Startups donāt collapse from bad ideas.
They collapse when their systems only work under ideal conditions.
Perfect focus.
Perfect people.
Perfect load.
Thatās not resilience.
Thatās temporary alignment.
Thread š
1
2
554
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.
Itās not as flashy, but it feels different...like once you try it, you donāt really go back.
1
28
crazy thing Iām seeing on GitHub today:
people arenāt building new AI toolsā¦
theyāre just dropping one simple config file into their repo and suddenly the AI writes clean, structured, production-ready code.
same model, totally different behavior.
23
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 theyāre still thinking in prompts instead of systems.
1
45
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
Replying to @GG_Observatory
Exactly.
No verification = no learning loop.
The agent just keeps producing⦠not improving.
Once you add result-checking, everything changes:
errors get caught, behavior adapts, outputs compound.
Thatās when it starts feeling like a system, not a demo.
9
AI agents donāt fail because theyāre dumb.
They fail because you gave them a perfect promptā¦
inside a messy system.
Most people obsess over wording.
The ones getting results fix the environment: memory, constraints, feedback loops.
Thatās 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
Full paper: transformer-circuits.pub/202ā¦
Anthropic blog summary: anthropic.com/research/emotiā¦
19
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
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 ā 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
Replying to @housecor
Makes sense. One agent you can actively steer often beats juggling many you canāt supervise. Parallel only wins when the work is cleanly separable. Otherwise youāre just managing chaos instead of getting better output.
1
224
Replying to @francoisfleuret
I grew up being told my trajectory was basically set by 25. The school I went to, the job I got, the salary I could reach. I'm watching people rewrite all of that in real time right now. The map changed. Most people haven't looked up yet.
243
