2026-08-01 17:19 UTC
Show HN: Agentmetry – local-first flight recorder for AI coding agents
Hacker News surfaced this AI signal from agentmetry.ai: Show HN: Agentmetry – local-first flight recorder for AI coding agents.
Topic
devtools
25 signals
4 in 24h
AI Coding Tools
Coding assistants, repository agents, IDE copilots, and software-building workflows.
Latest Signals
AI Coding Tools feed
2026-08-01 16:59 UTC
IssueTrojanBench Benchmarks AI Coding Agents Against Malicious Requests
IssueTrojanBench is a new benchmark designed to test AI coding agents' responses to malicious issue requests. It aims to evaluate the security and robustness of AI coding tools.
2026-08-01 16:58 UTC
Introducing the Kotlin Benchmark for AI Coding Agents
JetBrains has introduced the Kotlin Benchmark to evaluate AI coding agents on real-world Kotlin tasks. This benchmark aims to provide a standardized way to assess AI performance in coding Kotlin.
2026-08-01 15:25 UTC
Cursor removed cost information from the usage page and CSV export
No summary available yet.
2026-07-31 12:32 UTC
Cursor for iPad
Hacker News surfaced this AI signal from cursor.com: Cursor for iPad.
2026-07-31 07:00 UTC
DeepSeek V4 Flash updates weights on AI Gateway, boosting Terminal-Bench score
DeepSeek V4 Flash now runs updated weights by default on AI Gateway, improving its agentic capabilities. Its Terminal-Bench score increased from 56.9 to 82.7 without any change to the model ID or user code.
2026-07-31 00:00 UTC
Laguna S 2.1 AI Model Gains 10x More Capacity on Vercel AI Gateway
Laguna S 2.1 from Poolside now supports 10 times more capacity on Vercel's AI Gateway for both paid and free versions. This upgrade enables handling significantly higher volumes of requests, benefiting agentic coding and long-running tasks.
2026-07-30 17:44 UTC
Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments
Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and reliable verification. To expand this su...
2026-07-30 00:00 UTC
AI Gateway: GPT-5.6 pricing and speed updates
On AI Gateway , GPT-5.6 Luna and GPT-5.6 Terra are now cheaper and <a href="https://...
2026-07-28 17:00 UTC
AI Coding Agents Accelerate Scientific Computing and Discovery
Scientists are using AI coding agents to modernize scientific computing, speeding up software development and research in fields like genomics. This approach enhances the efficiency of complex computational tasks.
2026-07-28 13:00 UTC
AI Coding Agents Risk Exposing Credentials in Supply Chain Attacks
AI coding agents can inadvertently expose sensitive credentials during supply chain attacks. Docker Sandboxes offer a solution by isolating secrets from the agent's access.
2026-07-23 00:00 UTC
Code Finder: fast, efficient code search for coding agents
Code Finder runs its own search loop and hands your coding agent the exact files and line ranges, faster and cheaper than the agent searching on its own.
2026-07-15 12:53 UTC
Final article in series on improving AI coding agent evaluations
The eighth article in Microsoft's series on Agent Experience (AX) discusses how to effectively evaluate AI coding agents and improve their integration with technology. It covers controlling the agent stack, measuring extension impact, and iterating for better results.
2026-07-13 13:00 UTC
Introducing Precursor: detecting agentic behavior with continuous client-side signals
Precursor, our new continuous behavioral validation engine for bot management, offers visibility into how humans and bots actually interact across the full user journey. By turning session-level behavior into bot detection signals, it identifies advanced auto...
2026-07-08 12:11 UTC
The hidden variables in your agent eval
This is the seventh article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can’t control in the agent stack, how to measure whether your extensi...
2026-07-02 18:15 UTC
Devin Desktop, Replacing Windsurf
Hacker News surfaced this AI signal from cognition.com: Devin Desktop, Replacing Windsurf.
2026-07-02 09:03 UTC
Study Shows AI Coding Tools Double Developer Pull Requests in Enterprise
A longitudinal study of a mid-sized AI-forward company reveals that mandating AI coding tools led to a doubling of merged pull requests per engineer since mid-2025. The study analyzed data from 802 developers and over 196,000 pull requests.
2026-07-01 14:31 UTC
What AI benchmarks are not telling you
This is the sixth article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can’t control in the agent stack, how to measure whether your extension...
2026-06-26 00:00 UTC
On owning a codebase, and why it may be the hardest job in software
AI coding agents are producing more code than ever, but the world still runs on massive, decades-old codebases. Why owning and understanding them may be the hardest job in software.
2026-06-12 18:00 UTC
Award-Winning Researcher Trains Robots to Make Educated Guesses
<a href="https://yenlingkuo.com"...
2026-05-19 17:45 UTC
Google just redesigned the search box for the first time in 25 years — here’s why it matters more than you think.
For a quarter century, the Google search box has been one of the most recognizable interfaces in computing: a thin white rectangle, a blinking cursor, a few typed words, and a list of blue links. On Tuesday, Google will formally retire that paradigm. <p...
2026-05-08 00:00 UTC
Why coding agents fail in large codebases (and what to do about it)
Data from 1,281 agent runs across 40+ large open source repos reveals five repeatable failure patterns in coding agents, and the infrastructure fixes for each.
2026-04-21 18:02 UTC
Meet Replit Security Agent
Replit gives professionals a secure place to build with AI. Replit Agent already protects your apps as you build by automatically scanning for vulnerabilities, and audits dependencies, before your projects are ever published. Before coding agents, a full pre-...
2026-03-03 00:00 UTC
CodeScaleBench: Testing coding agents on large codebases and multi-repo software engineering tasks
The initial findings from CodeScaleBench, a new benchmark designed to evaluate coding agents against the true complexity of enterprise software development, including large codebases and multi-repository tasks.
2026-02-25 00:00 UTC
A new era for Sourcegraph: The intelligence layer for AI coding agents and developers
Today, we're announcing Sourcegraph 7.0, a release that marks the beginning of a new chapter for our company and product.
Companies (8)
View allModels (1)
View allProducts (3)
View allAbout this Topic
Stable editorial lensCoding assistants, repository agents, IDE copilots, and software-building workflows.