What credentials does this author have to cite social science research in their determination of the competency of other people? Their only other article is about eschewing native apps - why am I supposed to take their opinion about measuring competency seriously if they are a software engineer, not a psychologist? They are clearly outside of their domain of expertise and therefore incapable of producing work with any value whatsoever, according to their own arguments.
oh, believe me, I can just tell from the way they're talking about stuff, just like a webapp/psychology double major is well-versed in evaluating data systems
This is really cool. I vibe coded almost exactly the same app, mine also tracks saturated fat, cholesterol, sodium, and fiber (I'm getting older so these macros are pretty important to me). One of the really cool things you can do if you have tool calling hooked up is to have the LLM analyze your diet and tell you what you can do better to hit your targets - swap pizza for pasta, decrease the amount of cheese you put on your sandwich, if you're gonna have fast food don't get the fries and eat low fat/low sodium the rest of the day, etc. What model are you using? I have found Qwen Flash to be really good for my app - smart enough, tool calling works really well, and very cheap.
There is a lot to learn in nutrition. The glycemic load metric is quite revealing for pizza vs pasta (slow digesting carbs are supposed to be better). Al-dente cooked pasta is also slower digesting than well cooked pasta.
Another interesting thing is how each plant food has unique molecules that can be health promoting in humans. That was one aspect I wanted to reveal/compare for the foods I ate.
Dr Weil / Perfect Health Diet / Marks Daily Apple are three sources I like to check for information on nutrition.
Nice. I vibe coded a similar kind of system, you can dump a recipe into the chat window and it will use tool-calling to lookup macros for any foods it doesn't have in the DB and put them in, estimate raw -> cooked changes in nutrition and weight (if needed), estimate total weight of the cooked product, and macros per gram (e.g. writes a 100 gram serving to the db, you can scale it up and down and it scales the macros linearly). Similar to you I have used this app to alter my macro mix from high-fat to high-carb (for workout performance) and cut my sodium from ~4g/day to ~2.4g/day by interrogating the DB about what foods I should eat more and less of. Found some surprising wins in my habitual diet that were easy to change to hit my health targets, and looking up and logging these things by hand without LLM assistance would have been too tedious and time-consuming for me to continue to do it for as long as I have been (maybe 3 months now)
Curious, what model are you using? I have found Qwen Flash to be really great for this - tool calling works well, it's smart enough, and very cheap.
Maybe people who choose blue do so because they assume there’s some kind of monkey paw involved in the choosing the red option, like your wife and kids die or something like that
I wonder if red choosers really don’t understand that they are choosing to live in a world where half of all people, the more selfless half, are dead. It’s like living through a nuclear war except all of the nice people are gone, not just a random sample
I guess you base that surprising "half" on the transparent analogy with politics, and so you think real-world Democrats will press blue to assert their Democrattiness. This is probably true. However, since this is the internet, and being a Democrat is associated with being online and living in a city, there are probably more than 50% blue-pressers, as shown in the poll. Just like in the real world, you won't change that ratio whichever way you vote in the poll. If swaying opinion is within a voter's control, then your "choosing" is meaningful but the "half" becomes meaningless. If swaying opinion isn't within the voter's control, it's "choosing" that becomes meaningless, and the fate of the half is already sealed by cultural forces beyond our control.
I disagree that the hypothetical maps onto politics. Voting for democrats is mostly a vote for someone else (billionaires, etc.) to shoulder additional burdens to achieve some positive end. By contrast, this game involves serious risk to one's self and family. Lots of people would vote to raise corporate taxes to increase funding for schools in Baltimore. But those people aren't going to move their kids to Sandtown to help increase the property tax base.
I think if you played the game for real, blue would get maybe 5% of the vote, tops.
If we imagine people will ignore their real-world political tribalism:
Voting blue is voting to possibly die, either because you want death or in risky solidarity with others who voted to possibly die, who may have chosen by mistake. Voting red is voting for those interested in death to die, along with those who chose blue by mistake, and along with anybody who voted blue in support of those who voted blue by mistake.
So we can have a blue campaign that says "we must not allow even one voter to die, we must all pull together and vote blue", and a red campaign that says "please don't be a giant crowd of idiots who risk death, just accept that maybe two voters aren't going to make it because one was depressed and the other had an involuntary hand movement, and everybody else play it safe and vote red".
This is a ridiculous situation, and Jonathan Swift unfortunately died in 1745, so the best commentary I can offer is "I don't know".
reply