sebra

At least Anthropic have a max subscription for corporate. Codex is only pay-as-you-go pricing beyond the base plan. Hence I'm stuck with Opus for work for the foreseeable future.

The tweet misses the conclusion from the paper that handcrafted AGENTS.md might help. To me its no surprise that 100% vibed AGENTS.md are unproductive. Not reviewing your design docs is probably even worse than not reviewing your code? I've seen some AI-generated agents.md which were just plain wrong. No surprise agents perform worse after reading those.

I use AGENTS.md to make sure my agents loop effectively (tests, quality, etc). Not to describe the code / architecture.

It's because that price point is for individuals not for companies. So my company can't pay for the $100 plan unlike with Claude. Only pay-as-you go pricing is available for companies beyond the $29 plan which runs out for me in 2/5 hours. And pay-as-you-go is insanely expensive.

I'm working on a large (at least 300k+ loc) Django code base right now and we have 32 direct dependencies. Mostly stuff like lxml, pillow and pandas. It's very easy to use all the nice Django libs out there but you don't have to.

Thanks Dylan. Turns out my colleague actually had a teams call with you yesterday and the issue was confirmed and prioritised on your end.

You have a great product. Looking forward to get back to using it!

I've tried Greptile and it's pretty much pure noise. I ran it for 3 PRs and then gave up. Here are three examples of things it wasted my time on in those 3 PRs:

* Suggested to silence exception instead of crash and burn for "style" (the potential exception was handled earlier in code but it did not manage to catch that context). When I commented that silencing the exception could lead to uncaught bugs it replies "You're absolutely right, remove the try-catch" which I of course never added * Us using python 3.14 is a logic error as "python 3.14 does not exist yet" * "Review the async/await patterns Heavy use of async in model validation might indicate these should be application services instead." whatever this vague sentence means. Not sure if it is suggesting us changing the design pattern used in our entire code base.

Also the "confidence" score added to each PR being 4/5 or something due to these irrelevant comments was a really annoying feature IMO. In general AI tools giving a rating when they're wrong feels like a big productivity loss as then the human reviewer will see that number and think something is wrong with the PR.

--

Before this we were running Coderabbit which worked really well and caught a lot of bugs / implementation gotchas. It also had "learnings" which it referenced frequently so it seems like it actually did not repeat commenting on intentional things in our code base. With Coderabbit I found myself wanting to read the low confidence comments as well since they were often useful (so too quiet instead of too noisy). Unfortunately our entire Coderabbit integration just stopped working one day and since then we've been in a long back and forth with their support.

--

I'm not sure what the secret sauce is but it feels like Greptile was GPT 3.5-tier and Coderabbit was Sonnet 4.5-tier.

"The browser" -> "A browser" and this is not an issue

I have the same issue. I think it's because I'm adblocking because if I try in chrome with no adblocker it loads the ads instantly.

But eh either 5s of black screen or 60s of ads. I tried watching a 15 min yt video without adblock and it had 5 ad breaks with some unskippable ads.

Riksbanken have been pushing for cash payments too. Personally I think its too little too late. The culture in Sweden has already changed to purely digital

https://www.riksbank.se/sv/press-och-publicerat/nyheter-och-...

Sweden has also done multiple pilots of a digital currency pressed by the state. This might be an interesting alternative to not give up control of our currency and privacy to banks and cc companies. Also supposed to work offline. https://www.riksbank.se/globalassets/media/rapporter/e-krona...

That is just not true. To quote the Swedish riksbank. "The Swedish payment market is almost entirely digital"

https://www.riksbank.se/en-gb/payments--cash/payments-in-swe...

That used to be semi-common for smaller transactions in Sweden but was made illegal. Not sure why, probably to fight tax avoidance.

At this point the cost of handling cash is way higher than handling cards and as no one in Sweden ever uses cash its no longer relevant at all anyway. Now many (maybe even most?) dont accept cash to avoid the cost of handling cash instead.

There are numerous things still missing in terms of async support. Most notably for me is DB transaction support which leads to most non-safe endpoints running on the shared sync_to_async thread and me having to separate my code into one async function calling another sync function wrapped in sync_to_async.

In fact if you look at the source there is a lot of async methods in the framework itself which just straight up calls sync_to_async e.g. caching. This doesn't matter as much as hopefully it will get added proper async eventually. But I think believing your requests wont block just because you're using async is a bit naive at this point in Django and the async implementation has been going for years.

Not to mention that the majority of third party libraries lack support for async so you'll probably have to write your own wrappers for e.g. middleware.

I think one reason for the eReader market not being big is that they're so good and sustainable. I bought my Sony PRS-T2 in 2012 and am still using it to this day. It has battery life for weeks, storage space for 100+ books and works just as well as when I bought it. It's really hard for me to motivate buying a new one when the only interesting "new" tech is backlight and I guess it's the same for most eReader owners.

The ~90e I paid for it back in 2012 was for sure good value!

I added this to personal instructions to make it less annoying:

• No compliments, flattery, or emotional rapport. • Focus on clear reasoning and evidence. • Be critical of users assumptions when needed. • Ask follow-up questions only when essential for accuracy.

However, I'm kinda concerned with crippling it by adding custom prompts. It's kinda hard to know how to use AI efficiently. But the glazing and random follow-up questions feel more like a result of some A/B testing UX-research rather than improving the results of the model.

Apples only delivery choice in Sweden is UPS which is notorious for messing up deliveries here. I ordered a MacBook and the delivery is supposed to be hand over with signature required. The UPS guy left it outside my apartment door in the stairwell in the morning. I was lucky it was still there when I got home from work. Apparently I signed that delivery (the UPS guy probably signed it himself...)

Nice one! Had this problem last time we ran a tournament.

I also did some constraint programming to solve my poker problems. We play mostly cash games so I did a MiniZinc model for computing the least amount of transactions after the game: https://github.com/SRautila/poker-home-game-calculator

It is very much maintained and got it's 1.0 release not long ago. Sadly there is a single guy doing all the work for Ninja so the tempo of releases varies. I also think there is quite a way to the stability of DRF and DRF's ecosystem. If you want permissions and throttling for example you'll have to use django-ninja-extra which is pretty much "DRF but its Ninja".

For me personally I think the micro approach of Ninja / FastAPI is at odds with what I want out of DRF. I just want to make my crud stuff and not worry about implementing e.g. throttling, etc, on my own.

As a long time Django and DRF user I'm really happy this release finally got out. If you look at the PRs being released some of them are years old. It's true that DRF is a mature and feature-complete framework but Django is still evolving slowly and DRF must keep up with that at the very minimum. Big thanks to the maintainers for getting it out!

Here are some of my hilights from this relase:

* Default on model gets sent to API docs

* Orderedict replaced by plain dicts everywhere - plain dicts are ordered in python since 3.6 so this is a welcome simplification

* Automatic support for UniqueConstraints in ModelSerializers - this is one of the places where DRF were lagging behind. I found myself using the deprecated unique_together just to not bother with writing validators on all my serializers

* There is a new router supporting path converters instead of regexp - Looking forward to trying this out! Also long overdue IMO as this came to Django in 2017 :)

For me it feels like people have always been over-engineering dependency management where the practical issues from not doing it are pretty much non-existent.

My approach is to just use Docker, no virtualenvs. I get that you might run into the multiple interpreters issue in theory but across multiple projects in the past 5 years I haven't seen that. Also, this might no longer be true but avoid using Alpine. If you're deploying Django there is no reason to optimize image size and Alpine has a lot of things which are missing (i.e. at least a couple of years ago, wheels where not supported leading very slow build times).

I only do a single requirements.txt. Anything which makes your prod and local environment differ is a bad thing in my opinion. Fine black might make my image a couple of mbs larger but why would it matter? On the other hand attempting to figure out why something which works on my machine does not work on prod is always a nightmare.

Setting requirements as a range in requirements.txt allows me to automatically get bugfixes without spending time on it (e.g. django>=4.2.3,<4.2.99 django-ninja>=1.0.1,<1.0.99) Again, I might have run into 1-2 issues over the past couple of years from this and I've saved a lot of time.

Getting a project running locally should not take more than 1 minute (a couple of .env vars + docker-compose up -d should be enough).

The biggest practical issue in dependency management in python is dependencies not pinning their dependencies correctly.

Yeah, pills. I'm a Swede so you'll probably need to look for a different brand if you're in the US. Here is the ones I buy: "Valerina Forte" https://www.fass.se/LIF/product?nplId=20090224000447&userTyp...

My tactic for falling asleep just about anywhere is over-ear headphones (QC35) and a sleeping mask.

Sleeping slightly on your side is no problem with QC35 and if the noise around you is low enough you don't even need white noise. The battery lasts a couple of nights too (esp with no white noise on).

I've tried doing the same with Sonys over-ear but they make a loud noise when I move my head so they don't work for me at all. AirPods Pro work in a pinch but the battery runs out and my ears start hurting.

Another thing which I find mildy helpful which wasn't mentioned here is Valerian. If my lack of sleep is stress-related Valerian works sometimes for calming. If my lack of sleep is due to bad routine / off schedule Melatonin works very well but if I'm stressed it does not work at all and leaves me groggy in the morning.