raphh (@raphh) header
raphh (@raphh) profile picture

Product Engineer. iOS/macOS & more. Prev @Immoweb, @SeLoger, @M6 and @Bedrock_Stream

Brussels
Joined December 2008
Photo by raphh (@raphh)Photo by raphh (@raphh)Photo by raphh (@raphh)Photo by raphh (@raphh)Photo by raphh (@raphh)Photo by raphh (@raphh)Photo by raphh (@raphh)Photo by raphh (@raphh)Photo by raphh (@raphh)Photo by raphh (@raphh)
Ant renaming the Max x20 plan to Ultra and more importantly dropping the 5h limit. Let's go!
We’re renaming our Max plans: Max 5x → Max Max 20x → Ultra Max is still $100/month, and Ultra is still $200. If you’re a subscriber, there’s nothing you need to do. We’re also removing the 5-hour limit for verified Ultra accounts, starting today with most existing subscribers. Newer accounts keep a temporary limit until they’re verified, which helps us prevent fraud and abuse. You'll get an email when it's removed. Weekly limits remain unchanged. View our plans here: claude.com/pricing
17
"Take a step back" never disappoints.
13
Another beautiful native iOS app, @Shopify gets it 😍
We rebuilt the @Shopify mobile app for iOS and Android—and with it, shipped the biggest design facelift the app has ever seen. Smoother gestures, more consistent interactions, fluid animations, and haptics all come together in a beautiful new native design system. And there’s more to come. Proud of the team for rebuilding one of Shopify’s largest apps while keeping merchants moving @jonrundle @mustafa01ali @TheJackRead @chrisaalid @RedEffect1 and many more ... 💚
18
"Your job has fundamentally changed. It is no longer to write code, and LLMs are not here to help you write better code faster. Your job is to help the LLM write better code faster." Hell yeah, Andy Yen gets it. Pretty hilarious that the journalist thinks this is somehow an outlandish take lol. More proof that it's still so early.
Replying to @josephfcox
Here is Proton CTO's AI manifesto, that I obtained multiple copies of 404media.co/manifestos-fear-…
38
Over the years I've been doing most of my movie watching at home, but when there's an IMAX screening it's usually my cue to drag my ass back to the theater, and I never regret it. These are such humbling experiences that push cinema to another level. Feeling blessed to be able to appreciate this kind of art and to have an IMAX 70mm theater in my city. So far I've only been going for Nolan movies, since he's obviously the master at it, but I booked my ticket for Dune: Part Three too after seeing that insane 4-5 minute sequence before The Odyssey. Some movies are really meant to be experienced in a theater, and I'll try to honor that more going forward.
1
70
@Kinepolis are you going to have screenings for these too? teapawt.net/dunemovie/status/21155…
For one week only, Dune and Dune: Part Two return to IMAX. Plus witness an exclusive sneak peek of Dune: Part Three. Tickets on sale Friday. #DuneMovie #FilmedForIMAX
17
Replace "AI" with any topic and it's always the same. Most big companies aren't high-trust, high-autonomy, high-ownership environments, so things can't really move fast. It even tends to get slower over time as more people get hired and bureaucracy keeps increasing.
Why big companies are struggling to move faster with AI. 1. Let’s have a meeting to get everyone aligned. 2. Simple solution but we need a PRD before anyone can do anything. 3. Someone uses AI to generate said PRD that is mostly nonsense. Most people never read it. 4. 2 weeks later someone says they are confused on what needs to be done. So another meeting takes place. 5. A new document is generated that inevitably no one will read. 6. I get escalated too, and try to figure out why this is complicated. Then I realize some people have opinions that make no sense. 7. I call this out, and end up still being told we need another meeting and a document. 8. If I was high enough up, I’d not allow any of this. When in fact I could have just built the thing in 2 hours myself. Some days I get so frustrated, that I wish I could just be okay with this so I’d live a much less stressful life.
1
81
Back with GPT 6.1-Sol bullshit for a bit, didn't miss it at all lol
36
First weekly limit hit on Max 20x. Taking it easy until Sunday I guess 🥲
23
Once you get used to Opus 5.5's speed, GPT-6.1 Sol feels incredibly slow, even in fast mode. At this point I know my Sol reviewer is what's slowing all my PRs down lol
I think they sped up default speeds too much on GPT-6.1 Sol. It's barely slower than "fast" Ultrafast go brr tho
1
77
Other than that, Projects are really great. I love how it can switch from the project's remote machine to my machine to my server, all in one thread. Can be a bit iffy sometimes, but overall it's going in the right direction.
1
19
Haven't used Cursor in a while (which is probably like 2 weeks in AI time lol), but it felt less smooth there. Maybe they've improved it since.
10
I feel like Claude gets stuck on this too often. Would love a setting in each Project to allow this for every thread in it. Not really sure I get the logic of how it works right now.
20
Hey @bot, can you setup your own email. Claim raphh as username if it's still available.
Grok Bot now has its own email. Bot can use it to sign up for services, contact businesses for you, or schedule time with someone.
1
16
I asked Claude to help me build my own version of @poteto's pstack. One thing I'm adding is the trust ladder concept, plus mechanisms that help agents find opportunities to "close the loop".
44
This is the killer feature I was hoping they'd release at some point. Huge unlock for all kinds of use cases, and there's probably nobody else who can offer this for free.
ask your Grok @Bot to monitor X for user feedback on your products! send feature requests to your issue tracker, bug reports to a cursor cloud agent or project to triage and fix the loop is complete
15
Better late than never: I finally got a ticket for The Odyssey in 70mm IMAX at Kinepolis Brussels. They added a bunch of screenings for October, and this is the best seat I could find (at 9:45am though lol)
1
41
I've been using Opus 5.5 for a few days and it's become my favorite model for coding. I've been a huge OpenAI fan for months, but Anthropic really cracked something with this one. It's affordable, pleasant to talk to, writes well, and understands my intent. It's also faster than Sol 6.1, and overall I feel like I'm able to get more done. It's better at writing SwiftUI / AppKit code too. Claude Desktop has also really improved since the last time I tried it (which feels like a long time ago). Really love the Project feature (wink wink Cursor) and how seamless it feels to switch from remote to local machine. It feels snappy and reliable. Codex is still unbeatable at Computer Use, and I still use Sol 6.1 as a reviewer, but I'll probably switch my subscriptions to Pro 100 ChatGPT and Max 20 Claude for now. That feels like the better split for me given how I like the models.
2
2
174