murkt

Can this be a Siri-like core? Set me a timer, tell me what’s the weather, etc. Here is transcribed text and available list of tools for the model to call, and voice the output.

The last one is about involving less people. You don't have to read it as "shut up and keep your thoughts for yourself". I read it more like "Do we really need to have six people working on this feature/present in this call?"

You can make the feature with one colleague, or you can call in five more people to weigh in and do their parts of the work.

If you involve five more, the result could be better in theory, but it will certainly take MUCH more time because of communication overhead.

What I meant is that only sometimes I am faster than Claude with debugging. When it's a standalone problem, a report in Sentry, and I just know immediately where I need to go to fix it. Then it's faster to do myself, than telling Claude what's the problem and where to look and wait.

Bugs happen during feature development, as you say, but then Claude is in the context, and I don't need to tell it where to go, it sees the bug with failing tests, or smth similar.

BTW. One thing that helps my Claude with debugging harder problems is that I tell it to apply scientific method to debugging. Generate hypotheses, gather pros/cons evidence, write to a journal file debug-<problem>.md, design minimal experiments to debunk hypotheses.

You can add that as a skill, and sometimes it will pick it up automatically, but it works wonders just as a single sentence in the input.

Sometimes debuggind is faster indeed, and making small very focused changes too.

But during feature development? Not possible. And I consider myself a very fast developer

A fee years ago, I woke up in the middle of the night with a very cool sounding riff playing in my head for a song that I was thinking about at that time. I am not a musician and that would be my first, if I would recruit enough help.

I made noises with my mouth, and it still sounded cool. Instead of recording those noises into any recording on my phone, I went back to sleep and couldn’t remember it the next morning :(

Azure is worse. These series of posts were posted here not that long ago https://isolveproblems.substack.com/p/how-microsoft-vaporize...

Autonomous Thriving Hroup?

DeepSeek pelicans are the angriest pelicans I’ve seen so far.

Frankly, that usually comes from orgs that deal with the real world. 50k generic requests per day is nothing. 50k orders per day for a small e-commerce company can be pretty overwhelming.

It’s becoming laughable when people use it to boast about microservices or something :)

When I see rps in development context, I immediately know it is requests per second. x/s on the other hand… 3x/s. kx/s looks like a physics formula to me. Some spring action? K is for coefficient, x is displacement.

> writing “90 kBq” is a lot more convenient than “ninety thousand requests per second” and “90,000 requests/s”

I once made a joke during the talk that MongoDB is better than Postgres in two ways, and one of those ways is that it’s faster to say “Mongo” than “Post-gres-Qu-eL”.

Same vibe here. 90krps is not that longer than 90kBq.

With requests per minute, rpm: engine in my car revs up to 9000 requests per minute!

It’s sometimes funny to see some marketing posts like “we built our infrastructure to handle UNREAL load during the event, 100 million of requests during the day.” Which is just a bit more than 1100 rps.

In my experience, your Case 2 plays out a bit differently. "Just inherit and go" and in many cases you end up with more lines of code in total than doing the same thing in my own function with some kind of helper. Even in the dead standard thing, like displaying a list of objects with pagination. But now I don't own the flow!

Any kind of customization and I need to go jump through the hoops, I need to go look at the code what exactly happens there. But this class inherits a couple other classes, and I need to go read them as well. What for? Grug not want read seven basic multiple-inherited class just to display a list of objects.

So I disagree that it's a no-brainer. It's a no-no brainer for me.

As for writing the libraries, I have the same problems with all libraries that provide class-based API, where I need to inherit from libraries' classes to do my thing.

I like my code to be stupid and linear, to own the flow, so I can read the code and understand what happens there. Same is true for agents!

I am also willing to accept some LoC penalty for my approach. But it's shorter in practice, so win-win for me.

I was using Django since 2006 up to ~2012, and then again touched in 2014-2015. Never again.

Class-based views were a problem when they were introduced in Django, and they’re still a problem.

Especially for the so-called AI-ready framework. Because of indirection, you either have to go read all the basic classes, or read documentation three times over. Instead of just reading the self-contained view function itself, once.

Especially true for an agent, it will have to go read the new framework’s docs and source over and over and over…

Remember Sonnet 3.5 and 3.7? They were happy to throw abstraction on top of abstraction on top of abstraction. Still a lot of people have “do not over-engineer, do not design for the future” and similar stuff in their CLAUDE.md files.

So I think the system prompt just pushes it way too hard to “simple” direction. At least for some people. I was doing a small change in one of my projects today, and I was quite happy with “keep it stupid and hacky” approach there.

And in the other project I am like “NO! WORK A LOT! DO YOUR BEST! BE HAPPY TO WORK HARD!”

So it depends.

Was there a change in Claude Code system prompt at that time that nudges Claude into simplistic thinking?

Here is a gist that tries to patch the system prompt to make Claude behave better https://gist.github.com/roman01la/483d1db15043018096ac3babf5...

I haven’t personally tried it yet. I do certainly battle Claude quite a lot with “no I don’t want quick-n-easy wrong solution just because it’s two lines of code, I want best solution in the long run”.

If the system prompt indeed prefers laziness in 5:1 ratio, that explains a lot.

I will submit /bug in a few next conversations, when it occurs next.

With 9M params it just repeats the joke from a training dataset.

Long way ahead still:

> Given its key importance for the EU's competitiveness, the Commission is calling on the European Parliament and the Council to reach an agreement on the EU Inc. proposal by the end of 2026.

Good analogy! Would be interesting to read more details about how you’re getting very high quality outputs

Try asking it for some curves that go in this or that direction. CW, CCW, curves to the left, to the right, etc.

Produces a bunch of crap and it’s really hard to convince it that something needs to be changed. “Yep, I looked at the screenshot, it curves, so it’s okay.”

When it’s a simple single-line query: sure.

When they’re 30 lines apart, because it’s a function that builds a complex query with joins and filters based on some function arguments: not easy.

I don’t really understand how .pyi will give me proper Find usages here. I haven’t used them a lot, though, and just rely on pycharm Find Usages or just rg.

Also, what about foreign keys? Let’s say it’s a filter on user__email__startswith. Are you able to find it when executing Find Usages on User.email field?

Seeing a new library in 2026 that uses Django-style filter syntax is really surprising.

With SQLAlchemy approach I can easily find all usages of a particular column everywhere.

    .filter(Folder.user_id == user_id)

Versus

    .filter(user_id=user_id)

Grepping by user_id will obviously produce hundreds and thousands of matches, probably from dozens of tables.

Starts of sentences are not capitalized, which makes it a bit harder to read. English language prescribes capitalization after a period.

Sounds pretty fun! Do you have any screenshots to show?

How can they alter humanity? What's the difference for humanity since CERN found Higgs particle? In what ways could the potential dark matter particle detection alter humanity?

Yep

Well, when I’m driving in Kyiv, and there is an air raid alert, usually my car navigation starts to derp, and after a few minutes it thinks that it’s suddenly in Lima, Peru.

Not that I mind too much, I know how to get around without navigation.

Maybe they’ve left a lot of clearly AI-generated comments. Or even wrote the text of the reply with AI. It’s usually quite easy to tell.

Zig has not surpassed 1.0 and explicitly strives to remove features, which Java and Rust don’t do anymore. That’s why it feels different.

Java and Rust have surpassed 1.0 version a long time ago, so they don’t remove features left and right on each feature release.

Not that it’s a bad thing. Python removes stuff, and it takes time to upgrade to new versions.