Bridging A Gap Between LLMs And Programming With TypeChat

July 22, 2023 by Bryan Cockfield 33 Comments

By now, large language models (LLMs) like OpenAI’s ChatGPT are old news. While not perfect, they can assist with all kinds of tasks like creating efficient Excel spreadsheets, writing cover letters, asking for music references, and putting together functional computer programs in a variety of languages. One thing these LLMs don’t do yet though is integrate well with existing app interfaces. However, that’s where the TypeChat library comes in, bridging the gap between LLMs and programming.

TypeChat is an experimental MIT-licensed library from Microsoft which sits in between a user and a LLM and formats responses from the AI that are type-safe so that they can easily be plugged back in to the original interface. It does this by generating JSON responses based on user input, making it easier to take the user input directly, run it through the LLM, and then use the output directly in another piece of code. It can be used for things like prototyping prompts, validating responses, and handling errors. It’s also not limited to a single LLM and can be fairly easily modified to work with many of the existing models.

The software is still in its infancy but does hope to make it somewhat easier to work between user inputs within existing pieces of software and LLMs which have quickly become all the rage in the computer science world. We expect to see plenty more tools like this become available as more people take up using these new tools, which have plenty of applications beyond just writing code.

Contrary View: Chatbots Don’t Help Programmers

June 8, 2023 by Al Williams 67 Comments

[Bertrand Meyer] is a decided contrarian in his views on AI and programming. In a recent Communications of the ACM blog post, he reveals that — unlike many others — he thinks AI in its current state isn’t very useful for practical programming. He was responding, in part, to another article from the ACM entitled “The End of Programming,” which, like many other articles, is claiming that, soon, no one will write software the way we do and have done for the last few decades. You can see [Matt Welsh] describe his thoughts on this in the video below. But [Bertrand] disagrees.

As we have also noted, [Bretrand] says:

“AI in its modern form, however, does not generate correct programs: it generates programs inferred from many earlier programs it has seen. These programs look correct but have no guarantee of correctness.”

Continue reading “Contrary View: Chatbots Don’t Help Programmers” →

Parametric Design With Tinkercad

April 26, 2023 by Al Williams 32 Comments

Tinkercad is like the hamburger helper of 3D design. You hate to admit you use it, and you know you should put in more effort, but — darn it — it’s easy, and it tastes pretty good. While I use a number of CAD programs for serious work, sometimes, when I just want a little widget like a flange for my laser cutter’s exhaust, it is just easier to do it in a few minutes with Tinkercad. However, I heard someone complaining the other day that it wasn’t of any use anymore because they took away custom shape generators. That statement is only partially true. Codeblocks allow you to easily create custom parametric items for use in Tinkercad.

There was a time when you could write Javascript to create custom shapes, and it is true that they removed that feature. However, they replaced it with Codeblocks which is much easier to use for their target audience — young students — and still very powerful.

If you’ve used parametric design in a professional package or even used something like OpenSCAD, you probably don’t need to be sold on the benefit. This is, of course, a simple form of it, but the idea is to define things as mathematical relationships. As an example, suppose you have a front panel with two rows of four holes for switches evenly spaced and centered. That would be easy to draw. But if you later decide the top row needs five holes and the bottom only needs three, it will be a fair amount of work. But if you have the math defining it right, you change a few variables, and the computer does the rest. Continue reading “Parametric Design With Tinkercad” →

How Much Programming Can ChatGPT Really Do?

March 25, 2023 by Bryan Cockfield 50 Comments

By now we’ve all seen articles where the entire copy has been written by ChatGPT. It’s essentially a trope of its own at this point, so we will start out by assuring you that this article is being written by a human. AI tools do seem poised to be extremely disruptive to certain industries, though, but this doesn’t necessarily have to be a bad thing as long as they continue to be viewed as tools, rather than direct replacements. ChatGPT can be used to assist in plenty of tasks, and can help augment processes like programming (rather than becoming the programmer itself), and this article shows a few examples of what it might be used for.

AI comments are better than nothing…probably.

While it can write some programs on its own, in some cases quite capably, for specialized or complex tasks it might not be quite up to the challenge yet. It will often appear extremely confident in its solutions even if it’s providing poor or false information, though, but that doesn’t mean it can’t or shouldn’t be used at all.

The article goes over a few of the ways it can function more as an assistant than a programmer, including generating filler content for something like an SQL database, converting data from one format to another, converting programs from one language to another, and even help with a program’s debugging process.

Some other things that ChatGPT can be used for that we’ve been able to come up with include asking for recommendations for libraries we didn’t know existed, as well as asking for music recommendations to play in the background while working. Tools like these are extremely impressive, and while they likely aren’t taking over anyone’s job right now, that might not always be the case.

The International Space Station Is Always Up There

March 15, 2023 by Bryan Cockfield 9 Comments

Thanks to its high orbital inclination, the International Space Station (ISS) eventually passes over most inhabited parts of the Earth. Like other artificial satellites, though, it’s typically only visible overhead during passes at sunrise and sunset. If you’d like to have an idea of where it is beyond the times that it’s directly visible, take a look at this tabletop ISS tracking system created by [dpelgrift].

The tracker uses an Adafruit Feather inside its enclosure along with a Featherwing ESP32 WiFi co-processor. Together they direct a 3D printed rocket-shaped pointing device up and down by way of a SG90 micro-servo, while a 28BYJ-48 stepper motor provides rotation.

This setup allows it to take in all of the information required to calculate the Station’s current position. The device uses the current latitude and longitude, as well as its compass heading, and combines that with data pulled off the net to calculate which direction it should be pointing.

While it might seem like a novelty or programming challenge, this project could be useful for plenty of people who just want to keep track so they know when to run outside and see the Station pass by, or even by those who use the radio repeater aboard the ISS. The repeater on the ISS and plenty of other satellites are available to amateur radio operators for long-distance VHF and UHF communication like we’ve seen in projects like these.

Modernizing C Arrays For Greater Memory Safety

February 10, 2023 by Al Williams 75 Comments

Lately, there has been a push for people to stop using programming languages that don’t promote memory safety. But as we still haven’t seen the death of some languages that were born in the early 1960s, we don’t think there will be much success in replacing the tremendous amount of software that uses said “unsafe” languages.

That doesn’t mean it’s a hopeless cause, though. [Kees Cook] recently posted how modern C99 compilers offer features to help create safer arrays, and he outlines how you can take advantage of these features. Turns out, it is generally easy to do, and if you get errors, they probably point out unexpected behavior in your original code, so that’s a plus.

We don’t think there’s anything wrong with C and C++ if you use them as you should. Electrical outlets are useful until you stick a fork in one. So don’t stick a fork in one. We really liked the recent headline we saw from [Sarah Butcher]: “If you can’t write safe C++ code, it’s because you can’t write C++.” [Cook’s] post makes a similar argument. C has advanced quite a bit and the fact that 30-year-old code doesn’t use these new features isn’t a good excuse to give up on C.

Continue reading “Modernizing C Arrays For Greater Memory Safety” →

Create A Compiler Step-By-Step

November 27, 2022 by Al Williams 19 Comments

While JavaScript might not be the ideal language to write a production compiler, you might enjoy the “Create Your Own Compiler” tutorial that does an annotated walkthrough of “The Super Tiny Compiler” and teaches you the basics of writing a compiler from scratch.

The super tiny compiler itself is about 200 lines of code. The source code is well, over 1,000 but that’s because of the literate programming comments. The fancy title comments are about half as large as the actual compiler.

The compiler’s goal is to take Lisp-style functions and convert them to equivalent C-style function calls. For example: (add 5 (subtract 3 1) would become add(5,subtract(3,1)).

Of course, there are several shortcut methods you could use to do this pretty easily, but the compiler uses a structure like most full-blown modern compilers. There is a parser, an abstract representation phase, and code generation.

Continue reading “Create A Compiler Step-By-Step” →