Full-text search across 66404 articles. Combine with topic and date filters; results sorted by relevance.
A developer released @ttsc/evidence, a compiler-based tool that converts natural-language coding rules from AGENTS.md and SKILL.md files into enforced compiler rules, after citing studies showing six frontier models foll…
Skyvern shipped its August 2026 changelog, headlined "Building Agents just got 10x easier," introducing the opt-in Skyvern 3.0 engine beta that drives the browser through a persistent tool loop in which only actions coun…
Databricks Field Engineering has released Consort, an open-source agentic framework for test-driven development on a branching database, built on Lakebase Postgres. The framework enables developers to branch databases li…
An IT analyst at bestaiweb.ai detailed how a March 2026 incident revealed the difference between JSON parse failures and schema failures in LLM outputs, leading to a dual defense of embedding exact schemas in prompts and…
OpenBMB released MiniCPM5-2B, a 2.5-billion-parameter dense language model designed for on-device deployment, which scores an average benchmark of 53.9, outperforming larger 4B-class models like Qwen3.5-4B (51.1) on codi…
A legal software company's R&D organization tripled output per engineer in 18 months by rebuilding its development life cycle around AI agents, according to its CTO. Deployments grew from 82 to more than 155 per quarter,…
Meta's Superintelligence Labs released Muse Spark 1.3 on September 2nd, priced at $0.55 per task, 42% cheaper than GPT-5.6 Sol at the same intelligence score, and it scored 75.4% on the DeepSWE 1.1 coding benchmark, ahea…
Masterpoint engineer Veronika Gnilitska outlines a workflow that uses AI agents and MCP servers to convert AWS click-ops resources into Terraform/OpenTofu code, emphasizing human review gates and verification scripts to …
Anthropic's Threat Intelligence Report, published on 27 August 2025, disclosed that a lone threat actor used its Claude Code AI agent to rob 17 organizations over three months, harvesting Social Security numbers, bank de…
Adding more AI agents to an engineering team can reduce output, according to a 30-year programmer who found that scaling from 4 to 8 agents cut monthly code production from 70,000 to 67,000 lines. The analysis invokes Am…
Google has placed Antigravity's /boost reasoning mode, which splits hard problems across multiple agents, behind paid Antigravity 2.0 and CLI plans, sparking debate on Hacker News over pricing. A LeadDev survey of nearly…
Anthropic released Claude Fable 5.1 on September 1, 2026, cutting cache-read pricing by 75% to $0.25 per million tokens while keeping base input at $10 and output at $50 per million tokens, yielding an estimated 25% lowe…
CodeRabbit's review of Fable 5.1 found that the coding agent improved precision by 4.5 percentage points to 37.3% and cut total review comments by 87 to 166, but recall dipped 1.0 point to 61.0% and latency rose 48.7% to…
HashCortX v2.5.0, a local-first AI workspace app, now runs on pre-2013 CPU Windows devices, according to its developer. The MIT-licensed desktop app supports 11 cloud AI providers plus Ollama, includes an autonomous codi…
Anthropic's AI-native SDLC playbook restructures software development around coding agents, but its verification stage depends on infrastructure the playbook does not specify, leaving agents to test against fakes that ma…
Microsoft Fabric's Copilot, integrated across its data platform, enables automated data engineering by generating PySpark ETL code, debugging Spark stack traces, and writing DAX measures, requiring an F64 capacity or equ…
A developer demonstrates how to build a multi-agent AI system in Flutter, using a Planning Agent, Generation Agent, and Validation Agent to handle complex tasks. The approach leverages Gemini API with structured output t…
An engineer's experiments with using LLMs to write technical documentation found that models produce fluent but factually wrong docs, inventing parameters and behaviors not present in the code. The developer recommends c…
NVIDIA published a tutorial on training a cross-embodiment robot navigation policy using an agent-driven workflow based on its COMPASS framework, which reuses the pretrained NVIDIA X-Mobility policy and trains a residual…
A new set of 10 Product Owner interview questions for the age of AI argues that hiring managers should test judgment about what to build rather than fluency with AI tools, as the cost of code generation collapses. The qu…