kkielhofner

I've used it for hybrid search and it works quite well.

Overall I'm really happy to see Typesense mentioned here.

A lot of the smaller scale RAG projects, etc you see around would be well served by Typesense but it seems to be relatively unknown for whatever reasons. It's probably one of the easiest solutions to deploy, has reasonable defaults, good docs, easy clustering, etc while still be very capable, performant, and powerful if you need to dig in further.

> I'm an engineering manager

How are you involved in the hiring process?

> Our engineers are fucking morons. And this guy was the dumbest of the bunch.

Very indicative of a toxic culture you seem to have been pulled in to and likely have contributed to by this point given your language and broad generalizations.

Describing a wide group of people you're also responsible for as "fucking morons" says more about you than them.

They will.

- It's a cornerstone of their brand.

- R2 users are at least paying for something (storage).

- Their network is massively overbuilt to be able to absorb DDoS attacks.

- They offer free bandwidth with their CDN - including completely free users. These resources need to get fetched from origin and/or cached. R2 doesn't have to fetch from origin which eliminates the bandwidth required for the fetch.

Large providers typically pay very little/nothing for bandwidth other than equipment costs (ports, etc). As a large provider they have free peering to most of the "last mile" ISP/eyeball networks in the world. This benefits all parties because these ISPs don't have to pay transit providers and neither does Cloudflare and it's faster. Same goes for all of the big clouds.

People who think AWS/GCP/Azure/etc bandwidth pricing of $0.12/GB (or whatever) is fair/reasonable have no idea what bandwidth actually costs these operators. As noted it's effectively nothing and the big clouds capitalize on this ignorance by charging insane markups for bandwidth.

ICC, IPP, QAT, etc are definitely an edge.

In AI world they have OpenVINO, Intel Neural Compressor, and a slew of other implementations that typically offer dramatic performance improvements.

Like we see with AMD trying to compete with Nvidia software matters - a lot.

> The US voting machines are just waiting to be hacked, just a matter of when, not if.

The US election system is very distributed and fragmented - there is virtually no standardization.

Even in the tightest margins for something like President you'd need to have seriously good data to figure out which random municipality voting system(s) you'd need to target to actually affect the outcome.

> we don't want to hurt performance on other real-world tasks just to do well on MTEB

Nice!

Fortunately MTEB lets you sort by model parameter size because using 7B parameter LLMs for embeddings is just... Yuck.

LLMs have nearly completely sucked the oxygen out of the room when it comes to machine learning or "AI".

I'm shocked at the number of startups, etc you see trying to do RAG, etc that basically have no idea what they are, how they actually work, etc.

The "R" in RAG stands for retrieval - as in the entire field of information retrieval. But let's ignore that and skip right to the "G" (generative)...

Garbage in, garbage out people!

Jensen has said for years that 30% of their R&D spend is on software. Needless to say as they continue to crush it financially this number continues to completely race past AMD.

Turns out people don’t actually want GPUs, they want solutions that happen to run best on GPUs. Nvidia understands that, AMD doesn’t.

Lisa Su keeps talking about “chips chips chips” and MAYBE “Oh btw here’s a minor ROCm update”. Meanwhile, Nvidia continues to masterfully execute deeper and wider into overall solutions and ecosystems - a substantial portion of which is software.

Nvidia is at the point where they’re eating the entire stack. They do a lot of work on their own models and then package them up nice and tight for you with NIM and Nvidia AI Enterprise. On top of stuff like Metropolis, RIVA, countless things. They even have a ton of frameworks to ingest/handle data, finetune/train, and then deploy via NIM.

Enterprise customers can be 100% Nvidia for a solution. When Nvidia is the #1-#2 most valuable company in the world “no one ever got fired for buying Nvidia” hits hard.

The people who say “AMD and Nvidia are equal - it’s all PyTorch anyway” have no view of the larger picture.

With x86_64, day one you could take a drive out of an Intel system, put it in an AMD system, and it would boot and run perfectly. You can still do that today unless you build something for REALLY specific/obscure CPU instructions.

Needless to say that’s not the case with GPUs and a lot of people that make the AMD vs Intel comparison don’t seem to understand that.

For reference seven trillion dollars is 25% of US GDP.

Yeah, that's um, wild.

Living in a climate (Wisconsin) that has extreme highs and lows my understanding is this is typically intended to smooth-out a gas bill (as one example) moving from $10/mo in the summer to $400/mo in the winter.

It’s a budgeting thing.