Torben Wetter (@TorbenWetter) header
Torben Wetter (@TorbenWetter) profile picture

Software & Cloud Architect šŸ‘ØšŸ»ā€šŸ’». Building Ladepark, an iPhone map of which EV chargers are free right now. Posting what I find in the charging data.

Hamburg, Germany
Joined June 2018
Photo by Torben Wetter (@TorbenWetter)Photo by Torben Wetter (@TorbenWetter)Photo by Torben Wetter (@TorbenWetter)Photo by Torben Wetter (@TorbenWetter)Photo by Torben Wetter (@TorbenWetter)Photo by Torben Wetter (@TorbenWetter)Photo by Torben Wetter (@TorbenWetter)Photo by Torben Wetter (@TorbenWetter)Photo by Torben Wetter (@TorbenWetter)Photo by Torben Wetter (@TorbenWetter)
How long does a car stay at a public charger in Germany? From four weeks of live status data, per site: DC (CCS): typically 30 minutes. AC (Type 2): 133 minutes. The surprise: above 150 kW it barely gets shorter. At 400 kW sites a car still stays about 27 minutes.
1
123
When are public EV chargers in Germany busiest? I plotted every hour of the week from four weeks of live status data, across 2,897 sites. Busiest: Saturday at noon, 38% of charge points in use. Quietest: the same Saturday at 3 a.m., 9%. Is it the same where you live?
1
6
428
I installed OpenClaw on a Raspberry Pi in its own IoT network and really tried to lock it down. But what's the point of an AI agent that can't access anything? Its whole purpose is to do things for you. So how do you give it access without trusting the machine it runs on? – at Hamburg, Germany
4
1
341
For approvals, I added a second Telegram bot to the group chat. Controlled by the gateway, not by OpenClaw. It sends me Allow / Deny buttons. OpenClaw doesn't even see these messages, it just gets back whether the action was approved and executed, or denied. – at Hamburg, Germany
1
1
128
Torben Wetter retweeted
Say hi to Poke.com! šŸ‘‹šŸ¼šŸŒ“
473
207
605
3,988
3,268,088
Got a health check in London last month with lots of results I couldn't make sense of. So I spent the weekend building a dashboard to actually understand what's going on: āœ… All biomarkers in one place, with filters and priorities āœ… Shows optimal/normal ranges āœ… Explains what each marker means and how to improve it āœ… Terminal-style because... why not šŸ˜… – at Hamburg, Germany
1
5
390
Torben Wetter retweeted
Client: How much do you charge? Me: $400/hour (with thinking) & $20/hour (without thinking)
120
547
66
10,684
480,802
Might need to revisit the Y-axis limits on our @home_assistant temperature graphs... ā˜€ļø – at Hamburg, Germany
1
255
Torben Wetter retweeted
So excited to share one of my white-whale projects: a fully physics-based, holographic foil shader. Each pixel simulates a ray of light diffracting into a rainbow of waves, which add and subtract to create these incredible patterns. Not a single gradient was used here!
939
2,169
305
31,884
1,973,282
Claude Code has completely changed the way we develop our app, Chorus, so much so that we now consider it one of our employees. We now put an asterisk on the whiteboard next to any task that Claude will mostly handle. And the asterisks are multiplying. Here’s what we’ve learned about how to manage Claude. ## Get the easy stuff right Run /model to see which model you're using. Set it to Opus. It’s more expensive but worth it. I accidentally had it on the default (Sonnet) for weeks. I thought Claude was quiet quitting but I was just using his dumber, cheaper cousin. Use the Cursor/VSCode extension. You now have a shortcut (CMD+Esc) and it automatically reads the file you’re in and any text you’re highlighting. I’m still using Cursor, but the Claude Code extension has almost completely replaced the AI chat sidebar. ## Start with plan mode `Shift+Tab Shift+Tab`. This is a recent addition and I’ll use it for any work that doesn’t have a clear and small scope. I have no hard data but planning seems to improve results, and it also helps me think through what I want. Like any AI, Claude loves to overcomplicate things. It’s a token fountain. Every line of code it writes should give you pain. I will usually remind it to ā€œkeep it as simple as possible.ā€ We don’t need to solve every edge case, we’re a startup, you fool! ## Feed the beast Paste in links. Paste in images. To paste images you have to use ctrl+v (that’s right, ctrl, not cmd!). I had no idea this existed until we wrote this post and Jackson told me. Claude can use git and the GitHub command line tool, gh. Ask it to make PRs, resolve merge conflicts, debug using git bisect, etc. Don’t expect it to know what files to look at. Guide it with some @ s. Claude is good at searching but not amazing, it needs your help. Imagine you’re sending a human engineer your request. Except you don’t have to be as polite (but maybe you should, who knows). Tip from @OmidMogasemi: ā€œI’ve found the more I talk to Claude like an engineer I’m pair programming with, the better it performs. This has helped me get over the hump of figuring out what context to give it. You can act like you’re writing a Jira ticket for a junior engineer.ā€ ## Use the magic word(s) I also will often add ā€œthink ultrahardā€ (thx @simonw) if I want a bit of extra oomph. This is like a secret magical spell to tell Claude to use more tokens. It’s bizarre to me that we live in a world where I am telling you magic secret passphrases to whisper to your AI to make it code better for you, but here we are. ## Watch it cook, or not Once it’s made a plan, tell it to start implementing. I’m a trusting type so I always Shift+Tab to auto-accept edits. Don’t be afraid to esc and do some more explaining if you think it’s going down a bad path. Something I still haven’t figured out: what do I do while Claude is working? It’s impossible to get into a flow state with these vibe coding tool like I do when I code with my raw brain. Here’s one solution, let me know if you have any better ideas: nitter.cf/charliebholtz/status/1… 🚨 The Most Dangerous Trap 🚨 If you are having trouble—let’s say you’ve asked Claude the same things 3–4 times with different strategies and you’re getting nowhere—pull the eject button and give up. You are entering what I call the ā€œrabbit hole problem.ā€ Vibecoding is powerful but the absolute worst version of it is lazily throwing stuff at the wall, it not working, and then spamming the chat. It's really hard to fight this, and I usually catch myself when it’s too late, when I’m tired and I don’t want to put in the effort of actually thinking through the problem. Something that helps is to think of all the work as helping YOU think about the problem. Don't view code the AI wrote as having the same weight as code you wrote. You can throw it all away and it doesn’t matter. One useful strategy here is to start over with a fresh context (see ā€œAsk Claude to reviewā€ below). ## Review the code The hardest part is knowing whether Claude’s work was any good. With Chorus, Claude can’t interact with our app, so I ask it to write a testing plan I can manually check off. Here’s a testing plan Claude wrote in a PR description (as you can see, I skipped the hard parts): You can also spin up a second Claude instance and ask it to review the work. Each Claude tends to be very attached to its own work, and will find it much easier to criticize other Claudes. (Hey, that reminds me of someone!) Often I’ll ask some other AIs in Chorus if I feel like I’m going down a bad path. How do you spin up a new Claude instance? The easy way is /clear, but that will also irrecoverably wipe out your chat context, which you might want to return to. I usually just open a new pane in my terminal. Yes, this eventually becomes a huge pain. On harder tasks, I’ve found myself repeating, at least 2-3 times: Can you double check this is as simple as it can be? As a last step, and I know this sounds insane, but hear me out—read the code yourself. Be suspicious. Claude loves to cut corners. It’s constantly using ref to get out of changing the React state model, or using typecasts so it can avoid figuring out the right types. ## Keep teaching Whenever Claude messes up, put # in front of the correction. The instruction gets saved to Claude’s memory (stored in CLAUDE md), and Claude will follow it in future sessions. If possible you should check CLAUDE md into source control. ## When not to use Claude I don’t use it for UI work. There’s a distinctive LLM design language that I can’t quite put my finger on but just looks shitty. I see it in apps created with Lovable, Bolt, etc. Human designers (like @julianfkelly ) are miles better. I also wouldn’t use Claude to write code I’m going to build on a lot later on, where each tiny design decision I make now will become a massive binding constraint down the road. It’s still helpful for thinking through how to implement these things, though. ## What does this all mean? Things are changing really fast, and we’re still figuring out how to work with our newfound sand intelligences. I’ve been surprised how much I’ve started to trust Claude. The game changer here is that it can do full scoped units of work. Even for things it can't finish, it gets the ball rolling, which is often the hardest part. Congrats to you, Claude, employee of the month!
Some reasoning models (o1-pro) take forever to get to first token What if you can play vibe coded games from smaller models while you wait
58
113
27
1,589
234,847
Considering integrating iOS 26 features like Liquid Glass controls and Apple's Foundation Models into my #SwiftStudentChallenge app. šŸ¤” – at Hamburg, Germany
1
9
760
visionOS 26 quietly introduced a glimpse into the future of how we’ll browse the web: a spatial Reader. Safari can now automatically transform a website’s content into a spatial experience using Spatial Scenes — allowing you to literally look into the rooms of the apartment you’re about to book for your next holiday. It does this by beautifully blending the content with your surroundings and softly tinting your room with the website’s color palette. It's just not possible to capture. I also love that Apple Intelligence lives in a floating window beside the content, ready to summarize the page for you. I can’t wait to see how this evolves into what we’ll one day call the Spatial Web.
12
48
2
446
34,381
Torben Wetter retweeted
Now that visionOS supports persisting windows/widgets across app launches, I just put together this HomeKit app that allows me to control my AC directly by looking at it! šŸ˜šŸ˜Ž
49
92
22
2,251
187,819
Introducing interactive video from @odysseyml—video you can watch and interact with, imagined by AI in real-time. Give it a try for free today on (almost) any device, and let us know what you think. We think it's pretty cool!
84
114
84
790
264,997