Google just released free 2-hour course on full Harness engineering from 0% to 100%:
0% → 0:29 - Harness engineering from scratch
15% → 11:08 - build your first agent right way
30% → 28:08 - Eval engineering: build Chief of Staff agent
65% → 1:00:13 - Loop engineering
100% → 1:23:19 - self-improving graphs system that works 24/7
most people keep trusting agent that "looks right" - the real upgrade is a Harness that tests, judges and rewrite your agent until it works
learn Harness from Google, ship your first - then unlock the full Agent systems below:
This is f*cking insane. SpaceXAI engineer:
"99% of people use GrokBot for 1% of what it can do. They run one agent without loops or graphs
I run a team of 30+ GrokBot agents. By 7 a.m. my Chief of Staff has the day planned, my PM has handed out the work, and the workers have shipped half of it"
In this 1-hour session, SpaceXAI shows how to build that team from scratch
GrokBot → Chief of Staff → PM → Workers → Self-Improving Team
A loop sends every task back until it actually works
A graph lets one agent hand its result to the next without you in the middle
Anyone can ask GrokBot a question, almost nobody gives it a team to run
Worth more than most $1,500 agentic engineering courses
Watch it today
Then read how to build a fleet of GrokBot agents in the harness engineering guide below ↓
@Pumpfun is a fucking scam.
You guys gotta stop fucking over the retail traders. The people with sub $10k portfolios that you fucking treat like bottom dwellers. Fucking $4.62 payout for generating $3k in profits for my trailers, on a 15x callout.
#pumpfun#Memecoins
@APompliano@jvisserlabs Your small to medium sized businesses want nothing to do with Anthropic. Sentiments are terrible in the B2B which is their lifeline. Doesn’t matter if B2C model thrives when they’re generating negative profits per head.
@APompliano@jvisserlabs This is on the nail. Anthropic’s moat used to be superior development. The problem is, other LLMs are beginning to excel is that same Space, and some might argue that the benchmark comparisons between the frontier models are inaccurate
@APompliano@jvisserlabs More on the economics is that it’s simply too expensive. No org can afford to put even max credits for each seat other than the hyperscalers themselves. At the rate at which they are bleeding, they’ll either develop their own models (what Google is going already) or negotiate
@APompliano@jvisserlabs Why? Because the rate at which Anthropic is release new models means there’s barely any time for maturation to happen, and benchmark tests are useless when it’s not studied longitudinally for a technology that is progressive and supposedly self-recursively developing.
If anyone is interested in trying Pumpfunc, use my code below.
They are absolutely crushing it with the callout rewards. Basically get paid to do dd and just post about it. Takes 15 seconds!
https://t.co/rfOboOH3OZ
Boris Cherny (creator of Claude Code):
“I am not prompting my agents anymore. I am building “graphs” and “loops” - they’re building my agent for me.
in 4-6 months, we will all be building graph engineering for our agentic systems.”
In a 10-minute video, Boris Cherny breaks down where agentic engineering is heading.
It’s more valuable than a $700 course on agentic AI.
Don’t just scroll past. Watch it today, then dive into the full roadmap in the article below.