For (1), knowledge graphs help with lots of higher level kind of things, search presentation aspects, etc., but from an infrastructure perspective, they don't have a huge effect because they just aren't very large relative to the web corpus.
@jeffdean
-
In-Memory Index Redundancy and Distributed Cluster Architecture
By
–
The problem was that an in memory index, because of its size, did not have the same level of redundancy on a per-cluster basis as a disk-based index (e.g. usually every page was present in the memory of just a single machine).
-
Unpublished Search Systems Work from 2009 Conference Talk
By
–
We never really published any papers about lots of interesting systems work that underlies our search systems, so this relatively little known talk I gave at the Web Search and Data Mining conference in 2009 is the best public source of info.
-
Google Search Evolution: From Disk to In-Memory Systems
By
–
Someone just reminded me of this lecture I gave in 2009 that described the evolution of Google Search from 1999 to 2009. People who are interested in how our search systems work might find this interesting. It touches on disk-based serving systems, in-memory indices,
-
Airline Computer Systems: Industry Infrastructure Insights
By
–
More interesting info about how various computer systems in the airline industry work. Nice talk, @WriteAheadLog
! -
TPU Hardware Architecture: From v1 to v4 Optical Interconnect
By
–
If you want to read about them from the hardware perspective, read these three papers: https://
arxiv.org/abs/1704.04760
(about TPU v1, the one that started it off) https://
arxiv.org/abs/2304.01433 (about TPU v4 and its optical interconnect) https://
gwern.net/doc/ai/scaling
/hardware/2021-jouppi.pdf
… (ten lessons) -
Google Flights Complexity: ITA Software Founder Explains
By
–
If you want to know more about how Google Flights works, airline tickets, and why it is super complicated to deal with all the constraints and the combinatorial combinations, I highly recommend this set of slides by Carl de Marcken, one of the co-founders of ITA software, which
-
AI Education Platform Expanding Access to International Students Soon
By
–
Hang tight, it's coming soon to non-US students.
-
1B 4B 12B Models Running on Consumer GPUs
By
–
The 1B, 4B, and 12B parameter version should run on many consumer GPUs.
-
Gemma 3 Model Optimization Through Advanced Quantization
By
–
Some nice quantization work makes our Gemma 3 model even more compact.