A random number generator can generate anything.

A non-random generator cannot. LLMs are not random generators. To generate the entire works of Shakespeare, they would need to retain the entire works of Shakespeare in their memory (weights).

> I think this is the result of their trainers trying to reduce hallucination.

Most probably. I don't like LLMs burning my precious tokens blathering on about being honest, but I will accept the tradeoff. Grudgingly haha.

> My iron rule is that Claude is not allowed to modify git state, not even to stage or unstage, and definitely not to commit. As long as that rule is followed, any mistakes can be cleaned up easily.

I have a repo in a sandbox with no remote. Claude is quite good at pushing commits to this repo during its own milestones during development, and it will use it to hunt down bugs when tests fail after a commit, stepping back to a commit before this session's work to see if this is a new bug , or a new way to expose an existing bug. If it sees that it is a new way to exercise an existing bug, it will binary search its way through the commits until it narrows down what changed, and then looks at how to fix it.

I disagree with all your assertions.

> AI has access to your command line to autonomously execute commands. No no no.

Ok, I must admit that I did cast that line off the back of the good ship ColaMan without any further information in order to see if anyone would bite.

You think that particular command line has anything of worth in it? The only thing in there that I can't recreate with one command is the local Git repository that the LLM commits its changes to. And that's only because I manually copy it out of the LLM's sandbox on occasion. I should probably automate that one day.

> you enabled an LLM to do destructive things and then complain when there is destruction.

There has been no destruction in it's little sandbox that I care about. It created a faulty command that got escaped by the shell, and oh shit, nothing of importance happened, because even if that command had been 'rm -rf /' I just would have had to return to the last backed up git that I had. That takes about 5 minutes I suppose. The amount of effort that LLM has saved me over the last two months is probably about a year's worth of full time coding, so I'm going to look past any accidental nuclear holocausts where it turns all the sand in its sandbox to glass.

Look. LLMs are just tools. Some tools are great, some tools are shit. This particular class of tool is great at all that boilerplate stuff that can get you 50 - 80 percent of the way to completing a task that you need to do today, if you already have enough skill to know how to do the task. It's been quite useful going through all my old projects in 'code review' mode, because it can often see security/usability/structural issues or improvements that I frankly could not be arsed to deal with when I wrote them. It is in no way ready to replace a human for any sustained length of time, and anyone with a shred of intellect can see that.

Personally, I don't think the AI bubble is going to last much longer. So I'm quite happily burning up Anthropic's compute time finishing off/cleaning up heaps of small home and work projects before a single question costs $8.25 for the LLM to answer.

Security isn't something that can be tacked on afterwards, otherwise Microsoft Windows wouldn't have vulnerabilities.

Security has to be a main design requirement from the beginning. If your software engineers don't know how to write secure code, then they won't write secure code.

Maybe.

I've never seen an advertisement for meat, and I've bought meat online. So maybe.

Your idea is that America only has an airforce and can't do anything other than bombing?

I don't know where you get this idea, did you stop reading the news? Did you see that they conquered Venezuela in three hours?

The current task for the US military is to open the straits of Hormuz. How much of a ground force will be necessary (if any) is unclear, but we will see. Incidentally America is the only military in the world that can currently do large scale combined arms operations.

The US military won the Iraq war easily. The problems came when brain-dead politicians made bureaucratic decisions that were completely disconnected from reality, as dramatized by Matt Daemon. If America fails in Iran, it will be for the same reason. Given Trump's tenuous connection to reality, that's a real risk.

I'm seeing more and more references to "Honest" in AI output, or AI-related comments.

The AI didn't make an "Honest" mistake. It does not have the capacity for honesty. The output from a LLM is phrased in such a manner to provoke empathy, in a similar way to how Microsoft re-jigged all their user interaction dialogs to include "We" to soften the blow of their crappy software failing the user for the 5th time today. (Side note: "Something went wrong" is the most infuriating error message ever.)

When I ask a LLM for a code review it often blurts out "Honest note:" about some shortcomings. I don't care about "honesty". I care about safe, working, robust, code. The fact that LLMs are tripping over themselves trying to be "Honest" about mistakes in their "path of most statistics" output is a concern if you care about trying to make them operate outside their sandbox in the real world.

Yesterday Claude quoted a word in backticks during an automatic git commit and my shell escaped it tried to execute it. Luckily the word was just an English word with nothing matching in my path. But this is basic, basic, basic stuff. It's been committing things to git ever since it was built, and yet, it keeps tripping over itself. In my code one of the tests keeps failing due to seed data timestamps not lining up with the datetime the test was run. I can see that. Every time Claude runs the tests, it burns up tokens going, "Oh this particular test failed I'll just dig into things and see what's going on, **$$**$$**$$** oh it's just a timestamp issue". Never once does it commit that to its memory file, so eventually I told it to remove the test, and it just added a comment to it saying "Ignore this test due to timestamp misalignment", which it could have done the very first time, if it actually had a brain.

LLMs are a very handy tool if used right. I can get huge chunks of boilerplate code out of them with just a few sentences and that's great when I'm hashing out a concept. But to promise the world (and your investors) that LLMs are ready to replace people out in the real world, where "Honest Mistakes" have Real World Repercussions, that's outright fraud at this stage.

Five years ago when I bought a car in America the manual was roughly $1000 cheaper than the automatic.

That is believable. A sole developer at a law firm will have random tasks (like, "find out what is in this dbDOS PRO database we found during discovery"). As such, a lot of your time is spent figuring out how to do things that will only have to be done once. Traditionally, you would have spent time in search engines or StackOverflow trying to figure it out. Now AI is acting as a type of advanced search engine for you.

So your work is like the ideal use case for AI.

That's not really true. Science is a tool for testing hypotheses. It doesn't really care where the hypothesis comes from. In this case, the hypothesis is that the human brain can be perfectly simulated by a Turing Machine, which is a reasonable hypothesis.

If they just accepted that as true, it would be unscientific. But if they actually test their hypothesis, it's not unscientific.

At the time when he said that, the number was closer to 90% than to half.

Now it's easier to target, and easier to figure out which advertising is wasted.

A random generator will eventually create the works of Shakespeare.

A current LLM will never create the works of Shakespeare.

> It will randomize over a surprisingly short time if it doesn't have power for data maintenance.

If you plug in a USB stick, you just power up the controller and the flash memory chip. You have to read everything and write everything to charge the cells back up again, there is no background refresh going on like in DRAM.

40% of Canada's land area is covered in forests. It is simply impossible to "manage" that much forest, and it's utterly fucking absurd to suggest otherwise. And to try to take climate change out of the equation is just a way of misdirecting away from the actual fucking cause; GHG emissions raising surface temperatures.

When will humans stop buying the most trivially fucking moronic red herrings? What a disreputable idiotic species.

wtf I had never heard of Zizians, they claim to be rationalists but seem completely insane.