Great idea indeed. A carriage drove past me, delivered a passenger, returns to base.
Tag: Robotics
Navigating Code Generation with AI: Essential Skills for Programmers | August 04 2025, 14:28
I am currently using Gemini extensively for code generation, and I see a skill that programmers need to have to be successful in this field. It’s the ability to quickly read and understand someone else’s code, as well as explain why AI generation needs to be redone and how. For the former, you simply need to know the language very well and read “from the sheet,” because there will be little time to ponder. For the latter, you need to know patterns well and understand where they apply and where they do not. AI will still mess up using patterns inappropriately for a long time.
Moreover, a person will still need to understand “as a whole” 90% of the code generated by AI, and also manage to find time to comprehend each generated line of code. If you relax and miss it, the system may produce even working, but very poorly maintainable code. For instance, there is an unwritten rule that individual files should not contain so much code, and if it grows, you need to refactor, breaking one large into two or three. Sometimes this requires rewriting logic, but this rewriting is always aimed at one task – to simplify maintenance. And AI, while rewriting, also “improves” the code at the same time. And this is quite difficult to prohibit.
In addition, the very concept of LLM implies the limitation of the contextual window. Which gets filled with code very quickly. To create an illusion for the user that everything is working even with a large volume of code, LLMs are able to do preliminary processing, extracting only relevant pieces for processing and setting aside irrelevant ones, so that the relevant ones fit into the actual contextual window. But this process is very unreliable, and once it works, and the second time it turns out that something important was set aside, and as a result, the system did not see the whole picture and generated code, which includes a function very similar to the function set aside, and now we have two almost identical ones.
Besides, currently logic is distributed between the DB and the code. That is, data often controls the code. And data in LLMs simply often do not fit. There is too much of it. In the end, without programmers, current LLM architectures cannot cope. But the requirements for programmers’ qualifications will only increase with LLMs, not decrease. So yes, juniors should be worried, but leads not so much 🙂
Why Don’t We Have Self-Sustaining Solar-Powered Drones Yet? | July 16 2025, 01:33
I wonder why we still don’t see autonomous drones that could lead an “eternal” life: landing on roofs, deploying solar panels, charging from the sun, and taking off once a day for whatever their mission might be? When you consider the energy aspects, it seems like a feasible scheme. For instance, a heavy drone weighing about 8 kg could carry foldable solar panels with an area of 1.5 m² and a battery with a capacity of 2 kWh. In one sunny day, such panels could collect about 1.2 kWh of energy — enough for it to fly for 20 minutes at a speed of 40–50 km/h, take photos, and transmit them via the mobile network. And there would still be a reserve of energy for several cloudy days.
Even a light drone weighing 2 kg with small panels (0.5 m²) could rise into the air for 10–15 minutes every day if it managed to find good weather and a sunny roof. The power required for hovering for such devices is about 150–200 W, and solar panels with 20% efficiency at mid-latitudes can produce up to 350–400 Wh per day. The balance comfortably adds up, especially if not chasing speed and if there’s no rush on the roof.
Such a “solar nomad” could live for weeks and months, flying from roof to roof and charging in anticipation of missions. At first glance, the technology of batteries and panels already allows this to be done. Or am I missing something?
Exploring the Technological Marvels of Tesla’s Full Self-Driving Capabilities | July 11 2025, 03:59
I read various engineering blogs about Tesla’s autopilot (FSD) — simply because for the last month and a half I’ve been almost constantly riding as if in a taxi — you set the destination and hardly ever need to intervene, the car travels from point A to point B completely independently. This is certainly the future.
Such systems exist not only at Tesla. For example, Mercedes has one (Drive Pilot). Others only help in traffic jams at best. Though Tesla seems to be the only one that works on all roads.
So, returning to engineering curiosities. Tesla has an AI model production on its “farm” called Dojo — an exaFLOP supercomputer on Tesla chips. Videos from cameras are fed into it, and it trains models that are then sent out for autonomous operation across the entire fleet of Tesla cars.
The FSD architecture comprises about 48 specialized neural networks, trained on Dojo, which together form about 1,000 different prediction tensors. Tesla is gradually moving from modular networks (object recognition + planning) to end-to-end training — directly converting video frames into steering trajectory/action. This is akin to a “black box” — the neural network learns directly from human behavior, without manual tuning of knobs; an extremely cool engineering solution, but, I suspect, complex to debug.
By the way, it is claimed that Tesla has switched from C++ to Python. And that this shift to end-to-end training has made 300,000 lines of C++ code unnecessary, where various corner cases and rules for resolving different scenarios were accounted for — now it’s at the model level.
Tesla has abandoned radar and ultrasonics, switching to purely camera solutions (Vision Only) with “Hardware 4” (HW4, FSD Computer 2): 16 GB RAM, 256 GB flash memory, performance 3–8× higher than HW3.
Assess the performance: 22 milliseconds to create a 3D scene with cars, pedestrians, cyclists around — information is collected from 8 cameras 36 times per second.
85 ms for the entire cycle from receiving the image to changing the plan and commands to the wheels. Fantastic!
More than 4 million Teslas on the roads collect data daily, and in the FSD Beta version, more than a billion miles of autonomous driving have been recorded. This “live” dataset is used to train networks on the most real-world scenarios, including rare “edge-case” incidents (strange accidents, road conditions, etc.).
In June 2025, Tesla for the first time delivered a Model Y from the factory in Austin to a customer’s home without a driver or remote operator — fully autonomously. This is very cool.
The Vision network not only analyzes the current frame but also stores features from previous ones (at a distance of ≈1 m). This allows it to remember recently crossed markings/signs, even if they have already left the field of view – very similar to human memory.
Awaiting the Next Big Thing from Boston Dynamics | July 10 2025, 20:09
I’ve been thinking, it’s been a while since there was an exciting video from Boston Dynamics. Remember, each one used to create quite a stir online. I checked their channel. And it looks good. Hundreds of millions in investments from the Pentagon/US Department of Defense suggest that it won’t stop at drones.
From Concept to Prototype: Merging Surveillance and Health Safety | June 20 2025, 16:30
Not bad, thought of it a minute ago, and here’s the prototype already.
Hi, I'm Rauf Aliev. 