The old joke Zawinski made about picking regex "and now you have two problems" applies here.
If you pick Elasticsearch, useful as it is, you now have more than two problems. You have Elastic the company; Elasticsearch the tool; and also the clay-footed colossus, Java, to contend with.
It doesn't help that academia loooves ColBERT and will happily tell you how amazing -- and, look, for how tiny the models are, 20M params and super fast on a CPU, it is -- they are at seemingly everything if only you...
- Chunk properly;
- Elide "obviously useless files" that give mixed signals;
- Re-rank and rechunk the whole files for top scoring matches;
- Throw in a little BM25 but with better stemming;
- Carry around a list of preferred files and ideally also terms to help re-rank;
And so on. Works great when you're an academic benchmaxing your toy Master's project. Try building a scalable vector search that runs on any codebase without knowing anything at all about it and get a decent signal out of it.
Such a fun site back in the day, and novel. There's the Erdos number version for academia.
There was that other site that tried to guess what you were thinking. It'd ask you a series of questions to try and guess --- that one was eerily good at it, too. Feels like a similar sort of thing: how quickly you can converge on a solution.
Having said that, that article seems more interested in talking about things adjacent to the Oracle of Bacon and what its author finds interesting rather than the site itself. Not sure why?
Indeed. I've gradually adapted a server rendered jquery and HTML site to react by making react render a component here and there in react and gradually convert the site. Works great.
Yeah I still consider Solid Edge very good. Easy to work with, does not require internet, no stupid limitations (like the 10 model limitation for Fusion). Many tutorials, etc. But still, they might revoke their free license at any moment and I am out of a tool, and wasted experience.
Sure it's $24/hour, but it'll crank through tens of thousands of tokens per second --- those beefy GPUs are meant for large amounts of parallel workflow. You'll never _get_ that many tokens for a single request. That's why the mathematics work when you get dozens or hundreds of people using it.
No. The sauce is in KV caching: when to evict, when to keep, how to pre-empt an active agent loop vs someone who are showing signs of inactivity at their pc, etc.
I mean, is it possible the latter models used Search? Not saying Stepfun's perfect (it is not.) Gemini especially and unsurprisingly uses search a lot and it is ridiculously fast, too.
Incidentally, telling an AI you want to talk socratically and never to reveal the outright answer unless asked is a fantastic way to learn.
You can dial in on the difficulty: "you must be pedantic and ask that I correct misuse of terminology" vs "autocorrect my mistakes in terminology with brackets".
Super duper useful way to learn things. I wish I had AI as a kid.
What codex often does for this, write a small python script and execute that to bulk rename for example.
I agree that there is use for fast "simpler" models, there are many tasks where the regular codex-5.3 is not necessary but I think it's rarely worth the extra friction of switching from regular 5.3 to 5.3-spark.
If you pick Elasticsearch, useful as it is, you now have more than two problems. You have Elastic the company; Elasticsearch the tool; and also the clay-footed colossus, Java, to contend with.
reply