A developer documented deploying a Spring Boot-based Gemini chat app to Render's free tier, using a multi-stage Dockerfile that builds with Maven and Java 17 and runs on a slim JRE-only image. The wri…
A developer has outlined five distinct failure modes of "context rot" in LLM agent harnesses, arguing that degradation in reasoning quality occurs as sessions grow even before a context window is exha…
A developer has released an unofficial, community-built Java 21+ SDK for TypeSafe AI's System One API (POST /v1/systemone), offering sync and async calls, automatic retries with exponential backoff an…
Search professionals should prioritize backend software engineering fundamentals and hands-on experience with LLMs, agents, and embeddings, according to a hiring-trends report by Brian Pedersen cited …
Rage4J, a Java library for evaluating LLM applications, is now available at version 1.0.4 through Maven, according to its project page. The tool measures accuracy, relevance, and faithfulness of AI re…
A developer released a Spec Driven Development kit that encodes the rules of the HexaLayered Architecture into a Claude Code-readable .claude directory, including a constitution.md of testable constra…
A developer ran six Codex coding-agent executions of a Java String Calculator kata, varying the underlying model (Sol, Terra, Luna) and reasoning effort, to study how agents, a repository skill, and t…
A developer discovered that starting with JDK 23, the javadoc tool embeds default DejaVu web font files (about 4 MB) into generated API documentation, causing unexpectedly large artifacts. The issue c…
Safer-dependencies, a new security layer for Claude Code, automatically audits and blocks risky dependencies—including CVEs, typosquats, abandoned packages, and version-age issues—across npm, PyPI, Ru…
In the seventh installment of the Harness Engineering series, the developer details the Memory Layer, a component that gives AI agents persistence within and across sessions. The article distinguishes…
In the sixth part of the Harness Engineering series, the developer explains the role of the Environment in agentic systems, where tool side effects materialize. The post outlines three key properties—…
In the fifth installment of the Harness Engineering series, the developer introduces context engineering, the discipline of designing the payload sent to a language model on every turn of an agentic l…
A new Bash wrapper called mvn-lite reduces Maven build output for coding agents by 99%, cutting successful output from 6,753 bytes to 16 bytes in a real four-module Java application, while preserving …
JetBrains announced that IntelliJ IDEA's Java and Kotlin intelligence is now available as a preview extension for third-party editors, starting with VS Code and its forks such as Cursor. The Java & Ko…
OpenJDK elevated JEP 539 (Strict Field Initialization in the JVM, Preview) and JEP 401 (Value Objects, Preview) to Targeted for JDK 28, while JEP 535 (Shenandoah GC: Generational Mode by Default) move…
A series of vector database courses, led by Doug Turnbull and Adam Hevenor, will run the week of August 10, covering how to choose a vector database, improve hybrid search, and build a vector database…
A developer built and deployed a Java AI agent using the Google Agent Development Kit (ADK) on Debian 13. The agent, which provides time and weather information, was compiled with Java 25 and deployed…
An Android developer updated the Be Nice app to use Jetpack AppFunctions alpha10, which removed the appfunctions-service artifact and requires hosting an @AppFunctionServiceEntryPoint AppFunctionServi…
A developer modernizing a 20-year-old Java 1.5 codebase found that large language models initially produced plausible but incorrect answers, such as hallucinating dependencies and assuming a non-exist…
Software engineer Doug Turnbull argues that developers should prioritize writing code over specifications when working with AI coding agents, using tests as executable requirements to gradually expand…