whattheheckheck

Who is signing off on the correctness?

Nice the next level up is automating where that data got produced from. Hopefully it's correct

You can run to the farm to kill your own chicken so you can stay sharp and fit or figure out what's economically valuable. Or make a bet on what will be valuable later and commit to a brand of yourself

Regression to the mean of shitty monarchy bullshit in the grand scheme of things

Nice im interested

Yeah it can...

Do you have any github examples publically available?

If you find yourself getting irritated and physically agitated over language I suggest you do a 5 why analysis on yourself and seek therapy

Who is we? Own your insults and the consequences of them sir.

When prompting an autoregressive token generator entity to do reasoning on a word logic puzzle you may find value in preferring it to produce rigorous predicate logic step notation with explicit delineation of its generated claims/hypotheses on where to look before wasting 30 dollars on a "debug this" prompt.

The industry will probably will probably coalesce around including the chat history in git MRs to reduce this shenanigans.

Thr future of programs

Why did we even need bridges in the first place

Ask the ai what the game theory is for training employees... the Nash equilibrium is under training and self funded certification/training for devs in low trust environments.

https://arxiv.org/abs/2606.16475

Pretty sure it can dumb it down to cave man speak for any concept

What do you think the avg execs info exposure is to what's really happening

What do you do when people say "my self agent harness set of .md can build more stuff faster better and cheaper than your collection?"

Is it really hooking it all up to swebench and letting it rip / cost money?

Its going to get really annoying having to argue about this stuff for real for work when anyone can propose some loop and now the question pops up on what makes it better and what makes it worse. Who knows? Try it and see?

Im wondering if you can expand it using TLA+ some how. I like the declarative language that compiles down to langgraph idea. Langgraph or hamilton/burr are two strong contenders for state machines. Maybe mix dbos or Temporal in there and you could almost have something to full declare the whole system

And people clutch their pearls at ai not really understanding anything when people describe university experiences and lessons like this...

Have you seen marp? https://marp.app/

Why not just make an actual terraform module?

Ai guys would get torn apart by any sane copyright legal system. They have to go all in on the political favoritism play. They stole the content from the commons and continue to resell laundered IP via tokens

Because these models are not going to stand up legally

Can you share what other "sucky tools" would be on the same level? I understand they do kind of suck holistically but to explain it better to laymen how would you describe the whole thing?

Who is we?

They can slap it into ai and get the answer if they cant think of it themselves

Moderation in everything... including applying the phrase moderation in everything...

Yeah do people not know how to do deep knowledge work? Look up Cal Newport habits

You may be wise beyond your years and are sitting on a goldmine of consulting opportunity if you can actually get tasks done faster without ai given the exact same inputs

"Extremely bad"? What are the actual material consequences of the decision? Relate it to business outcomes

What do you prefer?

Yeah seriously what's the test of maintainable that couldn't be applied to the word clean?

What about the latest book Tidy First https://a.co/d/0b1hRqEV