So you were forced to downgrade to opus because you dared to challenge the output of fable?

They are the only one crying out loud about how dangerous their models are and are presumably also training their models heavily to be "safe". And through that training itself, the model learns about the other side - how are you going to teach a model to be safe, without teaching it what's not safe?

Kung Fu Panda opening scene anyone? One often meet his fate on the path that he takes to avoid it - Master Oogway.

git operate on the filesystem level, the unix behavior is just getting buried. You cannot rewrite git into a linkable library and decide it's now not unix. It's entire behavior is unix, which is why it's awesome.

Agree with first half of this sentence, we should all have fun with experiments.

> It was never based on a linkable and reentrant library, but instead on a "Unix" philosophy of chaining together simpler commands, which means that it's difficult to use it in long running processes without fork/exec overhead for everything.

Ahhh now we have philosophical disagreement in the only place in the entire article that says "why". Unix is a feature, it's arguably more important in current time: https://aperocky.com/blog/post.html?slug=unix-philosophy-age...

The first item on the article, the first thing it showed, was wrong though.

It is 100% faster to go from London to New York in 1881 than Volgagrad. Or any of the Russian hinterland colored green or Turkey or Egypt.

It's getting to a point that it's offputting, and the next step would be to put it into "untrusted" bucket. Opus 4.7 already burned their credibility once, 2 more strikes remain.

But at the same time, it's quite funny because they seem high on their own supply. The recent communiques from claude do not pass objectivity check.

And if Opus 4.6 -> Opus 4.7 -> Opus 4.8 is anything to go by, not sure if there are any value to their "acceleration"

While I don't necessarily disagree with their vision but if implemented like "Copilot for Windows" I don't see me or anyone wanting to go anywhere near it.

Apple being slow is just fine, at least they didn't launch "Copilot for Mac".

Sometimes the lack of certain feature is the feature.

And in that case, a folding phone is huge! Having played with one that my parent use, it's such an upgrade for reading/scrolling experience. When we all are spending so much time on the phone (that's a separate discussion, but it is the reality).

Oh the smell! It's so obvious.

I wonder why though, why does every single AI write like this? There are barely any variance and everything looks exactly the same. Youtube, blogs, linkedin, it is so obvious that everyone is using the same thing, is this even model specific?

I've never been a fan of AI polishing my writings, but now I wouldn't even get it grammar checked. All of my writing that I expect people to read, particularly philosophy and rationale, are one shot stuff that came out of keyboard like this one.

We don't need to know the entire knowledge base of mankind to want or know what to do next. It points to an entirely separate architecture than LLM.

This is giving too much credit to LLM. I think LLMs are great and it is incredibly useful both in personal and professional settings. However, it exist on a separate plane than human workers in the tools category.

Sooner or later, people will find out that LLMs only overlaps with existing human hierarchy (e.g. junior dev X%, senior dev Y%, etc), but almost never 100%. If it was 100% to a certain position, you are probably using the humans wrong to begin with there - since humans have one of the most priced thing that I don't see an single ounce out of LLMs: initiative

How is that true? I've been using Opus on an industry scale over last 6 months and this is just not real.

It has consistently with a certain percentage of chance each time (and no claude.md and skills do not stop it fully):

* Suggested to remove tests to allow for things to pass

* Suggested remove an error so that things can be "unblocked"

* Suggested to use a second path when the original path ran into problem instead of making the original path accomodate for that possibility.

* Suggested or silently added "features" or "guardrail" that I don't want.

* Can be left unsupervised only if given a goal that it can verify against itself. Without such clear goal (e.g. this test in the integration environment must be fixed), it flounders.

I'm not using just the native harness (e.g. CC) either, with additional, customized harness, the behavior improves somewhat but are still fundamentally constrained and cannot really be trusted without verification.

See my methodology (100% handwritten): https://aperocky.com/blog/post.html?slug=agentic-development....

Being a heavy user I think I've ran into every single hallucination that the model can do over development release and operations. I am still a heavy user but there are a lot of value in recognizing where exactly LLM's limit is and work around that.