• 0 Posts
  • 193 Comments
Joined 1 year ago
cake
Cake day: September 9th, 2023

help-circle
  • I thought it was supposed to be an infinite amount of monkeys, since it’s known as “infinite monkey theorem”, but apparently, according to Wikipedia,

    The infinite monkey theorem states that a monkey hitting keys at random on a typewriter keyboard for an infinite amount of time will almost surely type any given text, including the complete works of William Shakespeare. […]

    […] can be generalized to state that any sequence of events that has a non-zero probability of happening will almost certainly occur an infinite number of times, given an infinite amount of time or a universe that is infinite in size.

    However, I think, as long as either the timeframe or monkey amount is infinite, it should lead to the same results. So, why even limit one of them on this theoretical level after all?

    The linked study even seems to limit both, so they’re not quite investigating the actual classic theorem of one monkey with infinite time, it seems.
















  • And even in some prototype bus, the Gyrobus, in the 50’s that used an electrically charged flywheel that was also (to some degree) regeneratively recharged when breaking:

    Rather than carrying an internal combustion engine or batteries, or connecting to overhead powerlines, a gyrobus carries a large flywheel that is spun at up to 3,000 RPM by a “squirrel cage” motor.[1] Power for charging the flywheel was sourced by means of three booms mounted on the vehicle’s roof, which contacted charging points located as required or where appropriate (at passenger stops en route, or at terminals, for instance). To obtain tractive power, capacitors would excite the flywheel’s charging motor so that it became a generator, in this way transforming the energy stored in the flywheel back into electricity. Vehicle braking was electric, and some of the energy was recycled back into the flywheel, thereby extending its range.

    Source: Wikipedia: Gyrobus




  • Altering the prompt will certainly give a different output, though. Ok, maybe “think about this problem for a moment” is a weird prompt; I see how it actually doesn’t make much sense.

    However, including something along the lines of “think through the problem step-by-step” in the prompt really makes a difference, in my experience. The LLM will then, to a higher degree, include sections of “reasoning”, thereby arriving at an output that’s more correct or of higher quality.

    This, to me, seems like a simple precursor to the way a model like the new o1 from OpenAI (partly) works; It “thinks” about the prompt behind the scenes, presenting only the resulting output and a hidden (by default) generated summary of the secret raw “thinking” to the user.

    Of course, it’s unnecessary - maybe even stupid - to include nonsense or smalltalk in LLM prompts (unless it has proven to actually enhance the output you want), but since (some) LLMs happen to be lazy by design, telling them what to do (like reasoning) can definitely make a great difference.