The proposed feed solution looks a lot like the CouchDB replication protocol, as another object in a convergent evolution space to consider.

Using conventional explosives is a real thing that exists: https://en.wikipedia.org/wiki/Explosion_welding

Using the Project Orion spacecraft to get there, of course.

https://en.wikipedia.org/wiki/Project_Orion_%28nuclear_propu...

This alloy is naturally the macguffin in a Godzilla and/or Sentai film.

You avoid people problems by interviewing soft skills as soft skills, not building elaborate mazes of "technical interviews" that are really soft skill interviews testing how pedantic you want to be or how much you want candidates to sweat in soft skill-dominant conditions that don't resemble your job that you are hiring for.

I had an interviewer once interrupt me and say there was no way I would have studied gray codes in college. I still don't know if that was some bias that I went to a "provincial school" in their mind or that they hadn't noticed my Master's degree or that my degree program also involved a lot of hardware and electronics work or just that they didn't study it in college and were secretly telling me how useless their fancy "West Coast Ivy" degree program was for them.

I made the mistake of letting that company bring me back for a second "less technical" round of interviews, but I shouldn't have.

The big one on the list that wasn't AT&T was microwaves and that was a contractor to Nasa [0] in the heat of the moon race and a similar "Do stuff. Then we'll see if we can use it" mandate.

[0] Defense contractor Raytheon most specifically.

I think that's one thing people truly forget when they ask "Why can't we do things like this anymore?"

AT&T paid people to fuck around. Claude Shannon, father of Information Theory, founder of Artificial Intelligence, and namesake to Anthropic's flagship product, was also busy building flame-throwing trumpets and rocket frisbees while creating entire new fields.

So why can't I order a rocket frisbee today? Wtf America.

Depends on the company. The US maintains no requirements, federal holidays are a suggestion, not a mandate.

A few states inside the US upgrade federal holidays to state holidays to required paid time off. Most don't.

In the US paid holidays are a corporate "tradition" more than a regulated common good.

Even US federal employee holidays vary between agencies and branches of government.

I think that LLM's are a broken mirror or maybe disco ball. What you get back is almost always a reflection of what you put in, just garbled through and with the reflections of so many other people. The best parts that I often get back are mostly just the stuff that I already put in it.

I think that's also where LLMs get the most dangerous. That ELIZA effect of telling you exactly what you told it but in a slightly rephrased way makes you think that you think that your ideas are genius. You've got someone "actively listening" and telling you whatever idea you just gave it was the best idea it ever heard.

That's not what you want from a serious writing partner. You want a writing partner to challenge you, to point out your mistakes and flaws, to make you better, to offer a truly different perspective to your own. You don't want a dark reflection from a "yes man" to spiral into.

I think it is a net positive for me, because I am super unconfident by nature and the agreeable, almost sycophantic output from major LLMs give me just enough of a boost to debias me. They are certainly better than a physical rubber duck.

I feel it is a net negative for me. One of my hobbies has always been fiction writing. The LLM reflections of my own writing become slot machines to me for cheap dopamine hits. It's not because LLMs are good at fiction writing, far from it, it's that LLMs are good at reflecting my own writing back to me in fun house mirror ways that amuse me and frustrate me and pleasantly surprise me.

That slot machine addiction gives me a lot of perspective on what LLMs are good at in coding versus what they appear to be good at. It's easy to characterize them as "over-eager junior developers" or "powerful rubber duck debuggers" but their biases are still your biases so long as you are the one writing the prompts. A lot of the "surprises" aren't intelligence but fun house mirror versions of the same biases you input into the system.

I keep referring to their coding capabilities as "legacy code as a service" and the addiction to the fictional equivalent only underscores that understanding of LLMs. You don't write the next great American novel getting a word salad of past great novels back full of the best and worst of your own writing. You don't write the next great American software getting a legacy code jumble of past great software back full of the best and worst of your own prompting.

At the end of the day I'm still a pragmatist and using the LLMs in my programming efforts, but I don't trust them as a partner, I use them as a tool. (A biased tool that I know needs a careful eye.)

> but their biases are still your biases so long as you are the one writing the prompts.

That is if you only work with your LLMs / Agents in a "straight ahead" manner, versus using knowledge of the bias baked into AIs and purposefully invoking a specific type of subject matter expert for problems that require specialized knowledge. It is similar to using people skilled at what you need, invoke through the vocabulary and language of your prompts specialized skills that are not tapped until using the terminology only those specialists use, and like magic their skills are suddenly in-context and the AI acts accordingly.