🏥 In Practice

45 articles

🟡 🏥 In Practice April 27, 2026 · 3 min read

GitHub changes App installation token format: from 40 to ~520 characters, breakage risk for CI/CD pipelines

GitHub begins rolling out a new App installation token format on April 27, 2026. The old 40-character format is replaced by a JWT format of ~520 characters with the prefix ghs_APPID_JWT. Phase 1 (April 27 – mid-May) covers GitHub Actions and featured integrations; Phase 2 (mid-May – end of June) covers all App tokens. Developers must expand DB columns to 520+ characters and remove regex/length checks.

🟡 🏥 In Practice April 27, 2026 · 3 min read

GitHub Copilot receives GPT-5.5 GA: available on all major IDEs with 7.5× premium multiplier

GitHub announced the general availability (GA) of GPT-5.5 for Copilot Pro+, Business and Enterprise users on April 24, 2026. The model is available in VS Code, Visual Studio, JetBrains, Xcode, Eclipse, GitHub Mobile and Copilot CLI. Pricing: 7.5× premium request multiplier as promotional pricing. Enterprise and Business administrators must manually enable the GPT-5.5 policy.

🟢 🏥 In Practice April 27, 2026 · 3 min read

arXiv:2604.21361: Open Compute Project maps time/causality failures in distributed AI inference systems — 5 ms clock skew breaks observability

The team of Ankur Sharma, Deepa Shah, David Lariviere and Hesham ElBakoury from the Open Compute Project Unified Intelligent Infrastructure workstream published on April 23, 2026 an experimental study on time, causality and observability failures in distributed AI inference systems. Just 5 ms clock skew between nodes breaks causality observability while output remains correct — a serious problem for debugging large LLM serving deployments.

🟡 🏥 In Practice April 25, 2026 · 3 min read

GitHub Copilot Introduces Inline Agent Mode in Public Preview for JetBrains IDEs — Agentic Capabilities Directly in Inline Chat

GitHub announced a public preview of Inline Agent Mode for JetBrains IDEs on April 24, 2026, including improved Next Edit Suggestions with remote edits, global auto approve, more flexible terminal command control, and admin activation for Business and Enterprise plans.

🟢 🏥 In Practice April 25, 2026 · 3 min read

Anthropic Introduces Rate Limits API: Administrators Can Now Programmatically Retrieve Rate-Limit Configuration for Their Organization and Workspaces

Anthropic announced the Rate Limits API on April 24, 2026, part of the Admin API, which allows administrators to programmatically read the configured rate limits for their organization and individual workspaces. The endpoint returns limits by model group, batch, files, skills, and web search tool, and requires a dedicated Admin API key.

🟡 🏥 In Practice April 24, 2026 · 3 min read

Anthropic and NEC build Japan's largest AI engineering workforce — Claude for 30,000 NEC employees

Anthropic and Japan's NEC announced a partnership on April 24, 2026 that will give Claude access to approximately 30,000 NEC employees. NEC becomes Anthropic's first Japanese global partner and is building a Center of Excellence for AI engineering in finance, manufacturing, cybersecurity, and local government.

🟡 🏥 In Practice April 24, 2026 · 2 min read

AWS: multimodal biological foundation models accelerate drug discovery by 50 percent and diagnostics by 90 percent

AWS has published an overview of applying multimodal biological foundation models in drug development and patient care. Combining genomics, medical imaging, and clinical data achieves 4–7% higher AUC accuracy, up to 90% time savings in image analysis, and up to 50% lower drug development costs.

🟢 🏥 In Practice April 24, 2026 · 2 min read

CNCF: infrastructure engineer migrated 60+ Kubernetes resources in 30 minutes with the help of an AI agent

The CNCF blog published a case study of a migration from Ingress NGINX to Higress where an AI agent helped migrate 60+ Kubernetes resources in 30 minutes including validation. Higress is an AI-native gateway based on Envoy and Istio, with token rate limiting and caching for LLM traffic.

🟢 🏥 In Practice April 24, 2026 · 2 min read

GitHub Copilot Chat: new features for understanding pull requests and automated code reviews

GitHub has added three pull request features to Copilot Chat: understanding a PR through comments and reviews, structured reviews, and summarized change overviews. The features are available at github.com/copilot and directly from the diff view by clicking the Copilot button.

🟡 🏥 In Practice April 23, 2026 · 3 min read

AWS and NVIDIA Parakeet-TDT bring transcription for 25 languages at a cost of $0.00005 per minute

The AWS Machine Learning blog described how to use NVIDIA's open-source Parakeet-TDT-0.6B-v3 model for cheap multilingual audio transcription in the cloud. The model covers 25 European languages with automatic detection, and when combined with AWS Batch, processing one minute of audio costs just $0.00005 on Spot instances, or $0.00011 on on-demand g6.xlarge GPUs, with a scale-to-zero policy and the ability to process audio recordings longer than ten hours through buffered streaming.

🟡 🏥 In Practice April 23, 2026 · 2 min read

AWS SageMaker automatically benchmarks generative AI models and provides optimal inference configurations

Amazon SageMaker AI now automatically benchmarks generative AI models across different GPU configurations using the NVIDIA AIPerf tool, eliminating weeks of manual testing and providing recommendations ranked by cost, latency, or throughput.

🟡 🏥 In Practice April 23, 2026 · 2 min read

GitHub Copilot in VS Code gets BYOK: users can now connect their own keys for Anthropic, Gemini and OpenAI

GitHub has enabled Copilot Business and Enterprise users to bring their own API keys for major providers including Anthropic, Google, OpenAI, OpenRouter, and Azure in VS Code. BYOK models work within Copilot Chat and custom agents, with billing going directly to the chosen provider without consuming Copilot quota.

🟡 🏥 In Practice April 23, 2026 · 3 min read

GitHub Copilot for Jira gets custom agents, customized branching rules, and code review notifications

GitHub's latest updates to the Copilot cloud agent for Atlassian's Jira introduce a set of features that significantly deepen AI integration into project management. Teams using Jira as a task tracking system can now define their own custom agents, use Atlassian custom fields in rules, set customized branching rules per space, and receive code review request notifications directly in Jira — connecting the development flow between GitHub and the project management tool.

🟢 🏥 In Practice April 23, 2026 · 2 min read

OpenAI enabled free ChatGPT for verified clinicians in the US

OpenAI has enabled free access to ChatGPT for verified physicians, nurses, and pharmacists in the US. The program focuses on clinical documentation, patient care workflows, and medical research, with verification conducted through partnerships with American medical entities.

🟡 🏥 In Practice April 22, 2026 · 3 min read

Claude Cowork comes to Amazon Bedrock — AI for entire organizations

AWS and Anthropic enable running the Claude Cowork desktop application within AWS accounts via Amazon Bedrock. Data remains under user control, models are not trained on it, and integration with IAM and CloudTrail provides enterprise-grade auditing. Payment goes through existing AWS contracts.

🟢 🏥 In Practice April 22, 2026 · 2 min read

HolmesGPT and CNCF tools auto-diagnose Kubernetes alerts for $0.04

The STCLab SRE team uses HolmesGPT with the ReAct pattern and CNCF tools for automatic diagnosis of Kubernetes alerts. The cost is $0.04 per investigation, around 40% of alerts are resolved autonomously, and the most important lesson: quality runbooks matter more than model choice.

🟢 🏥 In Practice April 22, 2026 · 2 min read

On-device psychiatric AI: Gemma, Phi, and Qwen run without sending data to the cloud

Researchers led by Eranga Bandara published a mobile application that locally orchestrates Gemma, Phi-3.5-mini, and Qwen2 for DSM-5 aligned psychiatric assessments. The system sends no data to the cloud and targets sensitive contexts such as the military, criminal justice, and remote healthcare.

🟡 🏥 In Practice April 21, 2026 · 3 min read

GitHub Pauses Copilot Pro Sign-Ups Due to Agentic AI Pressure — Opus 4.7 Exclusive to Pro+

GitHub announced a temporary pause on new sign-ups for Copilot Pro, Pro+, and Student plans due to infrastructure pressure from agentic workflows. Opus models have been fully removed from the Pro plan and remain available only at the Pro+ tier. Existing users receive stricter usage limits and real-time consumption meters.

🟡 🏥 In Practice April 21, 2026 · 3 min read

IBM and Adobe Introduce Agentic Customer Experience Orchestration for Airlines and Healthcare

IBM and Adobe have introduced industry solutions combining agentic AI systems with Adobe Experience Cloud for airlines and healthcare, addressing the average annual loss of $29 million caused by fragmented customer experience.

🟡 🏥 In Practice April 21, 2026 · 4 min read

Microsoft, ANZ, HSBC, and Lloyds Unveil AI Agent for Trade Finance — Automated MT700 Letter of Credit Processing at Sibos 2025

Microsoft, in collaboration with ANZ, HSBC, and Lloyds Bank, published a proof-of-concept AI agent for trade finance. The agent parses MT700 letters of credit, detects discrepancies between invoices and conditions, and offers a conversational interface for treasury users. The solution was demonstrated at Sibos 2025 in Frankfurt.

🟡 🏥 In Practice April 20, 2026 · 3 min read

AgentV-RL introduces a tool-augmented verifier with forward and backward agents — 4B model outperforms SOTA reward model by 25.2%

AgentV-RL is a new framework for scaling reward modelling through an agentic verifier that uses multi-turn tool-augmented deliberation. Two complementary agents — forward (from premises to conclusion) and backward (from conclusion to premises) — validate reasoning. Through RL with proactive exploration, the 4B variant outperforms state-of-the-art outcome reward models by 25.2%.

🟡 🏥 In Practice April 19, 2026 · 3 min read

Claude Code architecture analysis: reverse-engineering the TypeScript source reveals 5 core values and 13 design principles of an AI agent tool

A new arXiv paper analyzes Claude Code's architecture by reverse-engineering the TypeScript source and comparing it with the OpenClaw open-source agent. It identifies 5 core values (human authority, safety, execution, capability, adaptability) and 13 design principles. The heart of the system is surprisingly simple: a while loop that calls the model, executes tools, and waits for user input.

🟢 🏥 In Practice April 19, 2026 · 2 min read

RACER: Training-Free Method That Doubles LLM Inference Speed by Combining Retrieval and Logits Draft Strategies

RACER is a training-free method for accelerating large language models that combines retrieval-based and logits-based drafting strategies for speculative decoding. It achieves more than 2× speedup over autoregressive decoding, outperforms all previous training-free methods, and has been accepted to ACL 2026 Findings. It was evaluated on Spec-Bench, HumanEval, and MGSM-ZH benchmarks.

🔴 🏥 In Practice April 18, 2026 · 3 min read

Anthropic Claude Design: visual collaborator powered by Claude Opus 4.7 for design, presentations and prototypes

Claude Design is a new Anthropic Labs product that turns Claude Opus 4.7 into a collaborative tool for visual creation — designs, prototypes, presentations, one-pagers. The system automatically reads the design system from codebases and design files, supports inline comments and sliders for adjustments, and offers a direct handoff to Claude Code for implementation. Available in research preview for Pro, Max, Team and Enterprise subscribers from April 17, 2026.

🟡 🏥 In Practice April 18, 2026 · 3 min read

Anthropic: infrastructure noise shifts agentic benchmark results by up to 6 percentage points

Researchers at Anthropic have demonstrated that RAM configuration and CPU headroom can shift agentic coding benchmark results by 6 percentage points — more than the difference between top models on the leaderboard. They tested Terminal-Bench 2.0 and SWE-bench. Recommendation: leads below 3 percentage points warrant skepticism until eval configuration is documented and matched.

🟡 🏥 In Practice April 18, 2026 · 3 min read

GitHub Copilot CLI gets automatic model selection: 10% discount on multipliers for all paid users

GitHub announced on April 17, 2026 that automatic AI model selection in the Copilot CLI tool has become generally available for all Copilot plans. The system dynamically routes requests to models such as GPT-5.4, GPT-5.3-Codex, Sonnet 4.6, and Haiku 4.5 depending on administrator policies. Paid users receive a 10% discount on the model multiplier when using auto mode — a model with a 1x multiplier consumes 0.9 premium requests instead of 1.

🟡 🏥 In Practice April 18, 2026 · 4 min read

PyTorch and Meta: over 90 percent effective training time through 40+ optimizations, MegaCache cuts PT2 compile time by 40 percent

Meta has published how it achieved over 90 percent Effective Training Time (ETT) for offline training of its recommendation models. The method includes more than 40 new optimizations in the PyTorch ecosystem, MegaCache which cuts PT2 compilation time by 40 percent, standalone model publishing saving 30 minutes per job, and async checkpointing. Improvements are open-sourced through PyTorch and TorchRec.

🟢 🏥 In Practice April 18, 2026 · 3 min read

AWS introduces granular cost attribution for Amazon Bedrock by IAM principals

Amazon Bedrock now tracks inference costs by IAM principal — the specific user, role or federated identity calling the API. The feature integrates with AWS Cost and Usage Reports (CUR 2.0) and Cost Explorer at no additional charge. It supports four access scenarios: direct IAM users, application roles, federated authentication and LLM gateway proxy patterns. Available in all commercial AWS regions.

🟡 🏥 In Practice April 17, 2026 · 2 min read

Amazon Bedrock: formal mathematical verification replaces probabilistic validation of AI outputs

Amazon Bedrock introduces Automated Reasoning checks that use SAT/SMT formal verification instead of probabilistic validation to verify AI outputs. Amazon Logistics reduced review cycles from 8 hours to minutes, Lucid Motors generates forecasts from weeks to under one minute, and education company FETG achieved 80 percent less effort and latency from 13 seconds to 1.5 seconds.

🟡 🏥 In Practice April 17, 2026 · 3 min read

AWS Nova Micro for Text-to-SQL: fine-tuning + serverless Bedrock for $0.80 per month

AWS demonstrated how LoRA fine-tuning of the Amazon Nova Micro model combined with serverless Bedrock on-demand inference can handle 22,000 SQL queries per month for just $0.80. Training costs $8 through Bedrock Customization or $65 through SageMaker. The approach eliminates the cost of continuous model hosting and is calibrated for variable production workloads.

🟡 🏥 In Practice April 17, 2026 · 2 min read

Google: AI Mode in Chrome brings side-by-side pages with AI assistant and multi-source search

Google launched new AI Mode upgrades in the Chrome browser that allow opening web pages side-by-side with the AI assistant, combining tabs, images and PDFs into one AI search, and accessing the Canvas tool for writing and coding from the Chrome search box. Available in the US from April 16, 2026 with planned global expansion.

🟡 🏥 In Practice April 17, 2026 · 3 min read

xAI Speech-to-Text API in general availability: 25 languages, batch and streaming

xAI has announced the general availability of its Speech-to-Text API supporting transcription in 25 languages through batch and streaming modes. The announcement comes one month after the Text-to-Speech API reached general availability in March 2026. With this, xAI completes its audio stack alongside the Grok language models and enters direct competition with OpenAI Whisper, Google Cloud Speech, and Azure Speech.

🟡 🏥 In Practice April 16, 2026 · 2 min read

GitHub: Copilot Cloud Agent Can Now Be Selectively Enabled Per Organization

GitHub has enabled enterprise administrators to selectively activate access to the Copilot cloud agent through custom properties, replacing the previous all-or-nothing approach. The new feature brings more granular control over AI agent capabilities at the level of individual organizations, with new API endpoints and management through the AI Controls interface within GitHub Enterprise settings.

🟡 🏥 In Practice April 16, 2026 · 2 min read

Microsoft: Frontier Transformation — How UBS, BMW, and Healthcare Are Moving from AI Experiments to Core Business

Microsoft has published the Frontier Transformation concept, describing industries' transition from AI experiments to integration into core business operations. Case studies include UBS for legal research, BMW for multi-agent vehicle analytics, Cooper Health Care for reducing clinician burnout, and Venchi for retail personalization.

🟡 🏥 In Practice April 15, 2026 · 2 min read

GitHub: Free Code Security Assessment Uncovers Vulnerabilities in Minutes

GitHub launches a free Code Security Risk Assessment powered by the CodeQL engine. It scans up to 20 of the most active repositories per organization and displays vulnerabilities by severity, language, and rule. Copilot Autofix resolved 460,258 alerts in 2025.

🟡 🏥 In Practice April 15, 2026 · 1 min read

GitHub: Model Selection for Claude and Codex Agents Now Available

GitHub now allows developers to choose between multiple AI models when launching Claude and Codex coding agents. Available models include Claude Sonnet/Opus 4.5 and 4.6 as well as GPT-5.2/5.3/5.4-Codex.

🟢 🏥 In Practice April 15, 2026 · 1 min read

HuggingFace: HoloTab — Free AI Assistant That Automates Browser Tasks

HCompany has launched HoloTab on the HuggingFace platform, a free Chrome extension that uses AI to automate web tasks. The key innovation is Routines — record an action once, repeat it endlessly.

🟡 🏥 In Practice April 14, 2026 · 2 min read

Google Chrome: AI Skills Turn Prompts Into One-Click Tools

Google has launched the Skills feature in Chrome, allowing users to save AI prompts as reusable one-click tools. The feature uses Gemini and works on Mac, Windows, and ChromeOS platforms.

🟡 🏥 In Practice April 14, 2026 · 2 min read

Google Research: Vantage — AI platform that assesses critical thinking and creativity through conversations with avatars

Google Research in collaboration with NYU presents Vantage, an experimental platform that uses generative AI to assess hard-to-measure human skills such as critical thinking and creativity. AI scoring showed agreement with human experts comparable to inter-expert agreement.

🟢 🏥 In Practice April 14, 2026 · 1 min read

AWS: How to build reward functions with Lambda for fine-tuning Amazon Nova models

Amazon Web Services has published a detailed technical guide for creating scalable reward functions using AWS Lambda for Amazon Nova model customization. The guide covers RLVR and RLAIF approaches, multi-dimensional reward system design, and monitoring via CloudWatch.

🟢 🏥 In Practice April 14, 2026 · 2 min read

Perplexity API: n8n Integration, AWS Marketplace, and New /v1/models Endpoint

Perplexity has announced several API updates in April 2026: a native n8n integration for visual AI workflows, availability on AWS Marketplace for simplified procurement, and a new /v1/models endpoint without authentication.

🟢 🏥 In Practice April 12, 2026 · 2 min read

ArXiv: Munkres' Entire Topology Textbook Formalized in Isabelle/HOL with LLM Assistance

A team led by Bryant has used an LLM-assisted pipeline to formally verify Munkres' entire 'General Topology' textbook in Isabelle/HOL — over 85,000 lines of verified code and all 806 formal results.

🔴 🏥 In Practice April 11, 2026 · 2 min read

OpenAI launches Academy — official educational platform with 24 courses

On April 10, OpenAI released its official educational platform OpenAI Academy with 24 courses covering AI fundamentals, ChatGPT, prompt engineering, safety, and industry applications ranging from healthcare to finance.

🟢 🏥 In Practice April 10, 2026 · 2 min read

AWS AgentCore enables a live AI browser in a React app with three lines of code

Amazon has introduced the BrowserLiveView component for React applications, which displays in real time what an AI agent is doing in a browser session. Streaming goes directly from AWS to the user's browser via the Amazon DCV protocol, bypassing the application server to minimize latency.

🟢 🏥 In Practice April 10, 2026 · 2 min read

AWS Bedrock explains model lifecycle: Active, Legacy and End-of-Life phases

Amazon has published an official guide to managing the lifecycle of foundation models in Bedrock. Models now have three clearly defined phases (Active, Legacy, End-of-Life) with 6-month notifications before deprecation and — starting February 2026 — an extended access period of at least 3 months in the Legacy phase.