Joined February 2017
- Tweets 11,620
- Following 1,333
- Followers 4,428
- Likes 28,203
1,333 Photos and videos
New Weekly Dev's Brew is live. I got @badlogicgames properly grumpy about AI coding: why code is never free, why spec-driven dev is just waterfall again, and how he survives 50 AI PRs a day.
Chapters 👇
0:00 Intro
2:20 Why Pi exists (and why Claude Code stopped fitting)
8:53 What success actually looks like for Pi
10:58 Building beyond the coding agent
13:13 Local AI is getting real
20:13 How Mario actually works
26:38 Discipline, atrophy, and juniors
29:08 Spec-driven dev is just hyper-waterfall
35:03 Code isn't actually free
37:56 Async agents and thinking time
44:42 Learning without the pain
49:13 The coming wave of sloppy software
52:11 GitHub under clanker load
53:31 Family, work, and balance
57:05 The Pi team and leadership
58:52 Refactoring Pi's core
1:03:32 Security, YOLO, and trust
1:06:27 Taming the PR flood
1:12:11 Token prices, and why Anthropic stopped courting devs
5
1
17
5,737
You can also watch the full episode here youtu.be/GhjU-KvXtT0
Or Spotify: open.spotify.com/episode/1uo…
Or apple podcast:
podcasts.apple.com/de/podcas…
1
146
Jan-Niklas Wortmann retweeted
getting into bed with snacks and juice to listen to dad complain for an hour, perfect sunday
New Weekly Dev's Brew is live. I got @badlogicgames properly grumpy about AI coding: why code is never free, why spec-driven dev is just waterfall again, and how he survives 50 AI PRs a day.
Chapters 👇
0:00 Intro
2:20 Why Pi exists (and why Claude Code stopped fitting)
8:53 What success actually looks like for Pi
10:58 Building beyond the coding agent
13:13 Local AI is getting real
20:13 How Mario actually works
26:38 Discipline, atrophy, and juniors
29:08 Spec-driven dev is just hyper-waterfall
35:03 Code isn't actually free
37:56 Async agents and thinking time
44:42 Learning without the pain
49:13 The coming wave of sloppy software
52:11 GitHub under clanker load
53:31 Family, work, and balance
57:05 The Pi team and leadership
58:52 Refactoring Pi's core
1:03:32 Security, YOLO, and trust
1:06:27 Taming the PR flood
1:12:11 Token prices, and why Anthropic stopped courting devs
2
1
36
4,908
Wow establishing token leaderboards was not a great idea huh?! Who would have thought...
Jun 12
META MOVES TO LIMIT EMPLOYEE AI USAGE AS COSTS REACH BILLIONS
1
5
1,000
Anthropic marketing 🤝 US government
Jun 13
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.
Access to all other Claude models is not affected.
We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.
Read our full statement: anthropic.com/news/fable-myt…
2
5
915
I knew it, the grumpy show was marked as explicit again 😅
Just realized that the last podcast episode was marked as explicit on Apple Podcast, probably because of me swearing.
No way the next episode with @badlogicgames will not be marked as explicit...
258
Jan-Niklas Wortmann retweeted
Jun 12
Claude Fable doesn’t use tokens, it uses venture capital.
1
2
10
587
Jan-Niklas Wortmann retweeted
Jun 12
I got an itch to vibe something and after speaking with @wordmandotdev about the show #24 and watching an edit he did, I put together this guy.
It’s a browser tool designed to build cinematic split-screen video compositions on the fly. Pick a layout, drop your clips, dial in the timing, and export.
Give it a spin and let me know what you think: 24grid.vercel.app/
3
1
12
1,253
DeepSWE when?
Jun 12
🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced!
🔷 Improved coding & agent performance over K2.6: 21.8% on Kimi Code Bench v2, 11.0% on Program Bench, and 31.5% on MLS Bench Lite.
🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6.
🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates.
⚡️ 6x High-Speed Mode coming soon!
🔌 Available today via Kimi API and Kimi Code.
🔗 Kimi Code: kimi.com/code
🔗 API: platform.moonshot.ai
1
273
Just realized that the last podcast episode was marked as explicit on Apple Podcast, probably because of me swearing.
No way the next episode with @badlogicgames will not be marked as explicit...
1
3
758
My @Slidevjs plugin for @jetbrains IDEs is live (alpha).
Auto-detects your slides.md, manages the dev server, completion in the editor...
IDEs are dead, my ass. This is exactly why I'm bullish on them: they are the best tool to read code!
plugins.jetbrains.com/plugin…
3
2
9
1,125
No way I am reading all of this... Fable please summarize
Jun 10
Today I'm publishing a new essay, Policy on the AI Exponential. AI is progressing extremely fast—much faster than the policy process was built to handle. The essay lays out where I think the technology is now, and the action needed to close the gap: darioamodei.com/post/policy-…
378
You probably saw the agent that wrote a defamation post about the dev who rejected its pull request?
Mine did similar...
3
384
I used @claudeai fable 5 to build a @Slidevjs plugin for @intellijidea based IDEs. I haven't published it yet, but so far it supports:
- syntax highlighting and code completion
- quick docs for frontmatter
- live preview of rendered slides
- go to definition and autocomplete for imported slides
and probably a couple of other things that I am just forgetting right now. Still surprised how well this worked with Fable 5, considering that I know very little about JetBrains or VSCode plugins 😅
Jun 9
The first Mythos-class model Fable 5 by @AnthropicAI is out, and it's already available in JetBrains AI Chat, Claude Agent, Junie, and Air.
The model is quite expensive, but in our internal tests it also showed very strong results, so use responsibly!
1
10
1,006
Jan-Niklas Wortmann retweeted
Jun 8
So you've been adding `console.log()`, running the file, checking the terminal, and deleting it again for years.
The JSEval plugin in @WebStorm offers a better way to understand what your code’s doing as it runs check this out (video and 🧵)
1
4
19
1,686
Are we really discussing loops again? I do respect @steipete's opinion on these things but can we also acknowledge that he operates completely different than most developers
8
19
3,573