I type fairly well. Well, I type fast, but I do wear out a backspace key relatively quickly on most keyboards. That and a space bar.
AI helps me deal with my issues in a way that I really like. This post looks at a small thing that I appreciate, and it’s why I wish I had a small local model running for more software.
This is part of a series of experiments with AI systems.
Searching for Posts
Today I was searching for some posts. I typed in something and found nothing.
Clearly, I mistyped something, but before I fixed this, I alt-tab’d over to Claude and tried a similar query. It worked much, much better.
Not perfect, as the search (corrected) on my site shows more posts.
In this case, what I really wish was that this search box (and lots of other software), were running a small model, not an LLM, but a SLM, that would interpret my poor typing and do what I want. Or ask me and remember what dumb mistakes I make all the time.
If an AI were powering the search, it would guess I mean “Monday” not “moday” and just run the appropriate search, get me all the results, and help me smooth out my day. Instead, I burned a few seconds looking at this, getting my brain to decode what search thing I’d mis-typed, and broke my concentration. I was thinking of a subject and had to change context to figuring out a search typo.
Not a big interruption, but an interruption nevertheless.
I typo things all the time. Git constantly asks me if “git stauts” is really “git status”, but it doesn’t just run that. I should re-enable autocorrect, but who has the time. Maybe I’ll ask Copilot to do that.
In any case, the sloppy mistakes, the implied context, these are things humans deal with well. We can overlook typos and even understand things that don’t look like words. I bet many of you know what this says.
“According to a researche [sic] at Cambridge University, it doesn’t matter in what order the letters in a word are, the only importent [sic] thing is that the first and last letter be at the right place.” – science alert
For most of my life, computers required being more exact, which was a struggle for many people. Search, led by Google, has helped, but it isn’t as good as an LLM, nor does this help in many pieces of software.
To me, this is one place a local LLM, watching what you type and doing a much better job than phone autocorrect, in all the place I type. That’s what Copilot should do. Fix my typing in software, in the CLI, and other places. Learn what I do and help me.
Right now, Copilot is not something I like, but I see AI potential for the future if they try to make it work well, and not just stuff it in there.
FYI, #@$#$#@$ Copilot didn’t do the work for me.
Voice of the DBA 
Steve – A little late to this one but better late than never.
In the past I’ve commented about concerns with AI and how its being marketed as something its not to do thing sit can’t and how foolish many in the business world are behaving as they drool at the notion of firing humans and replacing them with AI’s that will work for far less. Turns out the Ford Motor Co is already learning this lesson and their learning it the hard way which is how I fear most companies will have to learn.
Ford rehired about 350 veteran engineers and quality inspectors after automation and AI failed to match human expertise in catching vehicle defects. The company realized that simply feeding design rules into an algorithm could not replace the “gut instincts” and hard-earned wisdom of experienced workers. The company found that replacing seasoned professionals with AI led to significant issues. The machines simply could not identify the nuanced defects that veteran engineers spot easily. Ford is not getting rid of its automated systems entirely. Instead, the automaker is keeping the technology but requiring that it be strictly supervised and trained by human experts.
Ford has not disclosed the exact financial cost of building and deploying the underperforming AI systems, but executives admit the overall quality crisis tied to over-relying on automation cost the company billions of dollars. It cost Ford a few billion to learn something they could have learned for far less but greed is a hard characteristic to control especially with executives who often can not think past the next few quarters bonus. At least these lessons are being learned sooner rather than later. The proper way to use AI is a tool to assist humans, not to replace them.
LikeLike
Agreed. Likely they didn’t communicate well with the AI agents. Incomplete instructions or unclear ones. Communication is hard and Ford thought they were doing a good job, but it’s easy to forget how much context and knowledge humans have.
AI is a great assistant. Even if it gets a lot smarter, it will still need the context from experience.
LikeLike