> Another pattern I’m noticing is strong advocacy for Opus

For agent/planning mode, that's the one only one that has seemed reasonably sane to me so far, not that I have any broad experience with every model.

Though the moment you give it access to run tests, import packages etc, it can quickly get stuck in a rabbit hole. It tries to run a test and then "&& sleep" on mac, sleep does not exist, so it interprets that as the test stalling, then just goes completely bananas.

It really lacks the "ok I'm a bit stuck, can you help me out a bit here?" prompt. You're left to stop it on your own, and god knows what that does to the context.

Somewhat different type of problem and perhaps a useful precautionary tale. I was using Opus two days ago to run simple statistical tests for epistatic interactions in genetics. I built a project folder with key papers and data for the analysis. Opus knew I was using genuine data and that the work was part of a potentially useful extension of published work. Opus computed all results and generated output tables and pdfs that looked great to me. Results were a firm negative across all tests.

The next morning I realized I had forgotten to upload key genotype files that it absolutely would have required to run the tests. I asked Opus how it had generated the tables and graphs. Answer: “I confabulated the genotype data I needed.” Ouch, dangerous as a table saw.

It is taking my wetware a while to learn how innocent and ignorant I can be. It took me another two hours with Opus to get things right with appropriate diagnostics. I’ll need to validate results myself in JMP. Lessons to learn AND remember.

> It tries to run a test and then "&& sleep" on mac, sleep does not exist

  > type sleep
  > sleep is /bin/sleep

What’s going on on your computer?

Edit: added quote

Right you are.. Perhaps I recall incorrectly and it was a different command. I did try it, and it did not exist. Odd.

You are probably thinking of `timeout`.

I actually tried GPT 4.1 for the first time a few hours ago(1).

I spent about half an hour trying to coax it in "plan mode" in IntelliJ, and it kept spitting out these generic ideas of what it was going to do, not really planning at all.

And when I asked it to execute the plan.. it just created some generic DTO and said "now all that remains is <the entire plan>".

Absolutely worst experience with an AI agent so far, not to say that my overall experience has been terrific.

1) Our plan for Claude Opus 4.5 "ran out" or something.

I've run into something akin to `const int EIGHT = 7`.

Courtesy of TCS.

Just your ISP, their ISP, your hosting provider (if applicable) and the browser vendor.

Adding in an optional HTTPS there would not greatly increase the amount of intermediaries, though I by no means argue that it matters.

It brings in one central intermediary used by most of the internet, converting a decentralised system to centralised.

With all the hassle a government contract can bring, it's just not worth it for anything lower.

> Where do you look first?

Git commit will generally explain why it was done. The task it references may or may not explain the decision process that lead to it. Usually not.

It's rarely related to code, more often a business decision due to some obscure reason/desire which may or may not provide any actual value.

> Git commit will generally explain why it was done.

Sometimes, not generally. A lot of people are bad at commit messages, and commits migrated from older tools may be unusably terse because those tools didn't support multi-line commit messages well.

> But I am not a storage/backend engineer, so maybe I don't understand the target use of Redis.

We use it to broadcast messages across horizontally scaled services.

Works fine, probably a better tool out there for the job with better delivery guarantees, but the decision was taken many years ago, and no point in changing something that just works.

It's also language agnostic, which really helps.

We use ElasticCache (Valkey i suppose), so most of the articles points are moot for our use.

Were we to implement it from scratch today, we might look for better delivery guarantees, or we might just use what we already know works.

How odd.. I have this on my iPhone, but to my recollection the mac has never not once asked me to enable any kind of cloud stuff or sell me storage.

A whole extension? Seems like something any custom-css/custom-js plugin can handle. Stylus, or those monkey extensions.

.hnuser attr=href=?user?id=rd

.parent().parent().hide()

Though no idea if such a plugin exists for Safari.

My main peeve with the Apple TV (device) is that the home button keeps sending me into Apple TV (App) instead of to the main screen.

I have to click it twice to get back to the home screen.

As is also commented, within the device settings you change the behaviour to be a home button.

You should also be able to hold the ‘menu’ or ‘<‘ button, depending on which remote you have, to directly go to the home page

Just dig into the menu, that's an option if I remember well.