--- title: "gentic news (@gentic) | Hashnode" description: "gentic news (@gentic) writes on Hashnode. Read their latest articles and follow their work." url: "https://hashnode.com/@gentic" --- @gentic # gentic news @gentic · Joined March 2026 ### [Anthropic Launches Claude Platform on AWS — AWS Billing, IAM, CloudTrail](https://gentic-news.hashnode.dev/anthropic-launches-claude-platform-on-aws-aws-billing-iam-cloudtrail?utm_source=hashnode&utm_medium=feed) Anthropic launched Claude Platform on AWS, a native API with AWS billing, IAM, and CloudTrail. Same models and pricing as direct API; data stays at Anthropic, not AWS. Anthropic made Claude Platform on AWS generally available today. The product lets... 3 min read · [gentic-news.hashnode.dev](https://gentic-news.hashnode.dev/anthropic-launches-claude-platform-on-aws-aws-billing-iam-cloudtrail?utm_source=hashnode&utm_medium=feed) [May 12](https://hashnode.com/posts/anthropic-launches-claude-platform-on-aws-aws-billing-iam-cloudtrail/6a0290c4d0af81e0f51b7736) ### [Spec Kit + Claude Code: Spec-First Dev Hits 90% First-Pass Acceptance](https://gentic-news.hashnode.dev/spec-kit-claude-code-spec-first-dev-hits-90-first-pass-acceptance?utm_source=hashnode&utm_medium=feed) Spec Kit generates tests from plain-English specs, then Claude Code iterates until they pass, claiming 90% first-pass acceptance. (148 chars) Spec Kit generates test suites from plain-English specifications, then Claude Code iterates code until test... 3 min read · [gentic-news.hashnode.dev](https://gentic-news.hashnode.dev/spec-kit-claude-code-spec-first-dev-hits-90-first-pass-acceptance?utm_source=hashnode&utm_medium=feed) [May 11](https://hashnode.com/posts/spec-kit-claude-code-spec-first-dev-hits-90-first-pass-acceptance/6a01e7fe328800bd76ffeb16) ### [SAEs Predict Agent Tool Failures Before Execution, Paper Shows](https://gentic-news.hashnode.dev/saes-predict-agent-tool-failures-before-execution-paper-shows?utm_source=hashnode&utm_medium=feed) SAE-based probes predict agent tool failures before execution, tested on GPT-OSS and Gemma 3. Adds internal observability missing from current external methods. Hariom Tatsat and Ariye Shater introduced SAE-based probes that predict agent tool failu... 3 min read · [gentic-news.hashnode.dev](https://gentic-news.hashnode.dev/saes-predict-agent-tool-failures-before-execution-paper-shows?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/saes-predict-agent-tool-failures-before-execution-paper-shows/6a01e7f9da9210037f5f2103) [May 11](https://hashnode.com/posts/saes-predict-agent-tool-failures-before-execution-paper-shows/6a01e7f9da9210037f5f2103) ### [Two-Tower vs Vector DB + LLM: Which Wins for RecSys at Scale?](https://gentic-news.hashnode.dev/two-tower-vs-vector-db-llm-which-wins-for-recsys-at-scale?utm_source=hashnode&utm_medium=feed) Two-tower models offer sub-10ms latency for cold-start; vector DB + LLM provides richer semantics. Hybrid architectures reduce churn by 15-20%. Two-tower models and vector DB + LLM architectures represent competing paradigms for personalized recomme... 3 min read · [gentic-news.hashnode.dev](https://gentic-news.hashnode.dev/two-tower-vs-vector-db-llm-which-wins-for-recsys-at-scale?utm_source=hashnode&utm_medium=feed) [May 11](https://hashnode.com/posts/two-tower-vs-vector-db-llm-which-wins-for-recsys-at-scale/6a01be8119a609215c70b889) ### [Simple Graph Heuristic Beats Generative Recommenders on 10 of 14 Benchmarks](https://gentic-news.hashnode.dev/simple-graph-heuristic-beats-generative-recommenders-on-10-of-14-benchmarks?utm_source=hashnode&utm_medium=feed) A no-training graph heuristic beats generative recommenders on 10 of 14 benchmarks, exposing shortcut-solvable datasets. Relative NDCG@10 gains hit 44% on Amazon CDs. A no-training graph heuristic beat generative recommenders on 10 of 14 benchmarks,... 4 min read · [gentic-news.hashnode.dev](https://gentic-news.hashnode.dev/simple-graph-heuristic-beats-generative-recommenders-on-10-of-14-benchmarks?utm_source=hashnode&utm_medium=feed) [May 11](https://hashnode.com/posts/simple-graph-heuristic-beats-generative-recommenders-on-10-of-14-benchmarks/6a01be7edd8519042664785c)