> 60% of college/university graduates are women, but it’s not “necessarily a positive story for women overall,” since it also means women are disproportionately burdened with student-loan debt.

Sol is an absolute machine. I stopped doing parallel worktrees just because the cost of context switch outweighs the cost of waiting Sol to just finish the task it’s working on which is usually anywhere from 1-10mins.

I also like Codex CLI more than the Codex App bc it’s more scriptable and displays all the tool calls and reasoning whereas in the App it’s kind of folded away/obscured. This way as soon as I see a tool call fail (eg it tries to use jq assuming it’s available but it wasn’t so I take a note to set it up as it’s obviously useful for the agent to wrangle json).

I think its amazing what OpenAI have been able to squeeze out from a model like Sol thats much smaller in size than Fable.

Yes, Codex has no comparison so far.

Do you use the annotations and forking features in codex CLI? I can't find an easy way to access them.

/fork IIRC for forking. it's open source so you can ask Codex to take a look at the Codex code

Codex CLI has support for keybindings tho last time I checked they were quite limited and you cannot replicate full universal text editing experience.

Those that have, more will be given. Those that do not, more will be taken.

Refreshing that the author doesn’t try to conceal his character or thoughts.

The contents of his character and thoughts are quite objectionable though.

> The contents of his character and thoughts are quite objectionable

That's just your opinion though, not an objective fact. I happen to be of the opposite opinion.

No one cares enough of zig to do it, people will just continue moving to Rust and similar.

Well exactly, "Zig + someone using AI" can never beat Zig + someone who cares. A developer that cares about the project comes first, no amount of AI can change that. AI could be a good tool for a developer though.

You seem to think you know other people’s best interests better than they do.

It is possible that I do. Fifty percent of people are of below average intelligence.

Damn this is exciting. I love that gpt models are much faster, efficient and cheaper than Claude models. They are so fast even on high/xhigh that I don’t find myself using the parallel agent setup anymore much since its cognitively less demanding to just follow along what the model is doing and most tasks it will complete in <5-<10mins anyway.

This is because GPT-5.6 is just a more posttrained version of GPT-5.5, not a bigger model than GPT-5.5. It's not like how Mythos is bigger than Opus.

GPT-5.6 --------> GPT-5.6 Sol

GPT-5.6-mini ---> GPT-5.6 Terra

GPT-5.6-nano ---> GPT-5.6 Luna

Two important things to note, if you want to verify what I say/correct me:

GPT-5.6 Terra actually scores worse than GPT-5.5 on many benchmarks. It's not GPT-5.5 trained with more compute; it's basically GPT-5.6-mini that's been distilled from GPT-5.6 full size. Remember, GPT-5.4-mini had almost the same benchmarks as GPT-5.2 after all.

Opus 4.8 runs at ~90 tokens per second. Fable 5 runs at ~40 tokens per second on from Anthropic, because it's a bigger/slower model. A few days after the release, when the dust dies down, look at how many tokens/second GPT-5.6 Sol is running at. I will bet it's the about same as GPT-5.5, and not half the speed. (OpenAI is not incentivized to slow down the model for paying customers). But the model tokens/sec will be a big clue- if OpenAI is charging more money for the same sized model or not.

bigger doesn't mean better, chill out

That's true but size of LLMs has been strongly correlated with their "intelligence".

not just that, but the entire industry spend several years seeking investment on the "pure" idea that they just need more compute and more parameters to reach AGI.

And the "business" obvious is still doing that but the science and implementation has be realizing that this just isn't true. They're not getting AGI out of a single LLM by itself.

They clearly know it but have to pretend otherwise to keep the money flowing.

right, but the business arm will always be dominant. I see what Chinese models are doing as the same as japanese car models in the 80s: producing smaller, more efficient products that address the realities of the "total addressable market" that no business model would support. They're, unfortunately, providing public value where the US and Europe used to tread.

There's a lot to make efficient, but it should be clear to everyone that just throwing compute at larger models isn't going to magically make it rain.

In this case, it does actually.

> This is because GPT-5.6 is just a more posttrained version of GPT-5.5, not a bigger model than GPT-5.5.

What is this very confident assumption based on?

If it were fully trained from scratch, you'd expect to see a major version bump. The other point releases have been fine tunes or post trains.

but 5.5 was also no major version bump

Also tokens/sec are not only dependent on parameter size, so that is kind of a brittle theory.

do we know that Mythos is in fact a bigger model then opus?

I love that Codex is open source and issues like these can surface/be addressed publicly.

But this is model behavior and just a public issue tracker which claude code has just without code? I don’t see how it’s any different than https://github.com/anthropics/claude-code for these issues.

I do appreciate that codex is open source generally, but I don’t think it matters for this class of issue as the model is closed still

I feel openai in general is much more open and real business like compared to anthropic. They’re just a black box.

Thanks, I had good laugh. Nice fanfic.

Wait what. I never used CC but use Codex CLI with 5.5 daily and authenticating has never been an issue. I even rolled skills that instruct it how to retrieve test user credentials for auth purposes.

Today using the devtools I asked it to reverse engineer the login auth flow of another app in our company and it created a nice browser-like headless script (with cookie jars etc) that emulates the entire Auth0 flow with all the internal API calls, redirect loops etc so that given username/password I end up with a valid JWT without having to open an actual browser instance and go through the login steps manually. Zero hesitation or questions asked.

I think this is in-line with OpenAI's philosophy. They see Codex agents as just tools for developer to use. They don’t try to imbibe them with “feelings”, “constitution” or “morality” the way Anthropic does.

Yeah Claude does this for me all the time. I have a template project I use that also leverages puppeteer/webdriver/Firefox, and I can point Claude at the template and a website and it will happily build me an MCP service that it can use to interact with the site if there isn't an API or MCP already available.

The fucked up part is CC has no problem looking through k8s secrets for credentials and authenticating to services on the command line. It's always been protective of signing in on the web.

That seems highly likely to be an anti-spammer measure.