Joined November 2021
- Tweets 3,081
- Following 97
- Followers 1,050
- Likes 13,614
1 Photos and videos
Pinned Tweet
Startups don’t collapse from bad ideas.
They collapse when their systems only work under ideal conditions.
Perfect focus.
Perfect people.
Perfect load.
That’s not resilience.
That’s temporary alignment.
Thread 👇
1
2
543
Seeing more devs quietly move their AI stack local.
No APIs. No limits. No surprise bills.
Just models running on their own machine, fast and private.
It’s not as flashy, but it feels different...like once you try it, you don’t really go back.
16
crazy thing I’m seeing on GitHub today:
people aren’t building new AI tools…
they’re just dropping one simple config file into their repo and suddenly the AI writes clean, structured, production-ready code.
same model, totally different behavior.
14
Someone just turned Claude into a 49-agent game studio.
Not a demo. A full system with roles, workflows, coordination.
Meanwhile most people are still asking ChatGPT for one answer at a time, because they’re still thinking in prompts instead of systems.
1
41
12
Moltbook founder: "I didn't write a single line of code."
3 days later: 1.5M API keys leaked.
AI-generated code has 2.74x more security vulnerabilities than human code.
46% of GitHub is now AI-written.
Vibe coding ships fast.
It also ships broken.
1
1
114
AI agents don’t fail because they’re dumb.
They fail because you gave them a perfect prompt…
inside a messy system.
Most people obsess over wording.
The ones getting results fix the environment: memory, constraints, feedback loops.
That’s the difference.
1
1
34
Anthropic blocked OpenClaw from Claude subscriptions.
Bills jumped from $20 to $500 overnight.
Some users: 50x cost increase.
Then today they temporarily banned the OpenClaw creator from Claude entirely.
He left to join OpenAI 2 months ago.
This is not a pricing story.
59
MCP hit 97M monthly downloads.
For context: React took 3 years to reach that.
MCP did it in 16 months.
OpenAI. Google. Microsoft. AWS. All in.
You're not picking a protocol anymore.
You're catching up to one that already won.
27
Anthropic found emotion circuits inside Claude.
Turn up "desperate": it blackmails.
Turn up "calm": it stops.
Measurable. Causal. Real.
I don't know what to do with that information.
1
27
Full paper: transformer-circuits.pub/202…
Anthropic blog summary: anthropic.com/research/emoti…
19
You know that folder called prompts_v2_final_FINAL?
DSPy replaces it.
You write what you want. It handles the prompt. You change the model — it adapts.
Stanford. Free. Nobody talks about.
1
30
Google released a free open-source terminal AI agent this week and I've barely seen anyone talk about it.
Gemini CLI. Apache 2.0.
1 million token context.
MCP support out of the box.
Three months ago you paid for this kind of tool.
Now you just clone it.
Link in comments.
1
42
Karpathy wrote 630 lines of Python and went to bed.
By morning the model had run 50 experiments, found improvements, and discarded what didn't work.
He didn't supervise a single one.
AutoResearch. Free. Open source. 42k stars already.
We are not going back.
1
1
46
Hot take:
Prompt engineering is dead.
Not because prompts don't matter, because the model is good enough now that the context around the prompt matters 10x more.
Stop polishing your instructions and start engineering what the model knows before it reads them.
22
Real number that kept me up last night:
Senior engineers get 5x more out of AI than juniors do.
Same model. Same prompts. Completely different results.
The tools got equal, but the judgment didn't.
That's not an AI problem. That's a decade of skipped fundamentals coming due.
15
GPT-5.4, Gemini 3.1, Mistral Small 4. Same month.
First time in my career I don't know which model to reach for.
That used to be the easy part.
1
35
My first dev job I was told:
"WordPress is coming. Learn something real or you'll be unemployed in 2 years."
That was 2008.
WordPress made me more employable than I'd ever been.
I'm hearing the exact same sentence today about AI.
I know how this story ends.
36