Viewing profile — Muromec

>Yes but your 8 hours of work will serve more people. I work in place that serves about the third of a population of a small country and I highly doubt the advances in technology f…

Our CEO generously offered generous 1% yearly salary adjustment to the trade unions, an RTO mandate and a plan to reduce the number of employees by 20% in a few years, despite havi…

>The conflict in that case (and, I think AI) came about not from the technology or its advancement, but the use of that technology for class warfare by capitalists. Does this disti…

I think it gets lost in a translation somewhere. If it's boring technology, why be excited about it? I respect boring technologies and don't believe in the end of the world christi…

Only an order of magnitude? I'm both surprised by both the fact it's so low and the fact 1900 is 3x of 1800.

(not a native speaker) fired up as in "optimistic and enthusiastic about the new messiah" or as in "Butlearian jihadi, all AI is haram" way?

Thank you for your service to community, dear stranger. o7

I haven't considered looking at it from the security thread angle. Can you expand on this?

We don't go that far. From the small sample I saw, I noticed that people who can't answer the basic questions are ones that can't use AI effectively either and don't understand tha…

It signals you don't have enough time or will to chase the latest stuff, otherwise you would have learned it with other cool kids half a year earlier. It carries some signal, but I…

The most fun part being seeping through stderr of tsc and restarting the unit test runner after realigning some assumptions.

>It’s pretty typical stuff that you might expect an experienced engineer to do if they effectively use such tools daily. It's also the kind of stuff that somebody can learn in a we…

I was on the interviewer side last month. We stopped giving take-home assignments because they don't produce a signal anymore. We explicitly said -- feel free to use whatever frame…

They still have to bother with actually going to a judge and actually getting that warrant. Why do that if you can just skip it and not deal with inconvenient questions.

You can, but its not the first preference

If you would tell people at the start of 20th century how much energy we consume, they may not believe you or think it is wasteful.

But like any other CEO he can't get in jail, so who's laughing now?

>LLMs don't have agency, or desires of their own. LLM doesn't, but LLM is one part of what can be perceived as AI. Harness and context are the other two. I would even say that LLM …

By the time it does 10 turns of tool calls it forgets about the nagging again. It can and does ignore direct instruction from the user prompt too, sometimes repeatedly

>In this case, it is an advisory control only, because the LLM can also unhook that hook you can in principle make a hook in the harness itself that will run an auditor prompt that…

If the harness runs on your localhost, but the inference doesn't, it usually means it's calling some API. Whether you want to break TOS of your provider like that or simply buy tok…

Ourselves. Always be threatening yourself to not be surprised by unavoidable.

Oh, it would likely be my shit that will be burning and my property to be taxed in the event of. What I'm saying is -- if the system degrades to a state that only responds to eithe…

The trick I'm doing -- the model is given a tool that runs a prompt in the current thread to consolidate it's working memory and identity (it has a memory tool bound to the agent p…

Ask it to come back with a filled checklist and hand it over to a different agent with a fresh context window (three lines model). Or make it collapse the context and get back to t…