Anthropic engineer:
"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."
In 45 minutes she breaks down how Anthropic builds agents that remember, learn from their mistakes, and get smarter with every run.
Worth more than any paid course you'll find on building agents.
Watch the session, then read the guide on building loops below.
Anthropic engineers just showed how to build agents that can run for days with loops
"At Anthropic, 30%+ of our code is already written by loops. That's why we ship so fast"
In this 40-minute workshop, they break down the whole stack:
Agent loop
Harness
Memory
Sub-agents
This is worth more than most $500 vibe-coding courses
Bookmark and watch the workshop today, then read the article below
The Head of Claude Code at Anthropic said he hasn’t written code by hand in months.
In 2 days he shipped 49 full features. All written 100% by AI.
He just dropped a 30 min talk on exactly how he does it.
Worth more than any $500 vibe coding course. Bookmark it:
I interviewed @theaidocfilm's Daniel Roher this weekend for my For Humanity podcast on @AIRiskNetwork.
If you've seen the film, I think you'll find this interesting.
Claude Sonnet 5: The “Fennec” Leaks
- Fennec Codename: Leaked internal codename for Claude Sonnet 5, reportedly one full generation ahead of Gemini’s “Snow Bunny.”
- Imminent Release: A Vertex AI error log lists claude-sonnet-5@20260203, pointing to a February 3, 2026 release window.
- Aggressive Pricing: Rumored to be 50% cheaper than Claude Opus 4.5 while outperforming it across metrics.
- Massive Context: Retains the 1M token context window, but runs significantly faster.
- TPU Acceleration: Allegedly trained/optimized on Google TPUs, enabling higher throughput and lower latency.
- Claude Code Evolution: Can spawn specialized sub-agents (backend, QA, researcher) that work in parallel from the terminal.
- “Dev Team” Mode: Agents run autonomously in the background you give a brief, they build the full feature like human teammates.
- Benchmarking Beast: Insider leaks claim it surpasses 80.9% on SWE-Bench, effectively outscoring current coding models.
- Vertex Confirmation: The 404 on the specific Sonnet 5 ID suggests the model already exists in Google’s infrastructure, awaiting activation.
(Unverified leaks; treat timelines, pricing, and benchmarks with caution.)
Anyone know if there’s a way to verify the agents on Moltbook are external and not a platform controlled simulation? Feels ahead of the infrastructure.
the grok + tesla integration is actually super elegant. it’s the cleanest preview right now of how humans will move through the world with ai. i.e. llms for cognition + autonomy & self driving for locomotion. once thinking & motion collapse into one loop navigation sorta simply becomes intent.
i can’t wait to use this in my tesla.
🚨 BREAKING: Another Tesla Robotaxi spotted on public roads in Austin, TX with no one in the driver’s seat 👀🔥
This is not a test anymore… it’s happening $TSLA
Tesla is a well hated stock right now at 240.
It’s gonna explode to 325.
I am about to share a CALL which is right now just 40 cents for this weekly expiry.
For our folks only. Link in pinned tweet.
$tsla