Zagreus2142

``` We evaluated several precision pairings across our internal retrieval benchmark suite. Scores are NDCG@10 averaged across the suite, scaled to 0–100. NDCG@10 (Normalized Discounted Cumulative Gain at rank 10) measures how well the top 10 results are ordered against the ideal ranking, rewarding relevant documents more when they appear higher, with 100 being a perfect ranking. The full-precision baseline averages 90.26. Int8 query against binary documents averages 89.65, a 0.61 point drop, while reducing document-vector storage by 32x ```

Saying "Near lossless" to mean 90% accurate retrieval of saved vectors is simply a lie. Lossy-ness is binary, not something you can paper over with getting close enough. And 90% is not close. Sure, LLMs are all about gradient descent on noisy data sets so I guess this is acceptable in this field but that terminology usage still bothered me

Having banged my head on years/decade old inconsistencies between Chrome and Firefox with respect to webrtc APIs, some of these inconsistencies will never be ironed out.

But also, imo, Chrome is way more entrenched that LLM agents. I'm sure people will be happy with chromium being containerized this way.

I'm sorry but this article is marketing. From the 3rd paragraph from the end:

> Since our landing page is isolated from core product code, the risk was minimal.

The real question to ask is why your landing page so complex, it is a very standard landing page with sign-ups, pretty graphics, and links to the main bits of the website and not anything connected to a demo instance of your product or anything truly interactable.

Also, you claim this avoided you having to hire another engineer but you then reference human feedback catching the LLM garbage being generated in the repo. Sounds like the appropriate credit is shared between yourself, the LLM, and especially the developer who shepherded this behind the scenes.

I had not thought of visualing my mental debugging process as a decision _tree_ and that LLMs (and talking to other humans) are analogous to a foreign graft. Interesting, thanks!

Truly the response of someone who is a perfectionist using llms the right way and not a slop coder

Yeah this definitely matches my experience and guess what? Google maps sucks for public transit and isn't actually that good for pedestrian directions (often pointing people to "technically" accessible paths like sketchy sidewalks on busy arterial roads signed for 35mph where people go 50mph). I stopped using Google maps instinctually and now only use it for public transit or drives outside of my city. Doing so has made me a more attentive driver, less lazy, less stressed when unexpected issues on the road occur, restored my navigation skills, and made me a little less of, frankly, an adult man child.

Applying all of this to LLMs has felt similar.