ContentPosts from @priyangtripathi..
Link
@faun shared a link, 3 months ago

Using AWS ECR as a universal OCI repository

AWS ECR is an OCI repository supporting different types of artifacts, from Docker images to machine learning models, allowing for simplified management and unified access. Users can interact with ECR using CLI tools like ORAS, Helm, and Terraform, providing integration with CI/CD pipelines for effic.. read more  

Link
@faun shared a link, 3 months ago

Faster Index I/O with NVMe SSDs

A search service (Marginalia Search) gutted its old index internals and dropped memory-mapped B-trees. In their place: adeterministic, block-aligned skip listtuned fordirect reads on NVMe SSDs. It runs on128KB block sizes, usescustom buffer pools, and leans hard onio_uringfor async position lookups.. read more  

Link
@faun shared a link, 3 months ago

Building a web search engine from scratch in two months with 3 billion neural embeddings

An indie dev just went full mad scientist and built a full-stack, transformer-powered search engine—solo. They indexed 280 million pages from scratch with hundreds of crawlers, a fully sharded backend, and serious metal:64 RocksDB nodes,200 CPU cores, and82 TB of SSD. Under the hood: custom HTML pa.. read more  

Link
@faun shared a link, 3 months ago

The decline of high-tech manufacturing in the United States

High-tech manufacturing used to employ 2.8% of U.S. workers back in 1990. Now it’s down to 1.3%. The sharpest losses hitcomputers, electronics, and aerospace—industries that once defined the future. Onlypharma and med devicesmanaged to buck the trend, adding 189,000 jobs while the rest bled over a .. read more  

The decline of high-tech manufacturing in the United States
Link
@faun shared a link, 3 months ago

No, AI is not Making Engineers 10x as Productive

Claims of 10–100x dev speed from AI tools skip the hard parts—code reviews, bug queues, flaky tests. In practice, AI helps with the small stuff: one-off scripts, throwaway glue code, basic scaffolds. But scaling that help across big, messy codebases? Still a pipe dream. Too much context lost. Too ma.. read more  

Link
@faun shared a link, 3 months ago

LLM Evaluation: Practical Tips at Booking.com

A new LLM evaluation framework taps into an"LLM-as-judge"setup—think strong model playing human annotator. It gets prompted (or fine-tuned) to mimic human scores and rate outputs from other LLMs. It runs on a tightly labeledgolden dataset, handles both pointwise and head-to-head comparisons, and sh.. read more  

LLM Evaluation: Practical Tips at Booking.com
Link
@faun shared a link, 3 months ago

Anthropic Revokes OpenAI’s API Access to Claude, Alleging Violation Ahead of GPT-5 Launch

Anthropic just yanked OpenAI’s API access to Claude. Reason? Alleged violations of terms that forbid using Claude to train rival models—like GPT-5. Windsurf, an OpenAI acquisition target, got the boot earlier too. Spot the pattern: tighten access, box out competitors. System shift:APIs aren’t just .. read more  

Anthropic Revokes OpenAI’s API Access to Claude, Alleging Violation Ahead of GPT-5 Launch
Link
@faun shared a link, 3 months ago

Powering Real-Time AI Applications

Generative AI databases like SingleStore now cramOLTP,OLAP,vector search, andfull-text searchinto one SQL-first platform. Structured, unstructured—it eats both. No ETL. No silos. Just real-time data, ripe for AI models and semantic queries. System shift:Blending transactional and analytic guts in o.. read more  

Link
@faun shared a link, 3 months ago

Who does your assistant serve?

OpenAI’s release of GPT-5 backfired: instead of excitement, users felt betrayed by a forced upgrade that stripped away the warmth and reliability they had come to rely on in GPT-4o. Many treated the model as more than a tool — a companion, therapist, or emotional support — so when its personality sh.. read more  

Who does your assistant serve?
Link
@faun shared a link, 3 months ago

Implementing MCP Servers in Python: An AI Shopping Assistant with Gradio

Gradio just leveled up. It now auto-converts plain Python functions intoMCP-compliant LLM tools, grabbing input schemas and metadata straight from docstrings. New tricks:real-time progress streaming,auto file uploads, plus tight integration withVS Code’s AI Chatfor wiring up agent workflows... read more