Is there any similar ecosystem hook for a zip-like archive? It would be great to have something like .zip file containers for zstd/brotli which can contain a small number of dictionaries and then the decompression utility automatically uses them. For example, suppose you have a lot of .js / .css / .html files. Or Python files. Or whatever. It would be more efficient than individual .zstd files.
Intriguing article. Sometimes practical issues override theoretical ones, and it would be interesting to see which one dominates in networking.
(side note: does anyone else get thrown off by the Epilogue font? It looks very wide in some cases and very narrow in others... makes me want to override it with Stylus if my employer hadn't blocked browser extensions for security reasons, which raises the question of why I am even reading the article on this computer....)
They only run locally on my machine, and they use properly scoped API credentials. Is there some theoretical risk that someone could get their hands on my Gemini API key? Probably, but it'd be very tough and not a particularly compelling prize, so I'm not altogether too concerned here.
On the verification front, a few examples:
1. I built an app that generates listing images and whitebox photos for my products. Results there are verifiable for obvious reasons.
2. I use Claude Code to do inventory management - it has a bunch of scripts to pull the relevant data from Amazon then a set of instructions on how to project future sales and determine when I should reorder. It prints the data that it pulls from Amazon to the terminal, so that's verifiable. In terms of following the instructions on coming up with reorder dates, if it's way off, I'm going to know because I'm very familiar with the brands that I own. This is pretty standard manager/subordinate stuff - I put some trust in Claude to get it right, but I have enough context to know if the results are clearly bad. And if they're only off by a little, then the result is I incur some small financial penalty (either I reorder too late and temporarily stock out or I reorder too early and pay extra storage fees). But that's fine - I'm choosing to make that tradeoff as one always does when one hands off work.
3. I gave Claude Code a QuickBooks API key and use it to do my books. This one gets people horrified, but again, I have enough context to know if anything's clearly wrong, and if things are only slightly off then I will potentially pay a little too much in taxes. (Though to be fair it's also possible it screws up the other way, I underpay in taxes and in that case the likeliest outcome is I just saved money because audits are so rare.)
Not every tool can have a "security risk". I feel that this stems from people who see every application as a product and products must be an online web app available to the world.
Let's say I have a 5 person company and I vibe-engineer an application to manage shifts and equipment. I "verify" it by seeing with my own eyes that everyone has the tools they need and every shift is covered.
Before I either used an expensive SaaS piece of crap for it or did it with Excel. I didn't "verify" the Excel either and couldn't control when the SaaS provider updated their end, sometimes breaking features, sometimes adding or changing them.
Per corporate policy -- in the name of safety and legal reasons -- the most extensive public uses of AI, like vibe coding and agentic systems, aren't really options. The most common usage I have seen is more like consulting AI as a fancy StackOverflow.
Will this change? I personally don't expect to ever see pure vibe coding, with code unseen and unreviewed, but I imagine AI coding uses will expand.
Interesting. The syntax looks like C and Scheme had an illegitimate child together. (Don't get me wrong, I do like the unambiguity of prefix notation.)
reply