This release backports a fix originally released in v10.3.0 that prevents ESLint from crashing in host environments where require.cache is unavailable, such as Yarn Plug’n’Play.
Bug Fixes
253be16 fix: handle unavailable require cache (backport of #20812 to v9.x) (#21065) (Eric)
Documentation
74930ed docs: switch build to Node.js 24 (#20894) (Milos Djermanovic)
New option checkConstructorCallCallbacks in max-nested-callbacks
The max-nested-callbacks rule now supports a checkConstructorCallCallbacks option.
When enabled, the rule also counts callback functions passed to constructor calls with new, such as new Promise((resolve) => {}), when calculating nesting depth.
For example, with { "max": 1, "checkConstructorCallCallbacks": true }, the rule reports the following code as exceeding the allowed callback nesting depth:
run(()=>{newPromise(resolve=>resolve());});
1 2 3
New option errorClassNames in preserve-caught-error
The preserve-caught-error rule now supports an errorClassNames option.
This option lets you specify additional custom error class names that must preserve the original caught error by passing it as a cause.
For example, with { "errorClassNames": ["MyError"] }, the following code is reported because the thrown MyError does not include the original error as a cause, just like built-in error types must:
try{doSomething();}catch(error){thrownewMyError("something went wrong");}
1 2 3 4 5
Suggestions for no-compare-neg-zero
The no-compare-neg-zero rule now supports suggestions. Where appropriate, it suggests replacing -0 with 0 or using Object.is() instead of operators such as === or !==.
For example, for an expression such as x === -0, the rule suggests x === 0 to preserve the existing comparison behavior, and Object.is(x, -0) to distinguish -0 from +0.
Ranjan Roy from Margins is back for our weekly discussion of the latest tech news. We cover: 1) OpenAI debuts its new superapp 2) What happens when all AI products converge 3) Are consultants the key to winning in AI? 4) Are all AI products commoditizing? 5) Meta's new Muse Spark 1.1 model is very cheap 6) Zuck confirms Meta is thinking about a cloud business 7) Is it bad economics to rent your compute to competitors? 8) Instagram's loose Ai reuse settings 9) Oh man, Meta is relevant in the AI discussion again 10) Professor accuses students of cheating with ChatGPT 11) Was professor wrong?
Enjoying Big Technology Podcast? Please rate us five stars ⭐⭐⭐⭐⭐ in your podcast app of choice.
Want a discount for Big Technology on Substack + Discord? Here’s 25% off for the first year: https://www.bigtechnology.com/subscribe?coupon=0843016b
Four major releases—GPT Live, Grok 4.5, Cognition SWE 1.7, and GPT‑5.6 Sol—signal an accelerated model cadence and growing specialization across AI. GPT Live introduces full‑duplex voice with background model orchestration for real‑time translation, tutoring, and conversational assistants. Grok 4.5 and Cognition SWE 1.7 prioritize cost‑efficient, high‑speed agentic coding and workflow automation while GPT‑5.6 Sol acts as a fast, practical workhorse contrasted with Fable's deeper reasoning.
As artificial intelligence continues to evolve, ensuring the safety and security of AI agents has become more important. The Microsoft Learn documentation on agent safety provides a comprehensive overview of best practices and guidelines for developers.
The concept of shared responsibility is central to agent safety. While the Microsoft Agent Framework offers foundational tools and abstractions, it is ultimately the responsibility of application developers to ensure secure data flows. This includes validating inputs, configuring tools appropriately, and understanding the specific security needs of their applications.
Best Practices for Safe Agents
To create safe AI agents, developers should adhere to several best practices:
Deterministic Defenses: Implement label-based defenses to protect against prompt injection and data exfiltration. This proactive approach helps mitigate risks associated with adversarial inputs.
Data Flow Understanding: Gain a thorough understanding of how data flows through various components of the agent, including user input, chat history, and context providers. This knowledge is crucial for identifying potential vulnerabilities.
Data Security Measures
Robust data security is essential, especially when handling sensitive information such as Personally Identifiable Information (PII). Developers must implement stringent security measures to protect this data throughout its lifecycle.
Awareness of Indirect Prompt Injection
Developers should be vigilant about the risks of indirect prompt injection, where adversarial content can manipulate the behavior of the language model (LLM). Recognizing these risks is vital for maintaining the integrity of AI agents.
Integration with Microsoft Security Tools
The documentation highlights the integration of Microsoft Agent Framework with existing security infrastructures, such as Microsoft Defender and Microsoft Entra. This integration enhances the overall security posture of AI agents, providing additional layers of protection.
Real-World Applications
The insights from the documentation have practical applications…
Enterprise AI Operations: Organizations can leverage AI agents to manage operations at scale, transforming fragmented experimentation into trusted, reliable processes.
Automating Security Tasks: Tools like Microsoft Security Copilot automate repetitive security tasks, allowing teams to focus on more strategic initiatives.
Supporting Data and Monitoring
Centralized visibility into AI agents is crucial for administrators. By monitoring usage and security signals, organizations can proactively manage their AI agents, ensuring they operate safely and effectively.
At the highest level, cross-platform UI technologies prioritize coordinated featurefulness over polished simplicity.
I’ve added a coda to that article about how coding agents actually strengthen the argument for Electron on large teams, at least for now.
The initial release of the new ChatGPT app has been clumsy – there’s a lot of work to do to get Electron ChatGPT (née Codex) as polished as it should be. But, like it or not, cross-platform code is the least-bad way to coordinate a massive team on a rapidly changing product.
Log in
