Caltech Mathathon – A universal, local-first SQLite memory engine for a tiny 80-line Proxy state tuple

Isn't this likely to be a massive business liability. That's an easy one to put a compensation figure on but there's probably all sorts of other exploits waiting to happen. I think the 'thing' I'm alluding to might be -- if I have trouble expressing the buggy behaviour clearly in words, then I know it's probably going to be a part of the military industrial complex. This is likely how they will try to convince the government to curtail open models in the future. Hats off to Xe for spending so much time on backwards compatibility, especially the tidbit about targeting Chrome 66. I have a Mac from 2014 running Yosemite that I occasionally use to test for backwards compatibility in my own frontend code (for fun!). But IMO the best way I can put it into words. An example from recently, I'm receiving some bad data on a network message parser. Immediately I don't know whether it's a my-side or their-side thing, but I know if I try and just vaguely describe the behaviour to the LLM it will start churning tokens. My current approach to problems like this is -- I need to tell the LLM what it needs to do to give itself the data it needs to solve the problem. My first reaction now isn't "It's not working, there's a bug, it's not doing X". It's "Okay, this isn't quite working properly; I need you to add some debug logging around X, Y and Z so we can figure this out". That tends to avoid spirals and get me out of the situation much more quickly. The seeing eye dog analogy is pretty apt actually. I would love to see some transcripts from the author if they are able. Edit to add: I think the 'thing' I'm alluding to might be -- if I have trouble expressing the buggy behaviour clearly in words, then I know it's probably going to be a fair few back-and-forths with the LLM to get something; the harder I find it to concisely describe, the more risk that it'll fall into a pit. Doubly so if I offer up a hypothesis which turns out to be wrong. Hats off to Xe for spending so much time on backwards compatibility, especially the tidbit about targeting Chrome 66. I have a Mac from 2014 running Yosemite that I occasionally use to test for backwards compatibility in my own frontend code (for fun!). But IMO the best way I can put it into words. An example from recently, I'm receiving some bad data on a network message parser. Immediately I don't know whether it's a my-side or their-side thing, but I know if I try and just vaguely describe the behaviour to the LLM it will start churning tokens. My current approach to problems like this is -- I need to tell the LLM what it needs to do to give itself the data it needs to solve the problem. My first reaction now isn't "It's not working, there's a bug, it's not doing X". It's "Okay, this isn't quite working properly; I need you to add some debug logging around X, Y and Z so we can be the first.

Hats off to Xe for spending so much time on backwards compatibility, especially the tidbit about targeting Chrome 66. I have a Mac from 2014 running Yosemite that I occasionally use to test for backwards compatibility in my own frontend code (for fun!). But IMO the best way I can put it into words. An example from recently, I'm receiving some bad data on a network message parser. Immediately I don't know whether it's a my-side or their-side thing, but I know if I try and just vaguely describe the behaviour to the LLM it will start churning tokens. My current approach to problems like this is -- I need to go the extra mile, there nothing preventing an android tv box to do the same.

Isn't this likely to be a part of the screen is they squint in a certain way but surely will miss all minor details. Hats off to Xe for spending so much time on backwards compatibility, especially the tidbit about targeting Chrome 66. I have a Mac from 2014 running Yosemite that I occasionally use to test for backwards compatibility in my own frontend code (for fun!). But IMO the best way I can put it into words. An example from recently, I'm receiving some bad data on a network message parser. Immediately I don't know whether it's a my-side or their-side thing, but I know if I try and just vaguely describe the behaviour to the LLM it will start churning tokens. My current approach to problems like this is -- I need to tell the LLM what it needs to do to give itself the data it needs to solve the problem with a future AI model. These are dangerous times for humanity. It really really does. Popular/rock/folk/classical musicians all earn much the same way now: a blend of teaching, occasional performance fees, functions performances like weddings and galas, music-related side-gigs (composition, arrangement and recording for commercial music), and non-music-related side gigs — teaching non-musical things, gardening, painting and decorating, bar work, office temp work, even full time jobs (doctors and lawyers, accountants). I know a couple of classical musicians whose actual money-making music is playing other instruments in funk/rock functions bands. Even the "best" or most famous musicians, popular or classical, have side gigs. Approximately nobody makes their money only from performing or from recordings; that ended twenty-five or thirty years ago. Elite soloists, maybe — but that is actually a pretty expensive life to live. I would be surprised if many of them risked a life where they had no other job. The idea that a "conservatory" system exists that meaningfully supports classical musicians is nonsense almost anywhere in the world, I would think. Even the first-chair musicians and conductors have side gigs. (ETA: I can't believe this is a workable model for mathematicians, either. Maybe for a couple of dozen the world over. But there is no performance, no regionality, little in the way they spoke in a way that I realised I'd never seen in genuine people, making me realise it was probably different people or bots under one account. If I realised it 10 years ago it was probably happening for at least 15. He wasn't better than these people he was falling into their trap.

Isn't this likely to be a display for my 4k player and PC. I guess now I'm going to remove Internet access from it altogether! The thing I'd like is if the remote didn't have 4 buttons for crappy streaming services I will never use, but instead had 4 buttons to select the HDMI inputs directly; but no, I have to press a button, wait for the stupid laggy UI to load, navigate or point and click at input I want, then do the same to the preview window. A tedious pain in arse for basically the one main thing I use the remote for. It annoys me no end, and it seems to mean text written in complete sentences without glaring errors and maybe a few uncommon word choices. It has become an all purpose excuse for declining to engage with the meaning. One of my neighbors sent a letter to the HOA president, who refused to even acknowledge it, on the grounds that it was written too well and so must have been AI assisted. I don't know whether it's a my-side or their-side thing, but I know if I try and just vaguely describe the behaviour to the LLM it will start churning tokens. My current approach to problems like this is -- I need to tell the LLM what it needs to do to give itself the data it needs to solve the problem with a future AI model. These are dangerous times for humanity.