One more article praising Codex CLI over Claude Code. Decided to give it a try this morning.

A simple task that would have taken literally no more than 2 minutes in Claude Code is, as of now, 9m+ and still "inspecting specific directory", with an ever increasing list of read files, not a single line of code written.

I might be holding it wrong.

What I understand is Codex takes more time to gather context to make the relevant changes; with more context it may give a more precise response than Claude Code.

With Claude Code, I can 'tune' the prompt by feeling how much context the model needs to perform it's task. I can mention more files or tell it to read more code as needed.

With one hour of experience of Codex CLI, every single prompt - even the most simple ones - are 5+ minutes of investigation before anything gets done. Unbearable and totally unnecessary.

It has the same context. It does not take that long to ingest a bunch of files. OpenAI is just not offering the same level of performance, probably due to oversubscription.

Same here. Even with Opus in Claude Code I'm getting terrible results, sometimes feeling we went back to the GPT 3.5 eon. And it seems they are implementing heavily token-saving measures: the model does not read context anymore unless you force it to, making up method calls as it goes.

The simplest thing I frequently ask of regular Claude (not Code) in the desktop app:

"Use your web search tool to find me the go-to component for doing xyz in $language $framework. Always link the GitHub repo in your response."

Previously Sonnet 4 would return a good answer to this at least 80% of the time.

Now even Opus 4.1 with extended thinking frequently ignores my ask for it to use the search tool, which allows it to hallucinate a component in a library. Or maybe an entire repo.

It's gone backwards severely.

(If someone from Anthropic sees this, feel free to reach out for chat IDs/share links. I have dozens.)

Glad I'm not crazy. I actually noticed both 4 models are just garbage. I started running my prompts through those, and Sonnet 3.7 comparing the results. Sonnet 3.7 is way better at everything.

You're not crazy, and this isn't new for Anthropic. Something is off with Opus4.1, I actually saw it make 2 "typos" last week (I've never seen a model like this make a dumb "typo" before). And it's missing details that it understood last month (can easily test this if you have some chats in OpenWebUI or LibreChat, just go in and hit regenerate).

Sonnet 3.5 did this last year a few times, it'd have days where it wasn't working properly, and sure enough, I'd jump online and see "Claude's been lobotomized again".

They also experiment with injecting hidden system prompts from time to time. Eg. if you ask for a story about some IP, it'll interrupt your prompt and remind the model not to infringe copyright. (We could see this via API with prompt engineering, adding a "!repeat" "debug prompt" that revealed it, though they seem to have patched that now.

> I started running my prompts through those, and Sonnet 3.7 comparing the results. Sonnet 3.7 is way better at everything.

Same here. And on API, the old Opus 3 is also unaffected (though that model is too old for coding).

How is this better/faster than typing "xyz language framework site://github.com" into Kagi

IDK about you but I find it faster to type a few keywords and click the first result than to wait for "extended thinking" to warm up a cup of hot water only to ignore "your ask" (it's a "request," not an "ask," unless you're talking to a Product Manager with corporate brain damage) to search and then outputs bullshit.

I can only assume after you waste $0.10 asking Claude and reading the bullshit, you use normal search.

Truly revolutionary rechnology

I’m running into this as well.

Might be Claude optimizing for general use cases compared to code and that affecting the code side?

Feels strange, because Claude api isn’t the same as the web tool so I didn’t expect Claude code to be the same.

It might be a case of having to learn to read Claude best practice docs and keep up with them. Normally I’d have Claude read them itself and update an approach to use. Not sure that works as well anymore.

The article has this gist:

  user.log_entries.delete_all
  user.log_entries.create!(message: "User account reset")
  user.log_entries #=> [], will be empty until reloaded

This is false. At least not in Rails 7+ (haven't tested earlier), user.log_entries will return exactly what you'd expect (one instance of LogEntry).

OP here - for what it's worth, this was the case on our application which was Rails 8. Some other gem or workflow may have been involved, but is highly unlikely.

What is the target audience for these bi-anual shots? Only populations at high risk or are we supposed to start vaccinating everyone that is sexually active?

Btw, nothing on the article about potential side effects.

>What is the target audience for these bi-annual shots?

In the US, there are certain patients who are at high risk for HIV infection. They are men who have sex with men, intravenous drug users, and people who have sex for money or housing.

In Southern Africa, young women experience some of the highest incidence rates of HIV infection in the world [0], so that would be the high risk population there.

In terms of side effects, there are practically none for the once-every-two-months drug Apretude, which is prescribed in the US for the high risk population I mentioned. They are mostly around the physical injection itself/

[0]https://pmc.ncbi.nlm.nih.gov/articles/PMC4430426/

That would be up to individuals or health departments, who decide what risk is high enough. The risk for non-promiscuous people in 'western' countries is so low, that I don't see any country giving this to everybody.

This is not a vaccine, BTW, and it needs to be given every 6 months.

The previous title stated Kiro as being "Amazon's Cursor clone", which I agree was not adequate.

My suspicions were right that the name had something to do with amazon because I went into this thread thinking about Amazon's unique position in this market.

"one basic thing like handling file uploads" - say no more.

Actually, the article isn't even about handling file uploads - it's about deliberately creating a modular admin panel for dealing with file uploads.

It's not modularity for "framework-y" sake, but to easily deploy that admin panel in other applications with literally a one-liner.

I couldn't have written this comment better myself. Thank you this is exactly the point

Rails is not only alive and well, but actually booming.

There's a new data point: Ruby is #5 most used and #3 most loved language as per the recent Pragmatic Engineer survey! https://newsletter.pragmaticengineer.com/p/the-pragmatic-eng...

> Rails is not only alive and well, but actually booming.

Do you have any references that validate this?

Rails 'booming' on a 3 year time scale wouldn't surprise me, but would on a 10 year scale.

We're experiencing a global peak of Ruby meetups (globally). About 800-900 meetups in the last 12 months as per https://rubyconferences.org/meetups/ I'm hosting probably the largest Ruby meetup in San Francisco, see https://lu.ma/sfruby

Rails is not at the peak of visibility (like it was in 2008-2014), it is not a "default stack for new products" but here's what we see: Rails startup just did a large IPO (Chime), another Ruby startup filed for IPO (Figma) Rails startup just posted a record ARR growth (bolt.new)

Lots of startups and lots of success stories. See https://evilmartians.com/events/startups-on-rails-in-past-pr...

Again, not the #1 or "default" choice, which is probably a good thing, because we are past the hype+disappointment cycle and on the pragmatic side of things.

It has worked perfectly for me every time, and it’s such a great feature.

Great writeup. I'd love to know more about how the Supervisor works, and how it. "fork[s] a separate process for each supervised worker/dispatcher/scheduler".

In a Rails app served with Puma, I've always had a hard time understanding what would be the canonical way for having a loop doing some periodic work.

I know Puma has plugin support but I don't see much documentation there.

Forking a process / threads is something that we're used having Rails / Puma take care for us.

Pressed for time and without having time to deep dive, we ended up settling with sidekiq-cron, and it's been serving us so nicely.

Under the hood, it uses good ol' fork and keeps track of the generated process IDs.

It's surprisingly simple. You can check out the relevant source here: https://github.com/rails/solid_queue/blob/main/lib%2Fsolid_q...

I'm trying to understand why my Rails application constantly logs me out in my iPhone/Chrome.

The same web app stays logged in forever in my mac and I access both of them with the same time intervals.