JetSetIlly

I think the split is between people who are in a hurry and those who are not. I'm not in a hurry and so choose not to spend money to get a quicker result.

Taking time to solve a problem myself is pleasurable and I make no apologies for that.

Horses for courses.

Cool. This is how I imagine the ants were programmed by the spiders in Children of Time.

I've heard people say that these coding agents are just tools and don't replace the thinking. That's fine but the problem for me is that the act of coding is when I do my thinking!

I'm thinking about how to solve the problem and how to express it in the programming language such that it is easy to maintain. Getting someone/something else to do that doesn't help me.

But different strokes for different folks, I suppose.

"Any terminal tool like Claude Code or Codex (I assume OpenCode too, but I haven't tried) can do it, by using as a prompt pretty much exactly what you wrote, and if it still wants to edit, just don't approve the tool calls."

I'm sure it can. I'd still like a single use tool though.

But that's just my taste. I'm very simple. I don't even use an IDE.

edit: to expand on what I mean. I would love it if there was a tool that has conquered the problem and doesn't require me to chat with it. I'm all for LLMs helping and facilitating the coding process, but I'm so far disappointed in the experience. I want something more like the traditional process but using LLMs to solve problems that would be otherwise difficult to solve computationally.

"All of them are moving into the direction of "less human involved and agents do more", while what I really want is better tooling for me to work closer with AI and be better at reviewing/steering it, and be more involved."

I want less ambitious LLM powered tools than what's being offered. For example, I'd love a tool that can analyse whether comments have been kept up to date with the code they refer to. I don't want it to change anything I just want it to tell me of any problems. A linter basically. I imagine LLMs would be a good foundation for this.

The golang.org/x/ namespace is the other half of the standard library in all but name. That gets iterated often.

For stuff in the standard library proper, the versioning system is working well for it. For example, the json library is now at v2. Code relying on the original json API can still be compiled.

"These things are not intelligent. They're just tools."

Correct. But they are being marketed as being intelligent and can easily convince a casual observer that they are through the confidence of their responses. I think that's a problem. I think AI companies are encouraging people to use these tools irresponsibly. I think the tools should be improved so they can't be misused.

"Incidentally, those structures are also the sorts of things that greatly benefit human programmers."

Correct. And that's why I have testing in place and why I used it to show that the race condition had been introduced.

"Okay. If you’re being vague, you get vague results."

No. I was vague and got a concrete suggestion.

I have no issue with people using Claude in an optimal way. The problem is that it's too easy to use in a poor way.

My example was to test my own curiosity about whether these tools live up to the claims that they'll be replacing programmers. On the evidence I've seen I don't believe they will and I don't see how Go is any different to any other language in that regard.

IMO, for tools like Claude to be truly useful, they need to understand their own limitations and refuse to work unless the conditions are correct. As you say, it works best when you tell it precisely what you want. So why doesn't Claude recognise when you're not being precise and refuse to work until you are?

To reiterate, I think coding assistants are great when used in the optimal way.

I do have a test harness. That's how I could show that the code suggested was poor.

If you mean, put the LLM in the test harness. Sure, I accept that that's the best way to use the tools. The problem is that there's nothing requiring me or anyone else to do that.

I accept what you say about the best way to use these agents. But my worry is that there is nothing that requires people to use them in that way. I was deliberately vague and general in my test. I don't think how Claude responded under those conditions was good at all.

I guess I just don't see what the point of these tools are. If I was to guide the tool in the way you describe, I don't see how that's better than just thinking about and writing the code myself.

I'm prepared to be shown differently of course, but I remain highly sceptical.

Interesting. I've only dipped my toe in the AI waters but my initial experience with a Go project wasn't good.

I tried out the latest Claude model last weekend. As a test I asked it to identify areas for performance improvement in one of my projects. One of the areas looked significant and truth be told, was an area I expected to see in the list.

I asked it to implement the fix. It was a dozen or so lines and I could see straightaway that it had introduced a race condition. I tested it and sure enough, there was a race condition.

I told it about the problem and it suggested a further fix that didn't solve the race condition at all. In fact, the second fix only tried to hide the problem.

I don't doubt you can use these tools well, but it's far too easy to use them poorly. There are no guard rails. I also believe that they are marketed without any care that they can be used poorly.

Whether Go is a better language for agentic programming or not, I don't know. But it may be to do with what the language is being used for. My example was a desktop GUI application and there'll be far fewer examples of those types of application written in Go.

This is a timely article for me. I was consulting Joe Decuir's Engineering Notebooks just yesterday and wondered if these sorts of notebooks were a common thing or whether it was just Atari.

Joe Decuir was an engineer at Atari and was involved with the development of the 2600. His notebooks can be useful references for the 2600, even to this day.

https://archive.org/details/JoeDecuirEngineeringNotebook1977

https://archive.org/details/JoeDecuirEngineeringNotebook1978

I understand the issue is that Anthropic is not adhering to a standard. I was simply asking whether it's possible to solve the problem created by Anthropic in the way I was asking.

I've never used Claude or anything like it so this may be a dumb question: could you solve this problem by having a CLAUDE.md file that simply says to use AGENT.md if one is available. Can an AI agent not do that?

I'm the exact same demographic as the author, just turned 50, writing code since childhood in BASIC. I'm dealing with the AI in programming issue by ignoring it.

I still enjoy the physical act of programming so I'm unsure why I should do anything that changes that. To me it's akin to asking a painter to become a photographer. Both are artists but the craft is different.

Even if the AI thing is here to stay, I think there will be room for people who program by hand for the same reason there's still room for people who paint, despite the invention of the camera.

But then, I'm somebody who doesn't even use an IDE. If I find an IDE obtrusive then I'm certain I'll find an AI agent even more so.

Yes. When accounting I use a cheap calculator to do quick sums. Easier than using a calculator on the computer desktop.

Not really. Von Daniken talks about ancient aliens. Hancock talks about ancient human civilisations.

By default, all go mod downloads go through the golang proxy (https://proxy.golang.org/). That is part of the verification process.

True. Maybe we experience jumps in time and location in our dreams because we've been conditioned to it by films.

> Films are more like dreams than like real life.

Yes! The other happy accident of movies that contribute to the dream-like quality, besides the lower frame rate, is the edit. As Walter Murch says in "In the Blink of an Eye", we don't object to jumps in time or location when we watch a film. As humans we understand what has happened, despite such a thing being impossible in reality. The only time we ever experience jumps in time and location is when we dream.

I would go further and say that a really good film, well edited, induces a dreamlike state in the viewer.

And going even further than that, a popular film being viewed by thousands of people at once is as though those people are dreaming the same dream.

Yes, even if it's not a legal requirement it's definitely best practice to have sequential invoice numbers. I thought about this at the time but these numbers aren't invoice numbers, only order numbers.

In a business I once worked for, one of the users of the online ordering system represented over 50% of the business' income, something you wouldn't necessarily want them to know.

However, because the online ordering system assigned order numbers sequentially, it would have been trivial for that company to determine how important their business was.

For example, over the course of a month, they could order something at the start of the month and something at the end of the month. That would give them the total number of orders in that period. They already know how many orders they have placed during the month, so company_orders / total_orders = percentage_of_business

It doesn't even have to be accurate, just an approximation. I don't know if they figured out that they could do that but it wouldn't surprise me if they had.

A couple of threads on AtariAge are exploring the possibility of using the "unstable" opcodes in this group (ARR, etc.) as a sort of fingerprint. The hope is that the instability is a prediction of the specific model of CPU. To what end I'm not sure of yet, but it's interesting research all the same.

https://forums.atariage.com/topic/385516-fingerprinting-6502... https://forums.atariage.com/topic/385521-fingerprinting-6502...

The problem with DRS is the zones and only being able to use it when close behind another car. My understanding is the X-Mode can be used pretty much anywhere and anytime.

One of his less famous works is a audio play based heavily on Pink Floyd's Dark Side of the Moon. A recommended listen. https://en.wikipedia.org/wiki/Darkside_(radio_play)

The Hopkins Manuscript by R.C. Sherriff is one of my favourites on that list.

I suspect HiFi culture was slightly different in different parts of the world.

In my part of the world, the original HiFi guys rejected the EQ units. I was influenced by that I think (my father was an original). I still have a metre high stack of HiFi, in almost daily use, and have never felt the need to have an EQ unit.

Maybe it doesn't make it any easier but your question does remind us that cataloguing and categorising people can be dangerous. I accept that there are good reasons that the state could use this information, but we should also be alert to possible abuses.

Without looking, I honestly don't know if the passport and driving licence lists this information. But the census certainly does.

The census form in the UK requires disclosure of religion and ethnicity. It would be relatively easy to merge census data with ID.

I might trust this government not to do that, but I don't trust a future government (because I don't know who that will be).

Hopefully there will be. That will be a good solution for people like me, who want to live uncomplicated lives in peace.