iCreatAI News
Back to main site
Skip to content
#Tutorials
Oct 28Wed
  1. Hacker News AI34

    Who needs AI psychosis? I gave myself VR psychosis

    The author describes building and auto-deploying web-based VR games by voice-prompting coding agents from the pub, using tools like Wispr Flow, Claude's /remote-control, Git, Vercel and Cloudflare, with games playable via Three.js and WebXR on a Quest 2. He walks through several prototypes, especially Star Crusader, and argues that iterating on primary gameplay loops is the fastest way to develop taste. He also recounts a scaled-back drawing-and-deploying game activity with his daughter.

  2. Databricks Blog38

    From spot fixes to measured gains: improving document extraction accuracy with ai_extract and MLflow Prompt Registry

    A Databricks engineering post describes extracting roughly 40 structured fields from partner order documents across dozens of PDF layouts, where a schema fix that halved errors on the revision field raised total errors across all fields by 9%. The authors recommend putting field rules in schema descriptions, document-level logic in global instructions, precision mode (ai_extract 2.1) for complex structures, and citations to diagnose errors, while versioning prompts and schemas in MLflow Prompt Registry with aliases such as @prod and @candidate. They evaluate candidates against a frozen human-reviewed test set, tracking accuracy, coverage and run-to-run variation, and report that restructuring the prompt and schema plus precision mode cut overall errors by 32% and revision errors by 64%.

  3. AWS Machine Learning Blog50

    Exowatt beats frontier models on accuracy with SageMaker serverless model customization

    Exowatt used Amazon SageMaker AI serverless model customization to fine-tune Qwen3-1.7B for edge alarm triage (0.911 macro-F1 vs 0.698 for Claude Sonnet 4.6) and Qwen3-14B for cloud energy-market analysis (0.975 macro-F1 vs 0.625 for Claude Opus 4.7, at about 49× lower cost per 1,000 answers). The pipeline spans seven AWS serverless services, with the edge model quantized to GGUF and run offline via llama.cpp on existing CPUs, and the cloud model served through Amazon Bedrock Custom Model Import. Exowatt moved from experimentation to production in nine days and plans to reuse the pipeline across fleet tasks.

  4. AWS Machine Learning Blog40

    Fix evaluation bias to unlock better models on Amazon Bedrock

    Property Finder found that 96.8% of its evaluation labels came directly from its incumbent vision model's predictions rather than human verification, biasing comparisons against alternatives. After building expert-annotated ground truth (356 UAE images) and running evolutionary prompt optimization from v0 to v27, it selected Llama 4 Maverick 17B Instruct on Amazon Bedrock, reaching a Micro F1 of 0.80 versus 0.56 for its previous model on the evaluation set, at an estimated 86% lower cost per 1,000 images.

  7. Meta Engineering38

    PrivacyLib: Privacy Controls at the Data Access Boundary

    Meta details PrivacyLib, a common library embedded in the clients of hundreds of its data and processing systems that enforces privacy requirements at the point of data access, performing billions of checks per second. Systems integrate once and new requirements arrive as plug-in modules, with changes simulated before release and rolled out per module; for internal AI agents, tool calls carry agent context to PrivacyLib so modules can observe data use and block disallowed operations.

  8. Hacker News AI33

    Feynman's wobbling plate and Threshold Concepts behind modern AI

    Luis, who has studied AI for about 10 years, argues that curiosity-driven play at the edge of one's knowledge, as with Feynman's wobbling plate, is the engine of real learning, and outlines eight "threshold concepts" that explain modern AI: learning from data, representations and embeddings, next-token prediction, attention, evals, post-training and RL fine-tuning, harnesses and agents, and recursive self-improvement. He cites Vygotsky's zone of proximal development, Meyer and Land's threshold concepts, and Bruner's spiral learning, and includes a study prompt usable with any LLM. The post ends with a paragraph promoting his AI coach, Zairai.

  9. Hacker News AI58

    Can You Make a 3D Game with AI, If You Don't Know How to Do Anything?

    The author describes building a browser-based 3D game intro inspired by Mass Effect using mostly free tools plus Codex from a $20 ChatGPT subscription, spending about $15 and roughly 10 days. The workflow combined ChatGPT for prompts and character images, Hunyuan3D for models, Mixamo for animation, and Freesound for audio, with the author rewriting dialogues and fixing bugs himself. He concludes that AI now lets beginners experiment with game development without deep technical knowledge.

  10. Hacker News AI34

    Does AI Speed Up Development? Using the UKs GDS Service Standard as framework

    The author argues that AI mainly accelerates coding, which is only one part of digital service development, and uses the UK GDS Service Standard's 14 points to assess where AI actually helps. The tally is roughly 2 high-impact points (open source code and open standards, both code-heavy), 6 partial or mixed, and 6 low or none, with bottlenecks remaining in user research, organisational change, governance and procurement. The post concludes that speeding up the build step without widening the real bottleneck just moves the queue, and suggests the evolving Service Standard as a place to build evidence on AI's impact.

  11. Databricks Blog22

    BigQuery to Databricks: A Strategic Framework

    This Databricks guide outlines a BigQuery-to-Databricks migration framework across three pillars—Process, Technology, and People—covering estate assessment with the open-source Lakebridge profiler, BI-first or ETL-first entry points, wave-based migration, and dual operation via Lakehouse Federation. It describes moving data into open formats on Google Cloud Storage, migrating SQL logic through rule-based transpilation, LLM-assisted conversion, and engineers, plus three-level validation, and maps BigQuery governance into Unity Catalog. The People pillar covers shared Notebooks, Genie for natural-language code generation, and Databricks Academy training, closing with field lessons such as profiling before planning and defining parity criteria before dual-run starts.

Oct 27Tue
  1. Latent Space38

    Coding From the Himalayas With an Offline AI Agent

    A Thomson Reuters principal engineer describes running the OpenCode coding agent with Ollama and Qwen3.5 9B entirely on a laptop, then disconnecting the internet to fix a bug in an expense calculator and run its tests. The article covers model size and memory considerations, published benchmark scores, setup steps, and the limits of what can be done offline.

  2. Hacker News AI58

    Keeping API keys out of our AI agent's sandbox, and what that doesn't solve

    Doozy runs each task in a fresh sandbox holding only a signed, short-lived job token, and a credential gateway outside the sandbox verifies the token, checks whether the tool is enabled, and attaches the real key to that single call. Database queries run read-only with a 30-second timeout and a 200-row cap enforced outside the prompt. The author notes this stops key leakage but not prompt injection misusing enabled tools, and that a named-secret request path and per-tool approval remain open trade-offs.

  4. Hacker News AI58

    Dockerless Serverless GPUs: How I Built a Fast, Cheap AI SaaS with RunPod Flash

    This walkthrough of FlashFun.dev shows how RunPod Flash runs dedicated serverless GPUs from pure Python decorators with no Dockerfiles, cutting image generation cost from the 3–4 cents per image charged by hosted APIs like Google Vertex AI to between $0.00033 and $0.002 per image. The app races SDXL Turbo on a 24 GB GPU against Flux.1 Schnell on a 48 GB GPU behind a Cloudflare Worker, D1 and R2 stack, using scale-to-zero, model loading in container __init__, low-step distilled models and async polling to keep costs down. Benchmarks put pure GPU inference at 297ms against 1.1s total wall-clock time, with over 70% of latency spent on queuing, dispatch and base64 serialization.

  5. Simon Willison32

    webframe: evaluated as a scraper and a sandbox

    An evaluation of webframe, Jeff Lindsay's Go tool built on the glaze library that runs a web page like a program in a hidden headless web view, found it fast and lightweight for scraping with performance comparable to shot-scraper. It also surfaced rough edges including CSP failures, a 0×0 viewport, hanging loads, missing HTTP metadata, and limited browser controls.

  7. Databricks Blog20

    How to teach with Databricks Free Edition

    Databricks Free Edition is a perpetually free, browser-based version of the Databricks Data + AI Platform that students and educators can sign up for individually without a cloud contract, credit card, or installation, running on smaller compute under fair-use limits and not for production or commercial use. The article maps common courses—from intro programming and statistics to data engineering, data warehousing, ML, AI agents, and capstones—to platform tools such as notebooks, Apache Spark, Lakeflow, Delta Lake, Databricks SQL, MLflow, Genie Agents, and Databricks Apps, and answers instructor FAQs on distributing assignments and datasets, group work, and compute limits.

  8. PyTorch Blog34

    Optimizing Streaming Speech Recognition on Arm® Edge Devices with ExecuTorch

    This PyTorch blog case study takes the multilingual Nemotron 3.5 streaming ASR model from PyTorch to ExecuTorch and profiles it on a Google Pixel 11, measuring how chunk size and precision affect streaming WER and processing time. Enabling Arm SME2 cut whole-recording processing time from 9.79 to 4.61 seconds for FP16 (2.12x) and from 5.20 to 3.24 seconds for QC8W (1.61x), with GEMM driving most of the gain, while longer chunks improved accuracy at the cost of latency. ETDump and Arm Streamline were combined to attribute speedups to operators and confirm which KleidiAI SME2 microkernels actually ran.

  9. AWS Machine Learning Blog38

    Build agentic retrieval on a Managed Amazon Bedrock Knowledge Base with CDK

    This post shows how to build enterprise agentic retrieval on a Managed Amazon Bedrock Knowledge Base using the AWS CDK in Python, deploying four stacks (knowledge bases, AgentCore Gateway, agent runtime, and dashboards) with one `cdk deploy --all` command. It contrasts classic single-shot RAG with agentic retrieval, where an agent on AgentCore Runtime routes questions across two managed knowledge bases (financial and weather) exposed as MCP tools through the Gateway, invoking the AgenticRetrieveStream API for grounded, cited answers. The solution also provisions two CloudWatch dashboards spanning seven telemetry layers plus on-demand and continuous evaluation, since agentic systems need observability to verify behavior.

  10. AWS Machine Learning Blog40

    Groundhog Day for AI agents: Prompt caching patterns for using OpenAI models on Amazon Bedrock

    This post explains how AI agents resend their full context (tool definitions, instructions, and history) on every turn, and how Amazon Bedrock prompt caching avoids recomputing that prefix by reusing saved key-value state. It covers implicit versus explicit caching, caching conversation history and tool results, handling tool changes with allowed_tools and additional_tools, sharing cached prefixes across subagents and new sessions via prompt_cache_key, and monitoring cache reads and writes through response usage and CloudWatch.

  11. AWS Machine Learning Blog34

    Fleet-wide computer vision lifecycle at the edge with SageMaker SDK v3

    This post updates a 2023 MLOps pipeline pattern for visual quality inspection to Amazon SageMaker Python SDK v3, replacing the deprecated SageMaker Edge Manager with SageMaker Neo for edge optimization. It describes a dual-branch SageMaker Pipeline that trains an anomaly detector and a defect classifier per camera, gates models on their exported ONNX artifacts, compiles them with Neo, and registers them with camera metadata, while a Step Functions and DynamoDB semaphore layer paces fleet training. The sample deploys via AWS CDK and a full synthetic-data run costs about $0.07 in compute.

Oct 24Sat
  1. Simon Willison20

    Quick Study

    A prompt to Claude Opus 5.5 High asks it to build an artifact that opens a photo and, within a few seconds, paints a version of that photo using a canvas element and a simulated paintbrush. The post also references a previous experiment in which Claude Fable simulated a watercolor illustration with P5.js.

  2. AWS Machine Learning Blog58

    Multi-Turn Reinforcement Learning on Amazon SageMaker AI: A hands-on guide

    This AWS post walks through an end-to-end Multi-Turn Reinforcement Learning pipeline on Amazon SageMaker AI, using a Wordle agent hosted on Amazon Bedrock AgentCore that reports one outcome reward per episode for GRPO training of a LoRA adapter. In the example run, gpt-oss-20b improved from 61% to 84% solve rate on held-out words at default reasoning effort and from 15% to 69% at low effort, for about $339 in training tokens. It also covers IAM roles, dataset preparation, MLflow monitoring, serving-setting evaluation, cleanup, and reward-design mistakes and training failures encountered.

  3. AWS Machine Learning Blog34

    How Bayer Crop Science built an agentic decision engine on Amazon Bedrock AgentCore with AWS Unified Operations

    Bayer Crop Science built the Agentic Decision Engine (ADE), a multi-agent natural language interface over its Connected Decision Engine, running on Amazon Bedrock AgentCore with LangGraph orchestration and 22 specialist agents. In its first phase, ADE resolves about 80 percent of user questions without an engineer in the loop, and exposing APIs through AgentCore Gateway cut per-API integration overhead by more than 99 percent. The post details five design decisions, production readiness work such as task-level observability and cost attribution, and ongoing operations with AWS Unified Operations.

  4. AWS Machine Learning Blog22

    Orchestrating SageMaker AI endpoint auto scaling with AWS CDK

    Updating a SageMaker AI real-time endpoint configuration fails through CloudFormation or CDK because SageMaker AI requires the scalable target to be deregistered first, and manual deregistration leaves CloudFormation unable to track Application Auto Scaling resources. The post presents a reusable CDK construct that replaces the native scalable target and scaling policy resources with three custom resources—Deregister, Register Scalable Target, and Attach Scaling Policy—ordered with explicit dependencies and driven by a ConfigHash so endpoint and auto scaling changes deploy together. It includes a walkthrough using the sample-sagemaker-endpoint-autoscaling GitHub repository and guidance on integrating the construct into an existing stack.

Oct 23Fri
  1. AWS Machine Learning Blog18

    How U.S. Hunger connects leaders and data using Amazon Quick

    U.S. Hunger, which reports delivering more than 250 million meals, uses Amazon Quick to let CEO Rick Whitted explore Full Cart datasets directly and to give 17 colleagues across leadership, technology, finance, and compliance shared Spaces for KPI definitions, financial planning, and research. Data from its Impact Manager platform is refreshed from SQL Server into SPICE nightly at 2 AM ET, and the organization plans a Q4 2026 enterprise KPI framework routing NetSuite, Salesforce, and other systems through Boomi into Amazon Redshift.

  2. AWS Machine Learning Blog34

    Train Qwen3 on AWS Trainium with torchtitan

    This post walks through training Qwen3 three ways on a single trn2.48xlarge using torchtitan-neuron: via Hugging Face Transformers v5 as a modeling backend, via torchtitan's native Qwen3 by changing config.model_spec, and via NKI mixture-of-experts kernels from the torchtitan-neuron recipes, all using the same torchrun launch pattern. It also shows how to load and save published safetensors checkpoints, attach a custom NKI rope_hf kernel through torchtitan's override registry, and scale with data and tensor parallelism across 64 logical NeuronCores.

  3. AWS Machine Learning Blog38

    Adaptive agentic intelligence framework using Strands Agents

    The Adaptive Agentic Intelligence Framework (AAIF), built on Strands Agents, uses a small local language model (llama3.2:1b) as an orchestrator that routes routine requests to local SLMs via Ollama and complex requests to cloud models through Amazon Bedrock. The post walks through an IoT monitoring reference implementation with tools for device telemetry, local vision analysis, and Bedrock-based expert insights, and describes cloud-only, hybrid, and air-gapped deployment configurations. It also outlines converting tools into MCP servers for distributed tool calling and applying Amazon Bedrock Guardrails to the cloud inference path.

  4. AWS Machine Learning Blog58

    5 production challenges in multi-agent systems and how Deep Insight solved them

    AWS's Solutions Architecture team describes Deep Insight, an open-source multi-agent system (Coordinator, Planner, Supervisor, Coder, Validator, Reporter, Tracker) that turns a CSV file and a natural-language prompt into a validated DOCX analysis report with charts. The post, part one of three, maps five production challenges to a stack: Strands Agents SDK Graph and Agents-as-Tools patterns for execution flow, role-specific Claude models on Amazon Bedrock, Amazon Bedrock AgentCore for managed deployment, AWS Fargate plus Application Load Balancer for isolated code execution, and DynamoDB, Amazon SNS and Amazon Cognito for monitoring. It also cites LG Electronics' ChatInsight and TechRecon as reuse of the same architecture.

  5. AWS Machine Learning Blog20

    Securing Quick access from corporate networks with AWS PrivateLink

    This walkthrough explains how to connect on-premises data sources to Amazon Quick privately using AWS PrivateLink VPC endpoints and Quick VPC connections, so traffic stays off the public internet over Direct Connect or Site-to-Site VPN. It covers endpoint creation for website and API access, DNS resolution via Route 53 private hosted zones, endpoint policies, execution roles, data source VPC endpoints, required external domains, and enforcing VPC endpoint restrictions. It also addresses identity federation with IAM Identity Center and notes that browser sign-in still requires outbound access to public AWS sign-in endpoints.

  6. AWS Machine Learning Blog31

    How IskayPet unified corporate knowledge with Amazon Bedrock Managed Knowledge Bases

    IskayPet, an Iberian pet care company with over 330 stores and 4,500 employees, built a corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases that answers employee questions across retail operations, veterinary care, people and onboarding, and procurement in four languages and three countries without managing RAG infrastructure. The solution uses the native SharePoint connector with advanced indexing, a dedicated knowledge base per assistant scoped to specific sites or libraries, document-level access control tied to existing SharePoint permissions, and hybrid search with reranking. Built with Kiro and Claude Haiku 4.5, it reportedly cut time to find an operational answer from 3–5 minutes to about 7 seconds in roughly the first two months in production.

  7. AWS Machine Learning Blog34

    Deploy AI in a HIPAA-eligible environment with Amazon Quick

    This AWS post explains how to deploy Amazon Quick, a HIPAA-eligible service, for healthcare workloads that touch protected health information, covering covered entities and business associates, the distinction between HIPAA-eligible and HIPAA-compliant, and the unstructured (knowledge base) and structured (Amazon Quick Sight) PHI data paths. It details the controls Amazon Quick provides—managed infrastructure, encryption, RBAC and SSO, CloudTrail and CloudWatch vended logs—alongside what it does not do, such as de-identification and lake-level governance handled by AWS Glue, Glue DataBrew, and Lake Formation. It closes with a fictional health plan walkthrough, irreversible day-zero decisions (customer managed key, identity model, ACL-aware knowledge bases), and a step-by-step implementation guide.

  8. AWS Machine Learning Blog38

    Stream low-latency speech from AI agents using Kokoro TTS on Amazon SageMaker AI

    This AWS post describes streaming each sentence an agent produces to a hosted Kokoro-82M text-to-speech model on a SageMaker AI real-time endpoint, so synthesis starts on the first sentence instead of waiting for the full response. It covers bidirectional WebSocket handling, an incremental sentence chunker, and two transports for returning audio to the browser, reporting that incremental sending cut mean time to first audio byte from 329.3 ms to 156.7 ms in isolation and made bidi mode 2.4 to 3.5 times faster than batch in a deployed agent.

  9. AWS Machine Learning Blog32

    Stop guessing auto scaling targets for TTS on Amazon SageMaker AI

    This AWS post deploys Kokoro-82M, an 82-million-parameter non-autoregressive TTS model, as a custom container on an Amazon SageMaker AI real-time endpoint via AWS CDK stacks, then replaces a guessed auto scaling target with values derived from two live measurements: Q_max (the highest per-instance concurrency that still meets a 3,000 ms p95 time-to-first-audio SLO, measured at 50) and T_total (end-to-end scale-out time, measured at 260.2 s and planned against 320.2 s). Scaling uses the native ConcurrentRequestsPerModel metric, and a five-command tool chain (drift, qmax, ttotal, plan, validate) computes the scale-out threshold (37.5), scale-in threshold (25.0) and asymmetric cooldowns by arithmetic. The authors note the methodology generalizes to other latency-sensitive, concurrency-bound real-time SageMaker AI endpoints, while the specific numbers hold only for Kokoro-82M on ml.g5.xlarge.

  10. AWS Machine Learning Blog38

    How Rescale built an AI triage agent with Strands Agents and AI-DLC

    Rescale used the open source AI-Driven Development Lifecycle (AI-DLC) framework on AWS to build an agent that classifies and routes nightly end-to-end test failures, going from problem definition to staging in five days and to production within weeks. The agent runs in Rescale's Argo Workflows CI/CD pipeline on Amazon EKS, uses Claude on Amazon Bedrock for classification, retrieves historical failure patterns from a knowledge base, and queries pod logs via MCP, producing structured remediation reports. In production, classification agreement with human triage rose from 44% to 68%, and time blocking production deployment while failures are analyzed fell 20%.

Oct 22Thu
  1. Hugging Face Blog27

    Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium.

    This post walks through system-level profiling of inference on AWS Trainium using TorchNeuron, its open source native PyTorch backend, starting from scratch with no prior profiling experience. It shows how to configure torch.profiler with NeuronConfig and NeuronProfiler to capture a clean trace, read the key_averages() table to find operations consuming Neuron device time, and follow an operation through Neuron Explorer from framework dispatch to hardware execution. Using three RMSNorm implementations, it reports naive ops at 2,355 µs of Neuron time versus 403 µs for torch.rms_norm and 376 µs for naive plus torch.compile.

Oct 21Wed
  1. Latent Space62

    Claude Mods: Flipping the Harness Inside Out

    The author describes Claude Mods, Claude Code plugins written as TypeScript or JavaScript functions that hook into events like prompts, tool calls and interface renders to customize the CLI and Desktop behavior, framing them as an early "Attention Interface" that users can shape themselves. He highlights the built-in You Should Know mod, which flags uncommitted work the agent might cause you to lose, and his own Next Steps Supervisor from the open-source ModSmith plugin, then compares Claude Mods with OpenAI's ChatGPT Intelligent UI and Cursor's PR Routing & Approval. He also notes downsides—noise (99 of 111 turns triggered his supervisor), token cost of roughly 5–6k input-equivalent tokens per check on a 50k-token session, and the fact that mods run unsandboxed with your permissions.

  2. Simon Willison34

    Battle Drones - a vibe coded RTS with audio-based multiplayer

    Simon Willison describes Battle Drones, a browser-based Command & Conquer-style RTS built largely by coding agents such as Claude Code over 12 major iterations and 321 commits, with 3D models, fog of war, multiple maps and a random map generator, several game modes, and AI personalities. It supports multiplayer between two nearby devices by synchronizing game state over audio, and an online multiplayer mode was later added via a stateless WebSockets relay server on Fly.io. The post also covers agent-vs-agent battles where two LLMs play each other, and lessons such as using a deterministic simulation engine for replays and multiplayer.