afro88

The one that twigged me was in one of the first diagrams:

> Gradual release > The latest channel first; the stable channel trails it

Such an awkward, Claude-ish way of saying it

Under low risk, no reviews required:

> additive changes behind a flag

That's low risk when the flag is off. Is there suddenly proper code review before the flag gets turned on? That's when the risk is actualised.

Also, when they say "risk" - risk of what? Bugs and security incidents? What about other risks: future rework, slowdown of development, obfuscation of bugs, abstractions that will end up being made leaky to work etc. Are these all not considered because they are confident Claude can manage all of that?

So many questions

They look at it mostly like a black box. If it works, it doesn't matter if the code underneath is janky.

I've been vibe coding a game and it's so far from a one shot at this stage. A week and a half solid of prompting with multiple agents. Haven't looked at a line of code, but been iterating, playing and refining constantly. In my mind there's no chance anyone else could get the same result without pointing an agent at my game and reverse engineering it.

Maybe we need yet another word for this kind of development. It's going to be way more common.

Side note: I feel like I could only get this far with Opus 5.5 level models and tooling (cloud agents). No chance I could get to this point without rolling my sleeves up and helping with the technical side with earlier models, and no chance I could get this far pretty much only using my phone.

I'm basically paying Anthropic for both the experience of building a game with a team of decent engineers (it's been exhilarating), and the game itself. It's been incredibly fun. I would never pay this money for something to one shot it for me. This current level has been such a sweet spot of pretty much every ask being nailed and it still feeling like it's my own creation. Something one shotting it for me would kill most of the fun and feeling of "I did this" ownership.

I'm becoming more and more convinced that a big source of outrage on the internet is caused by people assuming that all other people are a homogenous blob.

It's not that "we" are going from one thing to another. It's that these are two different people, with different ethical boundaries.

Opus 5.5 in my experience outshines Fable 5.1 anyway. May as well have Opus do plan, breakdown and review, and Sonnet implement.

I've been vibe coding a game and running multiple Opus 5.5 in parallel on Claude Code Cloud, 5x Max plan, and I'm yet to hit a session limit too. Not sure when I'd use Sonnet. Though it would be nice to switch back to Pro I guess

I don't get it either. Ditto for visual design capability. It's so far above Opus 5 and yet the announcement mentioned nothing about it.

Agents are out of control by default, especially during a training run, which is why when they are productionised into cloud hosts or even local harnesses they have external guardrails in place

In other words, I have a gun that shoots bullets. It's up to me to use it responsibly and legally.

I've found Sol to be an excellent orchestrator, with Astra the planner and Sol again the implementer.

It's not the techs fault. This person chose to use it this way. They could have also carved out 20 mins at the start of their workday to do the same thing

> something that can beat a turing test w/o sweating

Ok I'll be that guy. It's pretty easy to figure out if you're talking to an LLM now we know it's tics, failure modes, jailbreak techniques etc

> Give me the cold hard truth.

Does this actually work to get better answers, or does it now just say "the cold hard truth" instead of "the honest take"

Where?

> I would expect an ethics team to build frameworks that can help train/eval the model that the company spend millions of dollars and months training is going to be aligned to the ethical stances the company chooses.

Which like any company will be entirely driven by legal constraints and money. Or just money if it's cheaper to break the law for profit and pay fines. There will be no "this is what's good for humanity, economics be damned".

Much like HR isn't to help employees but just the company.

I'm not a fan of Zuckerberg in the least, but one area a super intelligent lawyer would be fine at is being drowned in court filings and paperwork

The bigger problem with his argument IMO is that even with open models, it's still the person or organisation with the most money / access to GPU compute winning. They run the larger model (or collection of models), they can process more tokens through them in the same amount of time etc

I'm all for this and I'm keen to try it. I certainly don't want to take away from sharing another neat use case for learning.

But

> What you get is a beautiful animation that is 100% accurate and free of hallucinations

100% free of hallucinations when you're not an expert that can check it is impossible. LLM hallucinations are an unsolved problem.

Well go on then...

> The beauty of intelligence at this cost (even if it's not SOTA) is that it opens a whole bunch of new use cases. Test failure in CI? Have the bot automatically propose a fix, its cheap enough that you can discard it w/h issues. Test coverage too low? Auto generate tests on CI for every pull-requests! Monitoring server logs, continuous security audits and investigating every received exception now becomes possible.

I don't think this is the win you think it is. It's amazing that this is possible, but it introduces so much human overhead that you can drown in reviews and it can effectively slow you down more than a quick check and fix yourself.

The models need to get a lot more consistent in what they can and can't do before you can automate this stuff and only check the things you know the model isn't good at

You can't do that with tools either. Skills are basically prompts - they're not analogous to tools or MCPs. I'm not sure what your point is

Gary doesn't argue it's hype though. He argues 2 things: other people are getting carried away with the result, and we don't know enough about how it was reached to know where it falls on the impressive scale.

He literally says it's an impressive feat in the second article.

I've got a few of these.

There's one in particular that I use quite often and have for about a year, vibed for myself: it's a chat interface that walks you through processing an emotional or difficult moment, following a process / workflow. Supports Martin Seligman's ABCDE and Byron Katie's "The Work". Two techniques that I found most useful to improve my thinking and responses to difficult situations. You converse with it, and it leads you through the stages of the selected flow. More than a system prompt - it tracks and progresses through the workflow at the right times, and you download a consistent pdf of key details from the "session" at the end for your records.

The thing is, I can't sell it. I don't even think I can open source it. It's mental health (minefield of legal and ethical issues), and would probably breach copyright, trademark etc law.

Yet it's very useful to me. I guess it's the equivalent of making a system to do these things at home, like prompt cards or key points taken from the books, with a well formatted note taking structure. Except it's way easier because you just chat like you're talking to someone.

I would never have spent time building this. But now it's so cheap and easy to do.

Are they in 2026? I haven't had an issue with json and LLMs in a long while

IMO a much better test would be designs that aren't AI to begin with. Much more useful to see how well a model can html an image design without slopping it up

> Only an encrypted blind relay to allow for shared editing. The relay doesn't see any of the data.

Would love to know more about how this works then? Is it more or less encrypted P2P?

Is this a quote from a book? Beautifully written

When did that happen with Codex? I thought that was a Claude Code thing

It's not about figuring out if it's LLM written though. The style is hard to read and annoying. With the kind of sentences GP was talking about it's actually harder to get the substance.

Curious whether you were just bare asking it questions, or whether you provided it with lessons one by one with instruction that the lesson is the baseline truth etc

This has been the case since the early days. Aider had a bunch of code to be very forgiving with formatting of tool calls (file editing in particular at first). It's just the nature of the beast. It surprises me that Pi doesn't have a lot of this kind of stuff built in too