pedrosorio
https://jurgengravestein.substack.com/p/why-you-should-total...
> A recent study by the Institute of Software, Chinese Academy of Sciences, Microsoft, and others, suggest that the performance of LLMs can be enhanced through emotional appeal.
> Examples include phrases like “This is very important to my career” and “Stay determined and keep moving forward”.
Of course the top LLMs change every few months, so your mileage may vary.
https://en.wikipedia.org/wiki/Salvatore_Sanfilippo
This whole thread is hilarious.
I checked n=6...20. It looks like white wins for n=6 and n=8 with perfect play, otherwise it is a draw.
With random play, black seems to have the edge regardless of board size. About 2/3 of the games end in a draw, but black wins 20% and white 13%.
If they know what they're doing and it's not an exploratory task where the most efficient way to do it is by trial and error? Quite a few. Not always, but often.
That skill seems to have very little value in today's world though.
https://www.voronoiapp.com/energy/-China-Generated-More-Elec...
These are the same link
It's rarely the case that looking at school names is useful (for many things in life) when there are more data points.
In this case, without any insider knowledge, just by looking at their profiles, the relevant name would appear to be Benjamin Jeter (https://codeforces.com/profile/BenjaminJ) rather than ASU. Currently 5th active American in the top competitive programming platform, top 200 worldwide (https://codeforces.com/ratings/country/United%20States). That's elite.
In teams of 3, even one "super player" can make a big difference. Almost certainly carrying that team.
I guess, like a lot of other sports at the college level, having a reputation that attracts the best competitive programmers (and a great coach to go along with it) doesn't hurt: https://en.wikipedia.org/wiki/Andrey_Stankevich
What languages convey the version of the dependencies in a script’s import statements?
The “prove you’re special” motivation is definitely a strong third reason that does not align with the nepotism baby or monk archetypes
These models have proven to develop incredible abilities through pattern matching on massive text data, so I wouldn’t be too quick to dismiss the limits of what they could do.
Having them use specialized tools would probably be more effective (e.g. have the reasoning LLM use the DNA LLM), but in the long term with scale… who knows? The bitter lesson keeps biting us every time we think we know better.
Notice I am not talking about "rates of mistakes" (i.e. accuracy). I am talking about how confident they are depending on whether they know something.
It's a fair point that unfortunately many humans sound just as confident regardless of their knowledge, but "good" experts (lawyers or otherwise) are capable of saying "I don't know (let me check)", a feature LLMs still struggle with.
amount of data you'd need to learn to generate and cite fake court cases and give advice that may or not be correct with equal apparent confidence in both cases
fixed that for you
Should we not mimic migrating birds’ biology as closely as possible instead of trying to engineer airplanes for transatlantic flight that are only very loosely inspired in the animals that actually fly?
Regardless of your personal experience, if H1-B visas are currently allocated randomly to less than 50% of the applicants, then this is mathematically true.
Globally competitive in what sense, then?
This feels out of place. What did you do the first time?
Why do you need credentials to differentiate these two?
> In my opinion, this was a clear case of a programmer resisting the system approach because he wanted to spend time fixing the same problems over and over and pretend to be working hard
Which is funny when the first bullet point under "skills" in the author's resume [0] is:
> Team player mentality
I love working with "team players" like this.
[0] The "About me" page in website: https://latexonline.cc/compile?git=https://github.com/vitons...
Even in the simplest of applications where all you’re doing is passing “last user query” + “retrieved articles” into openAI (and nothing else that is different between users, like previous queries or user data that may be necessary to answer), this will be a bad experience in many cases.
Queries A and B may have similar embeddings (similar topic) and it may be correct to retrieve the same articles for context (which you could cache), but they can still be different questions with different correct answers.
It is to give you simplified toy problems that allow you to test your understanding of key concepts that you can use as building blocks.
By skipping those, and outsourcing “understanding” of the fundamentals to LLMs, you’re setting yourself up for failure. Unless the goal of the degree is to prepare you for MBA-style management of tools building things you don’t understand.
The point of o1 is that it's good at reasoning because it's not purely operating in the "giving a snap answer on the fly" mode, unlike the previous models released by OpenAI.