Ultra, or two Mac Studios with M4 Max at higher perf than that. And lightly quantizing this could give us modern dense models in the ~80GB size range, which is a very compelling target.

Wouldn't matter much still. M3 ultra has 819GB/s unified memory bandwidth. That means theoretical max tokem rate is 819/128 =~ 6.39 t/s. At 80 GB (5 bit quantization), its still near about 10 t/s ... far from a good coding experience. Also, these are theoretical max.. real world token generation rates would be at least 15-20% less.

I keep trying to use dirac-cli with codex and it won't work: Error: Codex API error: Codex API request failed: 400.

Any ideas?


Assuming you logged in with OAuth, I am guessing you are trying to use gpt-5.5?

In my tests, it worked using gpt-5.4 for me and I assumed gpt-5.5 is not available to me because I am on the free plan

Do you have the subscription that allows 5.5? If so, I can look into what changed in API. Sorry I rarely use openAI so it is a bit of an untrodden path


Yes I'm on ChatGPT Pro (OAuth) and I'm trying to use gpt-5.5-xhigh.

That was the issue, 5.4 works just fine.

Support for service: priority (GPT /fast mode) would also be cool!


Will fix this soon. Please feel free to create a github issue in the meantime.

Gpt 5.5 is now fully supported using codex and api

cool!

So an Obsidian plugin? Got it.

One can imagine an obsidian plugin of any arbitrary level of complexity, given it's written in a Turing-complete language.

This is very well put. Thanks for the comment.


It seems to be 160GB at mixed FP4+FP8 precision, FYI. Full FP8 is 250GB+. (B)F16 at around double I would assume.


There is no BF16. There is no FP8 for the instruct model. The instruct model at full precision is 160 GB (mixed FP4 and FP8). The base model at full precision is 284 GB (FP8). Almost everyone is going to use instruct. But I do love to see base models released.



Expired.


I’ve been using Codex Pro since they lobotomized Opus 4.6. Codex is so much better, GPT 5.4 xhigh fast is definitely the smartest and fastest model available.

For a while there I had both Opus 4.6 and Codex access and I frequently pitted them against each other, I never once saw Opus come out ahead. Opus was good as a reviewer though, but as an implementer it just felt lazy compared to 5.4 xhigh.

One feature that I haven’t seen discussed that much is how codex has auto-review on tool runs. No longer are you a slave to all or nothing confirmations or endless bugging, it’s such a bad pattern.

Even in a week of heavy duty work and personal use I still haven’t been able to exhaust the usage on the $200 plan.

I’ll probably change my mind when (not IF) OpenAI rug pull, but for spring ‘26, codex is definitely the better deal.


I also made the switch to OpenAI, the $20 plan, I dunno about "so much better" but it's more or less the same, which is great!

The models and tools levelling out is great for users because the cost of switching is basically nil. I'm reading people ITT saying they signed up for a year - big mistake. A year is a decade right now.


I underscored using xhigh + fast mode when saying it’s so much better.

Now with Opus 4.7 of course the “burden” of adjusting reasoning effort has been taken away from you even at the API level.

In my experience people don’t change the thinking level at all.


What issues did you consider about sending your code base to OpenAI?


None mate. Code is cheap, it's not worth anything any more, especially not my little personal projects


Any alternative to Claude Design ? Tried Figma with Opus 4.6 but it doesn't come close in my experience.

Codex is abysmal for UI design imo.


It really depends on what you‘re trying to do and what your skillset is.

But if you go information architecture first and have that codified in some way (espescially if you already have the templates), then you can nudge any agent to go straight into CSS and it will produce something reasonable.


Have you tried stitch.withgoogle.com?


Thanks for the tip! Hadn't seen that, but definitely giving it a try.


I created some decent prototypes with stitch but I don't know how it compares to claude design


stitch.withgoogle.com


I've been using paper.design and it's been working well for me via mcp on claude code


Google Stitch



Does this have a CLI only interface?


Yes. You could also look at the README.md.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: