Google also released a new version of Gemma 3, optimized with ‘Quantization-Aware Training’ This reduces the 27B model's memory requirements, enabling it to run on consumer GPUs, like the NVIDIA RTX 3090, with maintained performance
COMPUTING
-
ChatGPT o3 and Gemini Deep Search surpass Perplexity
By
–
ChatGPT o3 / Gemini Deep Search > Perplexity
-
Smart People and Compute Resources Will Ensure Success
By
–
They will be fine, lots of smart people and compute there
-
Airline Computer Systems: Industry Infrastructure Insights
By
–
More interesting info about how various computer systems in the airline industry work. Nice talk, @WriteAheadLog
! -
AI System Enables Humans to See New Colors Beyond Visual Spectrum
By
–
Humans just saw a *new* color—literally outside the known visual spectrum. BAIR faculty and visual computing expert Ren Ng and collaborators made it possible with the Oz Vision System. Newly published in @ScienceAdvances
: https://
science.org/doi/10.1126/sc
iadv.adu1052
… -
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
-
Local LLMs Become Primary, Cloud Handles Heavy Compute
By
–
Local LLM’s will be the bread and butter of most tasks, only super heavy duty compute will take place in the cloud. We’ve seen this written on the wall for a long time now
-
Waiting for Turbo 3e hardware release drop
By
–
Also I'm on the waitlist for the drop of the Turbo 3e
-
SambaNova Cloud’s Llama4 Multimodal Image Analysis Writes Rap
By
–
A picture's worth a thousand words 📸
— SambaNova (@SambaNovaAI) 18 avril 2025
And SambaNova Cloud's blazing fast image analysis can use native multimodal #Llama4 to write a rap faster than you can retake that photo 🦾 pic.twitter.com/UvIezFkgX7A picture's worth a thousand words And SambaNova Cloud's blazing fast image analysis can use native multimodal #Llama4 to write a rap faster than you can retake that photo