Info:

  Location: Ottawa, Canada
  Remote: Yes
  Willing to relocate: No

  Technologies: Recently a lot of Typescript/Javascript, PHP.  Web and mobile development, both frontend and backend.  I have a lot of Java and C# under my belt, but it's getting a bit dated and I kinda miss it.

  Résumé/CV: https://plaintextdev.com/wp-content/uploads/2026/10/James-Beninger-Senior-Full-Stack-Software-Developer.pdf
  Email: james@plaintextdev.com

A senior developer with 20 years of experience. I've built enterprise software for the Canadian government, worked at TripAdvisor on the review-processing team, and I've been freelancing for about a decade. I've become an expert at taking a design and making it work on real devices, but I'm also the guy people call when their in-house developers can't figure something out.

I'm looking for regular remote work, and I'd be happy to discuss any short-term freelancing positions as well. If you need a guy who can just do the thing, I'm your guy.

It's possible I invented skills before they were common. I've always had some instructions in agents.md that are something like "when working with typescript, read prompts/conventions.ts.md, when working with our fooBar module, read prompts/foobar.md"

I'm not sure if this differs greatly from skills. Maybe my wording makes these "skills" less likely to be read at the correct times, but I haven't seen an issue.

I'd be worried the standard wouldn't include my favourite carplay feature, where it plays the same song from my phone on startup no matter how I configure it.

If you decuple the vehicle features from infotainment you get infinite possibilities. You can get anything you want within the HW constraints of the car .. so you could probably get a device to do whatever you want and even multiple vendors supporting CarPlay.

That's not a generator tell when used judiciously. It's a genuinely useful construction that's been poisoned by overgeneration.

That's the flaw in RLHF: constructs tagged as effective or sophisticated speech become templates, are increasingly used out of context (e.g., "not just A, not just B, but C" is usually meant to provide some synthesis and further the progress of the text) and suffer from significant overexposure. (And gone is the em-dash…)

I think the grating one is that it's constructed to sound effective when it shouldn't!

Good points should be rewarded confidence. I read so many not X it's Y where the distinction beteeen X and Y isn't relevant to the discussion!

It's bad in and of itself the way LLMs use it. They separate it into a weird declaration when it's usually something you'd say at the beginning and/or end of a paragraph or passage where you're making a case for that statement.

It's part of how LLMs often seem to repeat the same thing over and over again. Most arguments are X is Y (and the others are X is not Y, or X is likely Y), and LLMs lean on "X is Y" because it is the most distilled form of that argument - a thesis minus the meat. Also "This is not a Y, this is a Z."

They're just thesis sentences inserted in inappropriate locations. The reason it makes them overdramatic is because separated from the argument, they seem like they should be premises. Conclusions without premises have the feeling of demands.

Lose anonymity and bring back key-signing parties. Maybe you can't guarantee that everything is human-generated, but at least you know the chain of trust that leads to the human that signed off.

Yes, I'm aware of the irony of creating a darknet that only works by removing anonymity.

Aka altman's world coin. I'm sure this darknet infra and party beer will be sponsored by mysterious people who turn out to be LLM companies and investors.

I think an invite system like lobste.rs could be enough. Prune bots at common ancestors

As someone who spends way too much time searching for the best abstractions, absolutely this is still true.

I often have a long back and forth with codex to explore the problem space and settle on the best abstractions. Occasionally it will make a suggestion that helps me, but for the most part it's reviewing while I'm in the driver's seat.

Contrast this to simply giving it a function name and a vague description of what the function will do. I'll generally accept its output with a few refinements.

But for larger project structure and metaphors, it falls flat, and often lands on a solution that's going to be a maintenance nightmare or result in endless repetition across not-quite-the-same cases. I've never seen it happen upon an appropriate abstraction that can cleanly cut through the nonsense.

That's my experience too. Its unfair to expect current AI to do this - since good abstractions are extremely task specific. Hard to train on that.

What's also annoying is that AI's approach is not consistent within a project, a different sort of complexity.

Also, attacking good naming and structure belies their claim of knowing anything about dev at all. If you can't tell the quality difference between a well-structured program and spaghetti code consisting of single-letter variables, you don't belong in software.

Honestly, from the tone, I suspect the gp post is just trying to get a rise.

This analogy is one of the best I've seen. It's going to live in my head a long time, I think.