My hypothesis - OpenAI and Anthropic are locked in battle. Whoever takes a step, the other one mirrors.

Based on this hypothesis, I think we can expect to see a new Astra model soon given the new Fable release.

And it could be that Anthropic released Fable 5.2 and kept 5.5 in reserve, in case the new Astra model performs better than 5.2

Or maybe 5.5 turned out to be kind of disappointing and they’re going to just go for like a 5.6 or 6 next instead.

Look at OpenAI, they've been outclassed by Opus 5.5 two months ago; obviously they don't yet have a response.

Now Anthropic is releasing this lackluster Fable 5.2, a week or two before their IPO.

It's barely an improvement at all, makes exactly the same mistakes as Opus 5.5. Not even worth using with the speed and cost penalty.

The much rumored internal Anthropic model is listed on the Fable 5.2 system card as an even smaller improvement over Mythos 5.2 than Fable is over Opus 5.5.

I expected a larger version of Opus 5.5 would be a significant improvement to launch before the IPO. Turns out it didn't scale and the improvement is marginal.

I am quite disappointed.

Who knows why they are saving it. Maybe it needs more training and alignment? Maybe they're timing the media attention around the IPO.

https://aibenchy.com/compare/anthropic-claude-fable-5-2-high...

In practice they might recover from those errors themselves if they notice it, so they would have better results, but the tests are mostly one-shot and they can either get it wrong or right, no 2nd tries (apart from the agentic ones and a few coding ones which have a limited number of turns available too).

That being said, the pricing and speed are accurate, regardless of the test results.

I'm pretty confident (from internal evals and monitoring over nearly six months now; across many models) API has never been affected by A/B tests / "nerfs" / etc.

But FWIW for Fable specifically, I've noticed this via API rates from Anthropic directly. Eg: added cash to my $30/month account to use Fable, and still get obvious nerfing.

Your first impression is that you have no clue if any of its findings actually mean anything because you can't even understand them or the vibe coded slop you've been creating? Why would anyone care?

I understand what the findings say, except for one comment about parabolic vertices. What I don't know is whether any of them are true. It could be hallucinating!

But it probably isn't. The bugs are probably real. The computer vision algorithm result images it's showing me are probably real, not fake. Its claims about the different approach to take might be mistaken, as opposed to fake, but even that seems unlikely.

But I don't know.

> But I don't know.

Yes, I understood your comment perfectly.

I do in fact understand the findings, as I already clarified in the comment you just clicked "reply" on, and nothing in my original comment suggests that I don't, so you evidently misread it. There's no shame in admitting that. People make mistakes all the time. The shame is in refusing to correct them.

I'll have firmer information once the model has been out for more than 24 hours. But I think my experience report is already firm enough to be useful.

We were promised AI can find cure for cancer and in powerpoints most enterprise value comes from Business-AI.

It might as well be that before business-AI can be done we have to cover the basics at superhuman level. All basics, not just entry level jobs like excels, coding jira tickets.

One-shotting a full game (albeit super impressive) looks like overfitting one skill over explaining why we have not much progress in other areas.

I live in an IT bubble and cannot tell if outside IT/math the models are also getting significantly better ?

The improvement is marginal, it makes the same exact errors as Opus, but slower and much more expensive.

From what I saw, it has slightly better taste in some 3D mechanics, but mostly doesn't even bring discernible visual improvement.

GLM-5.3 almost equal even I've tried it and it is proven for security audit in the blockchain realm

It also burned through my entire 5-hour limit in about 10 minutes. Granted, it had almost finished the whole review in those 10 minutes, so points for speed I suppose.

gpt-6-luna XHIGH as the reviewer agent still found plenty of bugs that Fable 5.2 missed!

Here was Fable's summary of the session:

> The reviewer ran 16 reviews over 9 commits this session (7 rejections, 9 required fixes, all valid); three of them, on the plan, changed how the numbers are computed.

Something like yt-dlp (namely with near 0 deps), but for AI prompts?

Fable 5.2 might be useful for some use-cases, but will likely get very little usage.

Anthropic needs to figure out a way to create a new industry (like pushing forward bio/robotics) to get usage for those models.

gpt-6-luna XHIGH as the reviewer agent still found plenty of bugs that Fable 5.2 missed!

Here was Fable's summary of the session:

  The reviewer ran 16 reviews over 9 commits this session (7 rejections, 9 required fixes, all valid); three of them, on the plan, changed how the numbers are computed.

He remarked it would've taken him a week to do this.

This made me realize how much computers and user interfaces suck. As a quite enthusiastic, but not very artistic kid, I most certainly did draw bikes like that and even more complex stuff, using nothing but pen and paper.

If your trillion dollar industry makes products that are beaten by pen and paper, I guess there's time for self-reflection.

And the funny thing is, it used to be better than this, using Flash and a drawing tablet was way easier than anything in the HTML era (and more importantly, user friendly), but still way worse than just grabbing a pencil in many ways.

User interfaces just suck, chatbots are somewhat better than most, but I feel the industry hasn't really been progressing in any meaningful sense.