SO was somewhere people put their hard won experience into words, that an LLM could train on.
That won't be happening anymore, neither on SO or elsewhere. So all this hard won experience, from actually doing real work, will be inaccessible to the LLMs. For modern technologies and problems I suspect it will be a notably worse experience when using an LLM than working with older technologies.
It's already true for example, when using the Godot game engine instead of Unity. LLMs constantly confuse what you're trying to do with Unity problems, offer Unity based code solutions etc.
> Isn’t back and forth exactly what the new MoE thinking models attempt to simulate?
I think the name "Mixture of Experts" might be one of the most misleading labels in our industry. No, that is not at all what MoE models do.
Think of it rather like, instead of having one giant black box, we now have multiple smaller opaque boxes of various colors, and somehow (we don't really know how) we're able to tell if your question is "yellow" or "purple" and send that to the purple opaque box to get an answer.
The result is that we're able to use less resources to solve any given question (by activating smaller boxes instead of the original huge one). The problem is we don't know in advance which questions are of which color: it's not like one "expert" knows CSS and the other knows car engines.
It's just more floating point black magic, so "How do I center a div" and "what's the difference between a V6 and V12" are both "yellow" questions sent to the same box/expert, while "How do I vertically center a div" is a red question, and "what's the most powerful between a V6 and V12" is a green question which activates a completely different set of weights.
For younger kids I can heartily recommend the Hobbit illustrated by Jemima Catlin- has plenty of pictures to them engaged. Read it to my 6 year old and we’re now excited for LotR.
The bulk of today's customers has no idea how to pirate music, so they're not really a threat anymore. Music streaming has been rather convenient, you pretty much get the same content across all services. Video streaming platforms have, unfortunately become fragmented and, as of late, ad-ridden.
Both Claude Code and Codex steer you towards the monthly subscription. Last time I tried Codex, I remember several aspects of it being straight up broken if used with an API key instead of a subscription account.
The business model is likely built upon the assumption that most people aren't going to max out their limits every day, because if they were, it likely wouldn't be profitable.
It's a 1.7 trillion token free model. Why wouldn't you try it?
I've been testing free models for coding hobby projects after I burnt through way too many expensive tokens on Replit and Claude. Grok wasn't great, kept getting into loops for me. I had better results using KAT coder on opencode (also free).
Openrouter has an apps tab. If you look at the free, non-coding models, some apps that feature are: janitor.ai, sillytavern, chub.ai. I'd never heard of them but people seem to be burning millions of tokens enjoying them.
This is the one I use. It is surprising good for the price. It just behaves as a regular webcam.
I primarily use it for micro soldering, so your mileage may vary, but it is very good for the price. I got it on Amazon where I believe they have an official store.
Check out chessiverse (I’m not affiliated just found from YouTubers). They purport to be a collection of bots that play like humans with human-like mistakes matched to ELO levels. I like it so far - the main value for me (vs lichess/chess.com) is knowing that who’s on the other end isn’t constantly cheating.
“ It is also worth noting that I contacted Procolored support four times over the course of my testing, for help with figuring out the software and settings. Every single time, the agent requested multiple times that I allow them to connect remotely to my computer”
