IF YOU ARE STILL PROMPTING BY HAND IN 2026 YOU ARE ALREADY BEHIND
the guy who built Claude Code at Anthropic said he stopped writing prompts a long time ago
he runs loops instead, systems that write the prompts for him and keep working while he sleeps
you type one request at a time and wait for the answer
he built a machine that fires hundreds of requests, checks its own output and fixes itself with no hands on the keyboard
here is how you make the jump
step 1 stop treating the model like a chat box and start treating it like a worker you manage
step 2 write a loop that takes a goal, breaks it into tasks and sends each one to the model on its own
step 3 add a second pass where the model grades its own work and retries whatever failed
step 4 let it run on a timer so it keeps shipping while you are away from the screen
the person still typing prompts one by one is doing the work of a intern
the person running loops is doing the work of a whole team off one laptop
prompting was never the skill, building the system that prompts for you is
VISUALIZATION OF A FUTURE FIELD ROBOT - ONE-SEASON PAYBACK
This clip is a concept render, not a working machine. But the job it's showing — manual field labor — is real, seasonal, and one of the hardest to automate.
A US farm laborer costs a farm ~$50,000/year, working roughly 8 months a season with breaks for weather, fatigue, and daylight. To replace one such robot, you need 3 workers, which is about ~$150,000/year.
A field robot with whole-body balance and dexterous hands could work year-round, in more hours per day, with no seasonal hiring, no housing, no visas to sponsor.
At a rough $100,000–$150,000 price point — where general-purpose humanoids are expected to land as production scales — one robot working multiple seasons could beat the cost of the labor it replaces within 2–4 years.
A girl walked on a beach that doesn't exist.
White bikini.
Bright sun.
Waves in the background.
People walking behind her.
It looks like a vacation someone filmed on their phone.
Nobody booked a flight.
Nobody packed a suitcase.
Nobody waited for golden hour.
The entire campaign was generated with AI.
That's what most people still don't understand.
Brands don't pay for reality.
They pay for content that keeps people watching.
AI just made that infinitely cheaper.
Kimi K3 is actually insane
someone typed one prompt and got a full Animal Crossing-style game back, playable from the first second:
> the cozy world, the little interactions, the whole gameplay loop, all in a single generation
one prompt did what used to take an engine, a team, and months of work
> from what i can see, Kimi K3 is already pulling ahead of Anthropic's Claude Fable 5 here
once summer ends, AI game-making is going to take over
THAT $70 "RUN YOUR OWN LLMS" PI KIT CAN'T RUN A SINGLE LLM. IT'S A VISION CHIP WITH NO RAM.
that clip sells a raspberry pi 5 in a slick case with an ai accelerator and the caption "your own llms." clean build, fun kit. the claim is where it breaks.
the fine print:
the popular $70 pi ai kit uses a hailo-8l, 13 tops. it's built for vision, object detection and image processing, and it has no memory of its own. so it cannot run large language models. full stop
the board that actually can is a different one: the newer ai hat+ 2, hailo-10h, 40 tops, with 8gb of dedicated ram. that's $130, not $70
and even that runs only tiny models. llama 3.2 at 1b, qwen 2.5 at 1.5b, deepseek r1 at 1.5b. edge llms live in the 1-7b range, against cloud models at 500b to 2 trillion
so the honest pitch: for $130 you can run a very small language model on a pi, slowly, as a fun learning project. that's real and it's cool. "your own llms" on a $70 vision kit is not.
why this keeps happening: "ai kit" and a big "tops" number sell. tops sounds like intelligence. but tops measures vision-style math, not whether the chip has the memory to hold a language model. the spec that matters for llms is ram, and the cheap kit has none.
the honest caveats, both ways:
the $70 kit is genuinely great, just at vision. cameras, object detection, that's its job
the $130 hat really does run small llms locally, which a pi couldn't do at all two years ago. that's progress
"small" is the load-bearing word. don't expect gpt at home on a pi
the takeaway: before you buy a kit because the caption says llm, check two numbers. not the tops. the ram, and the size of the model it can actually load.
no 70-dollar miracle, no gpt in a pi case, no tops number that means what you think.
save this before you buy the wrong kit for the word on the box.