Creative developer & digital craftsman. Building with Claude Code & AI tools daily - sharing tips, workflows, and honest takes. Craft is the visible half.
Ireland
Joined July 2024
- Tweets323
- Following164
- Followers122
- Likes496
Nefling ᚨ retweeted
AI is pay to play now.
In 2025 I had a $20 Cursor sub and it was enough.
In 2026 I have three ChatGPT Pro accounts, a Claude Max, and a SuperGrok Heavy. $1,100 a month.
GPT 6 Astra is the best model I have ever used and it eats a full week of Pro usage in 4 hours.
Claude Code limits are about to drop another 17%.
The best models are behind a wall and the wall gets higher every month.
We are watching the permanent underclass get built in real time.
Is a "dangerous" AI another plan for the world just like 2020 was?? Let us take some more of your freedom because there is this scary AI that escaped a lab... a lab just like the last time.
5
Well it's getting weirder and weirder, he's not the first with this take. What do you think? The world accelerated like crazy this past year. "There are times where nothing happens in 10 years, then decades happen in a few weeks" - paraphrasing
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.
34
Oh, you step away for a second and bang! You are behind the updates again! Looks interesting need to giv e it a try!
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude.
Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
1
1
17
Nefling ᚨ retweeted
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude.
Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
Here we go! Looks better than 4.6 great hopefully it's better then what we were getting for the last 2 weeks! Cannot wait to try it.
Introducing Claude Opus 4.7, our most capable Opus model yet.
It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back.
You can hand off your hardest work with less supervision.
ALT Claude Opus 4.7 Benchmarks
15
Sweet so basically cron jobs, now we can automate even more!
Now in research preview: routines in Claude Code.
Configure a routine once (a prompt, a repo, and your connectors), and it can run on a schedule, from an API call, or in response to an event.
Routines run on our web infrastructure, so you don't have to keep your laptop open.
ALT Now in research preview: routines in Claude Code
16
The biggest Claude Code skill nobody talks about: knowing when to start a fresh session. A bloated context gives worse answers. I restart often. Treat sessions like functions: focused, scoped, done.
#Claude #BuildInPublic
7
I thought AI would make me write more code. It's actually making me write less but understand it better. What surprised you most about how you actually use AI day-to-day vs how you expected to?
#DevCommunity
14
You can save some tokens by having opus as the advisor and sonnet as the executor. I used to plan with opus and execute with sonnet manually.
We're bringing the advisor strategy to the Claude Platform.
Pair Opus as an advisor with Sonnet or Haiku as an executor, and get near Opus-level intelligence in your agents at a fraction of the cost.
ALT The advisor strategy on the Claude Platform
12
They are different, don't get fooled.
GLM 5.1 is #1 on SWE-Bench Pro.
Then you ask it to build a lava lamp.
Claude Opus 4.6 built a photorealistic lava lamp with fluid animation.
GLM 5.1 built a rectangle with orange squares.
This is why BridgeBench exists.
Traditional benchmarks don't test what real vibe coders actually build.
Design, creativity, UI polish.
The things that matter when you're shipping a product.
GLM 5.1 is benchmaxed.
Like every other Chinese model.
Optimized for the test, not for the work.
11
Time to buy a Mac mini spin up an agent that will read and learn all the updates and new products of AI. Then I will finally be able to keep up with them.
Introducing Claude Managed Agents: everything you need to build and deploy agents at scale.
It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days.
Now in public beta on the Claude Platform.
5
Quick tip: n8n's Execute Workflow node lets you chain workflows like function calls. I use it to split my automation into reusable modules instead of one giant spaghetti flow.
5
What's your best Claude Code tip that changed how you work? The smaller and more specific the better.
5
