Been very skeptical for awhile but decided to try it cause it was like $30 for 3 months or something. I cancelled my Claude subscription (still have codex), but been pretty impressed with the grok CLI. Nice TUI and seems intelligent thus far.
Really? I've used all of the models extensively and Grok doesn't even compare to the others. I can ask for a big task and it will say "Done!" like 3 minutes in, but it will have done just the least amount of work possible. I also notice "muskisms" leaking back in the results like "I'm not roasting your code". Completely unusable for me and not comparable to the other model providers.
That is interesting, I've never been able to get it to successfully complete big tasks to any level of quality. For me the Anthropic models are by far the best at that, but the newer OpenAI models are starting to approach that quality. Grok always seemed like it was designed to write nasty tweets and the code quality I got from it matched that.
I think it's good for mid-sized tasks. It seems quick too. It just doesn't do as good of a job with large changes or architectural decisions as Opus imo.
I don't remember the version exactly but maybe June/July timeframe? I tried it on maybe a half dozen projects with different types of asks as I was comparing models for my company at the time.
Grok 4.5 came out in mid July and is a huge leap forward. Not quite as good as Opus 5 for code in my experience, but better and more succinct for understanding human documents.
I’ve been obsessed with everything durable lately and this is good timing as electric just got acquired so the state of their durable streams project is unknown.
Have you looked into the semantics of their like StreamDB stuff ? Pretty interesting
Also there is this that was built on top of it. Sounds somewhat similar goal as yours but I could be off. Need to explore more
https://ursula.tonbo.io/
On the same boat, and honestly, it’s not getting the attention it deserves. Given Databricks acquired ElectricSQL primarily for PGlite, the Durable Streams project is likely going to be abandoned unless new maintainers step in.
I did, in fact, initially write PicoMQ with OpenRaft, similar to Ursala, but I really wanted the operational complexity to be minimal and the nodes to be stateless (at least for most use cases), Pico uses SQL database as a metadata command log, inspired by RisingWave.
But Ursala would, without a doubt, have better durability ACK latency, as it wouldn’t have to wait for an ACK from S3. That said, I do plan on extending disk/EBS-staged WAL to hit similar low-latency durability ACK numbers. But again, most use cases don’t need single-digit-millisecond latency for ACKs.
I was planning to use electric cloud for durable streams recently and found out they are winding it down post acquisition.
Unfortunate timing and self hosting isn't complex or anything but still as you said, durable streams as a project is most likely going to be abandoned.
True, there are also a lot of open PRs and issues. I'm surprised no other developers or orgs are stepping in to keep the project afloat. No wonder the Apache Way goes a long way! Either way, their approach of building around an open-protocol was a good decision.
If you'd like to consider using PicoMQ, I have examples to deploy on Fly.io and AWS. ursula.tonbo.io is also a good option to try.
Your welcome! And feel free to ask any questions as try out PicoMQ or raise on Github issues. The disk-staged WAL is currently tracked here: https://github.com/PicoMQ/picomq/issues/13, I'm planning to ship it as an optional add-on.
> They don't want 100 apps that do the exact same thing.
I read it as the "insane" part parent is pointing at.
It's nothing new, has been going on basically since the existence of the App store and Apple has explicitly built their whole business to put themselves as the arbiter of who gets to have their app on people's phones.
Still it's healthy that from times to time we stop and shout "that whole situation is insane" (short of finding a way to actually do something about it)
Look up "wireless printing" in the App Store sometime. As best I can tell, one or two actors have spammed the entire category with dozens, perhaps hundreds, of subscription-heavy repackagings of CUPS drivers as iOS apps. They all have very similar blue line-art icons of a printer, similar preview images with similar typography, and are all crammed full of subscription options.
They are probably making a killing on people who forgot about or can't figure out how to cancel the $4.99/week subscription on the top 20-30 of these apps.
All this while of course the one app you've been working on for a year will be held up with multiple rounds of rejections weeks apart. For all the good Cook has done in his 15 years at Apple, the App Store will be the one real stain on his legacy, and I hope Ternus is as acutely cognizant of that as the developer community is.
> the App Store will be the one real stain on his legacy
Well, and the Apple Car. And the Butterfly Keyboard and that horrible i9 16" MBP. Plus the Airpower, and the Vision Pro, and he cancelled the entire Mac Pro lineup too. Also the $1,000 VESA monitor mount and goofy desktop wheels, and we should probably also mention his meetings with Donald Trump and eventual White House dinner with Bin Salman. Tim also failed to legally deter NSO Group, held a grudge against Nvidia during a $4 trillion ARM/CUDA datacenter boom, greenlit Liquid Glass, proposed Client-Side Scanning and fought dirty against organic and reasonable EU regulations.
But besides that, yes, the pitiful state of the App Store will be remembered as his true strategic slip-up.
How is the Apple Car a stain on his legacy? They worked on something, and decided not to do it. Who cares? Apple’s management of the App Store has ruined mobile apps. Nobody gives a shit about the car.
You're right, at Apple's scale we should forgive Tim Cook for wasting human talent and capital on failed megaprojects. It's not like those resources could have been diverted to address the other problems with Apple's services or hardware products, who cares?
(b) Don’t submit apps that are indistinguishable from what's already widely available. Opportunistically creating variants of existing app categories or popular apps degrades App Store discovery, reduces overall app quality, and harms both users and developers. Certain kinds of apps, such as dating, flashlight, sound effects, wallpaper, simple timers, and fortune telling, are well established on the App Store and we will not accept new submissions unless they offer a meaningfully different or improved experience. We may remove these apps from the App Store going forward if they are not updated, improved, or do not attract customers. Other kinds of apps, such as drinking games, Kama Sutra, fart, and burp apps, are mediocre, low-quality, or low-effort and do not add value to the App Store. Repeated submissions of this kind may lead to removal from the Apple Developer Program.
This is such a dumb policy, and it's absolutely not even being followed.
I submitted a timer app this year and it got approved. It's literally just a slightly more feature-rich timer.
I made this as a "my first app" type of experience. Never at any point was the quality of my app questioned, and I'm the first person who will tell you that it's not very good.
The other day in warp I literally couldn't run `ls` because it kept interpreting it as a AI command. I still love warp, but some of the stuff is crazy.
Warp team member here. If you have natural language detection on, you can turn this off in Settings > Agents > Warp Agent > Input by disabling "Autodetect agent prompts in terminal input." Still, I wouldn't expect `ls` to be classified as an AI command... I've seen this when auto-detection is disabled and you're in an agent conversation unexpectedly. Maybe that's the case?
FWIW I use ZSH in Warp daily and never had this problem with ls. Although I have experienced the the agent prediction doing a false positive auto-switch thing a few times.
Using Figma to make app store screenshots was always my least favorite part of launching an app.
Since the first image models started coming out i've been testing each on making app store screenshots, hoping one would be able to handle it.
Finally, with OpenAIs gpt image 2, it was finally possible!
I made an open source library that gained some traction but not everyone had gpt image 2 API Keys (you need to be verified corp) so I decided to make it as a MCP that you can add to any agent.
It's very simple to use. When you are done coding it up, add the MCP and tell it to make screenshots. It will pull in reference image, screenshots and your theme and research the space then propose some ideas that you can approve/refine.
I also handle revisions and translations as well as app store copy.
Would love any feedback and if you run out of the free three screenshots but not ready to pay feel free to message the chat I can give you some more credits for feedback!
reply