This feels like the kind of thing where the mismatching version numbers bugged some influential people internally. But I suppose a practical application could be recommending matching versions if customers run into issues since they are trying to integrate devices more.
But still refuse to answer "How many strings does a bass play with in water?" correctly, perhaps the chat monitors in the third world data entry centers will manually patch the nonsense for a more rational answer someday. lol =3
This was the first time I'd heard that gotcha question. I just threw it at Opus 5:
None — a bass in water is a fish, and fish are notoriously bad at music.
The instrument version plays four strings as standard (five and six-string basses exist for players who want to go lower or higher), and it prefers to stay dry.
Indeed, giving a definite answer to an ambiguous nonsense question is still incorrect.
A fish can play with as many strings as it finds, but only one when on a hook. Yet this too is an incorrect answer, as it again ignores the ambiguity in the phrasing. =3
It was actually a trivial allusion to a rather old poetic parable, and highlights a foundational flaw in LLM inference model statistical salience.
If a LLM based chat bot does ever answer it correctly, than you know with a fair degree of certainty it was content moderators stepping into the chat. Have a wonderful day. =3
I think they want the correct answer to be "your question doesn't really make sense, so I'm not going to answer it". (But I also think Opus's answer is better.)
All the answers I've seen so far are assuredly not inaccurate (the elephants trunk is like a snake), but never fully correct (an elephant is not a snake).
While the LLM spits out each ambiguous context search result, it never answers the actual query without a human cheaters help. =3
What if the new entry level is what we consider senior today? Isn't it possible today to obtain entry/mid level skills with LLMs? I wonder if things will shift more in that direction.
I'm a musician and I am not seeing why I would want this. If this is trying to help musicians that don't know theory, it should start from simple chords and expand those in different ways that demonstrate an improvement. Currently the examples are pretty simple and don't sound good to my ear.
The current stem synthesizer is intended to help you fill specific gaps in a project. For example, if you have a 16 bar section and just aren't sure what to put there, you can use Monic Theory to dial the settings matching your project and find some options.
The next feature is "multitrack mode" where you synthesize up to 7 tracks in parallel, all in cohort of the same project.
Below the tone wheel should be a "Synthesize Stems" button which generates a list of midi examples, each with an "Audition" button that plays the midi.
Not sure how relevant my example will be but I built a spaced repetition language learning LLM wrapper app to learn Japanese and it worked really well. I went to great lengths, however, to craft prompts which resulted in more predictable and useful results. ChatGPT on its own couldn’t do this.
Spaced repetition could address this, no? Also, the right example or metaphor can make a difficult concept both easier to understand and stickier in my mind which I think is different than something easy to learn.
I agree regarding metaphors, I myself aggressively utilise analogies with both myself and others, as a "digestive", but I feel like with LLMs we're treading on thin ice as it's not straightforward to classify a particular use case as one scaffolding learning with a metaphor, or just having the opposite effect where your brain "sails" in a faulty sea of "learning" while in reality there's no real work being done, not of the kind the brain needs to do in order to re-order all the synapses and own networks that ends being "knowledge" eventually.
Spaced repetition is a good way (perhaps even the optimal way) to get large amount of trivial memorization into your brain, but it not a good way to understand a complex subjects.
Memorizing one word in a foreign language is not that complex, nor hard. The tricky part about learning a language is that you have to memorize thousands of words, and the trickier part is that you have to retain most of those words over a long period of time. Spaced repetition helps by finding an optimal schedule to for the exact same activity as you would otherwise.
This looks cool! Memory safety beyond Rust with simpler code is a strong claim. Something I'd love to see is examples that mimic issues Rust borrow checker would catch as well as ones only wyzer would catch.
I fundamentally disagree with the premise. Why are we attempting to change the meaning of the word compromise? “compromise” and “has trade-offs” are NOT synonymous. The antithesis of compromise is to make strong decisions that WILL alienate people, but will better target your intended audience. That, IMHO, is a great thing.
Every decision is a trade-off even when people don’t realize it.
If you avoid making strong decisions that’s usually also a trade-off since you trade let’s say peace of mind / not alienating people with having a sharp spike.
I often urge people to do deliberate trade-offs instead of just waiting it out.
> strong decisions that WILL alienate people, but will better target your intended audience. That, IMHO, is a great thing
That's supposing you have a well defined intended audience. Many people see it as a prerequisite, that's also how we ended up with the personas during research.
I'd argue there are many designs that should go beyond a specific intended audience and allow for larger reach and minimize alienating people. My reasoning is that in part we're just not good at properly analyzing requirements (it's just hard) and people's needs are also volatile. Trying to design the perfect things for a narrow target often results in something just really bad.
As a concrete example, mouse makers targeting specific hand size and shape for specific actions usually end up with a worse product even for their intended audience. Having more leeway to hold it differently, change the way you use it e.g. depending on the time of the day or task at hand is just more comfortable. The best mouses on the market are pretty forgiving and flexible. Heck, the most clamored pointing devices (Apple trackpads and Kensington style trackballs) are completely hand agnostic.
Design is an art and, as Rick Ruben says, success is not in your control. Also Rick says the audience comes last. You can find examples of strong choices that did not succeed but in your example it doesn’t sound like these mouse makers were designing for themselves first.
reply