Our engineers work with the AWS chip design team to extract maximum computational efficiency from the hardware. This includes writing low-level kernels that allow us to directly interface with Trainium silicon and contributing to the AWS Neuron software stack.
SOFTWARE
-
Claude Becomes Core Infrastructure Through Amazon Bedrock
By
–
Through Amazon Bedrock, Claude has become core infrastructure for tens of thousands of companies seeking reliable and practical AI at scale. Together, we're laying a new technological foundation—from silicon to software—to train and power our most advanced AI models.
-
AWS Trainium Chips: Co-designing Hardware and Software for Frontier Models
By
–
Working closely with AWS, we're developing future generations of Trainium chips. Designing both hardware and software together lets us optimize every aspect of frontier model training.
-
Abacus AI MLOps Platform Addresses Data and Model Drift Challenges
By
–
Data Drift, Concept Drift, Model Drift, Observability, and Explainability — the @abacusai #MLOps Solution covers all that (and more) beautifully in one platform: https://
abacus.ai/drift
—————
#AIOps #DataScience #ML #MachineLearning #AI #DeepLearning #DataScientist -
Apple Watch AI detects critical health conditions and saves lives
By
–
This is incredible! This Apple Watch didn't just tell time – it detected a critical health condition and saved a life Add to that the new AirPods which are now hearing aids and satellite texting, and even more lives will be saved. Technology is truly amazing. By choosing to
-
Bfloat16 vs Quantization: Performance Trade-offs in Model Deployment
By
–
Bfloat16 or nothing! FWIW – all the models deployed on Hugging Chat are bf16. Quants are good for local/ hobby use – however you always leave perf on the table.
-
Software Engineering Productivity Research Reveals Ghost Engineers Phenomenon
By
–
I am really glad people are studying software engineering productivity as a real research field! What they discovered: ~9.5% of software engineers do virtually nothing: Ghost Engineers (0.1x-ers)
-
All-Night Coding Session: Recipe for Success
By
–
part of the recipe is that we stayed awake until 7 am coding
-
OpenAI Realtime API: Technical Guide Audio Processing Tools
By
–
🆕 post: OpenAI Realtime API: The Missing Manual
— Latent.Space (@latentspacepod) 21 novembre 2024
Everything we learned, and everything we think you need to know, from technical details on 24khz/G.711 audio, RTMP, HLS, WebRTC, to Interruption/VAD, to Cost, Latency, Tool Calls, and Context Mgmt
Enjoy this first guest post from… https://t.co/yll3YsfTcX pic.twitter.com/4il1t0Ah6zpost: OpenAI Realtime API: The Missing Manual Everything we learned, and everything we think you need to know, from technical details on 24khz/G.711 audio, RTMP, HLS, WebRTC, to Interruption/VAD, to Cost, Latency, Tool Calls, and Context Mgmt Enjoy this first guest post from
-
8B Model Proves Viable for Private On-Device Deployment
By
–
The 8B looks way too good for running privately on-device!