Mistral's Robostral Navigate: a state of the art robotics navigation model

One could maybe autogenerate these text planning commands, but it would require a map and the robot's current location, so it doesn't really solve that, unless it can find a specific thing completely on its own. How much of a planning horizon does it have?

Or, I don't know, make your own vacuums.

A in-model memory approach is probably still deep research but maybe a Rag-like pipeline could work in some instances

ICRA, 2010

But for interaction with the world? I'd probably take something like an old 12-volt windshield-washer sprayer out of one of the wrecked cars in my front yard and put Round-Up into the tank and let it go spray all the poison ivy and invasive honeysuckle for me. Doesn't need to gimbal like a turret -- just generally give it a fixed-aim that's roughly at the center of the camera vision and let the bot put pest plants roughly in its center-of-view and activate the sprayer for a second or two, mark the spot as sprayed, and move on to the next one.

Could test it with plain water and logging the plants that it chose to spray first as a review step before loading it with actual weed-killer.

I don't need complicated end-effectors that can fold my laundry -- just a simple weed-wacker motor or squirt gun would be enough for me to call this thing 1000% useful. Like a Roomba, but outdoors.

There are a handful of open-source farm bots built on traditional platforms with traditional robotics stacks, but there's something attractive to me about the plug-and-play nature of something like OpenClaw + Robostral (along with the extensibility that self-modifying agentic systems have to offer).

Made a comment that needed an additional tag because the joke might be getting a little too real in the near future

REWARD?

+5 to Foresight

Not sure if I’m out of touch (not doing robotics right now) or if things just slowed down. Back in ~2013 it looked like humanoid robots were just around the corner. Boston Dynamics became a hit. Aldebaran’s Pepper was presented. And the DARPA Robotics Challenge was on everyone’s lips.

And then suddenly, nothing.

Costs of simple tasks grow extensively: OCR with "Mistral OCR" at $4 per 1000 pages vs OCR with Opus 4.8 at sometimes¹ $1 per "page".

Or just the immense costs when burning tokens in an unoptimized agentic coding environment costing tens of dollars for a few simple classes or functions versus a highly optimized "autocomplete" model costing under $10 for thousands of such classes and functions.

Or the, over ten dollars worth of tokens when some "agent" using a general model, tries to perform the task I gave it to "read the event on example.com/event/1337 and put it in my calendar", include commute time as well"

The "general models" currently only become smarter by growing bigger and having larger context windows - by becoming exponentially more expensive to train and to run and to interact with. Whereas "Niche" models can do the things that "normal code" cannot do, and improve by tuning and tweaking only that. Their goal is then to fill in gaps that traditionally are hard or impossible with normal software. Wheras the goal of a general model (with agentic reasoning)is to replace that entire "normal software".

One example: I am not interested in "chatting with my calendar". I'm interested in a calendar because it is a well known view (UI) of my planning and tasks, but I see a lot of opportunities where AI can improve my working with this calendar. I may be interested in a smarter screen when I hit "+ Add event"; one that has knowledge of my previous events and patterns (some RAG vector db maybe). One that maybe has access to content I just copied, or read (though: privacy?) or can open my camera to let me shoot a pic of something that has the event info on it. In such a set-up, Niche LLMs perform dedicated tasks: determine patterns (he always books a Yoga class on wednesday or thursday, two days in advance, so lets suggest a yoga class), determine existing content (event is planned 100Km from his home, so lets suggest the commute based on previous commutes like this). Or an OCR model. Or an autocomplete model. Relatively simple, niche models, called from within software to aid me when "calendaring". Not replace the entire calendar with some chat.

¹Edit: This was a rather unscientific research of mine, where I compared some models to read from photographs, compared purely on costs and timing. "Opus" or other generic LLMS with image input capabilities commonly did better on "performance" esp with difficult input such as a picture of a poster of some rock event.

And even if you use all the tricks in the book to make them work for you, the cost can easily be 1000 _times_ more than the specialized model. Ditto for speed.

This is especially important for things like robotics or navigation.

All I can think of are robot dogs, Tesla bots, and whatever flavor of the month Japanese robots show up at trade shows.

Posts like this just reminds me of the end to end demos AV companies built in the early days using a single camera - only to realize that it’s harder than it looks years later into development.