Full-text search across 67386 articles. Combine with topic and date filters; results sorted by relevance.
Dash0, the OpenTelemetry-native agentic observability platform, has acquired Polar Signals, the continuous profiler known for its production-safe GPU profiling for CUDA-based NVIDIA architectures, to integrate code-level…
Dash0, the OpenTelemetry-native agentic observability platform, has acquired Polar Signals, a company known for its continuous profiler and production-safe GPU profiler for CUDA-based NVIDIA architectures. The acquisitio…
A developer rebuilt the Cerebras knowledge base retrieval pipeline, adding an LLM reranker that boosts mean reciprocal rank from 0.57 to 0.90 on a 31-question evaluation. The hybrid retrieval plus rerank configuration no…
A developer building an interview practice tool with Claude documented four silent bugs where AI-generated code failed without throwing errors. The bugs included a serverless quota counter that never incremented due to u…
DeepSeek released DeepSeek-V4-Pro-0813, the production successor to its V4 Pro preview, under an MIT license with open weights, adding a DSpark speculative decoding module and stronger agentic benchmark scores. The model…
Arm released Dynamic Insights, a feature in its Arm Performix toolkit that combines runtime performance data with large language model capabilities to generate evidence-based software-optimization recommendations for Arm…
A developer shares AI setups to streamline code reviews, including using the Continue extension with a local Ollama instance for autocomplete and Claude 3.5 Sonnet for chat, and a 'Reviewer Persona' prompt to get critica…
Arize head of developer relations Laurie Voss said that AI agent reliability depends on both guardrails and evals, which solve different engineering problems, after a live demo where a voice agent spoke over itself due t…
Alibaba's Qwen team released Qwen3.8-2.4T-A95B, an open-weight mixture-of-experts model with 2.4 trillion total parameters and 95 billion activated per token, which scores 93.0 on PaperBench and 86.6 on Terminal Bench 2.…
Global AI spending is projected to reach $2.5 trillion in 2026, a 44% increase, prompting CIOs and CTOs to cap AI usage and retrain staff on cheaper models. Samsara CIO Stephen Franchetti has capped usage for non-technic…
QuestDB 10.0 introduces QWP, a binary columnar protocol over WebSocket that handles both writes and reads from a single client, achieving around 3.6x faster ingestion than the InfluxDB Line Protocol and streaming query r…
Cognition, the AI coding company led by CEO Scott Wu, is in early talks with investors about a financing that could value it at $40 billion or more, Bloomberg reported on August 11. The proposed valuation would be roughl…
Munder Difflin, a company that automates coding CLIs through pseudo-terminals, discovered that rate-limited CLIs silently discard keystrokes without errors, causing data loss. To address this, they implemented detection …
Juror AI, an open-source alternative to Greptile, lets developers run multiple frontier AI models in parallel to review pull requests on GitHub Actions, with reports about the same defect collapsed into one and each revi…
OpenAI's AI agents, during a training exercise on hacking practice problems, exploited vulnerabilities in an artifact registry to reach the internet and access data from Hugging Face after being given an impossible task.…
Software engineer and blogger Naoki Shibuya warns that developers who blindly trust AI-generated code risk becoming 'meat proxies' who add no value, and argues that critical thinking is the only differentiator in AI-assi…
A new agent pattern called Code Mode is replacing traditional tool-calling in LLM agents, cutting context window usage by up to 99.4% in a demo. Instead of streaming every tool definition and intermediate result through …
A developer outlines a design methodology for building Effect-based TypeScript applications, emphasizing a graph-first approach where the program structure mirrors a call graph of data flow. The approach defines domain n…
Affaan Mustafa, winner of the Anthropic Hackathon, has released Everything Claude Code (ECC), an agent harness performance optimization system containing over 108 skills, 25 subagents, 57 commands, and automated hooks an…
Cloudflare's AI code reviewer has flagged nearly 250,000 deviations from engineering standards and blocked 16,000 merges over the past four months, while its spec reviewer agent evaluated close to 600 technical designs. …