Hacker News: gbingles

New comment by gbingles in "GLM-5.2 is the new leading open weights model on Artificial Analysis"

gbingles — Wed, 17 Jun 2026 15:17:11 +0000

AI review generally will find fault in anything. Any non-trivial code has multiple solutions with different tradeoffs. Any code can be over-engineered for theoretical edge cases and future use cases you don't need. No matter which solution you pick you can always at a minimum say that some alternative just looks and reads better.

Code is somewhat artistic. If you don't have well defined standards and priorities, the AI review cycle can spiral infinitely figuratively debating what makes art good, and your code will be no better for it.

New comment by gbingles in "GLM-5.2 is the new leading open weights model on Artificial Analysis"

gbingles — Wed, 17 Jun 2026 15:06:11 +0000

Tbh, so what? I googled "symbolic math engine in Typescript that can perform evaluation and simple expression reductions over +-/*()" and got what looks to be viable answers without using any AI model at all. Reciting well established things from memory isn't terribly interesting. Show it a novel codebase and have it implement something within it.

New comment by gbingles in "Amazon shipped fake product, refuses refund until 'correct' item returned"

gbingles — Tue, 06 Dec 2022 00:45:35 +0000

Loads of brands are nothing more than a logo on some Chinese generic products like that. Google "best hand coffee grinders" and see how many of the 100 dollar models you can find identical matches for on eBay for 20 bucks.

Maybe the eBay ones are QC near-fails or knockoffs, but it's hard to tell without buying a bunch to inspect.

New comment by gbingles in "Connecting the iDOTs (2020)"

gbingles — Sun, 19 Dec 2021 13:16:36 +0000

I was wondering if exactly that was possible. Generate an iDOT that leads to chunks a "regular" renderer would never look for.

Really curious that it happens in Safari sometimes though...