Painkillers for every ache? CDSCO warns of kidney risks, antibiotic misuse

After Trump-Xi handshake, Bessent extends truce

OSLabs engineers release open-source CLI to find cheapest Claude tier for your workload

Three developers at OSLabs have built PennyWyze, a free open-source command-line tool that helps teams identify the most cost-effective Claude AI tier for their specific use case. Users supply their production prompt and a labeled dataset of real inputs with known correct answers, and the tool runs each example against Claude Opus, Sonnet, and Haiku via the Anthropic API. PennyWyze measures actual accuracy and calculates real monthly cost projections based on live token counts, then recommends the cheapest tier that meets the user's defined pass-rate threshold. In a sample audit, the tool identified Claude Haiku as equally accurate to Opus at 49 out of 50 questions, while costing roughly $180 less per month. Currently, the tool supports only exact-match tasks such as classification and routing, with an LLM-as-judge mode for open-ended generation planned for a future release.

OpenAI agent hacked Australian government website, PM says

Article URL: https://www.bbc.com/news/live/cvgl73pxgndwt Comments URL: https://news.ycombinator.com/item?id=49825580 Points: 11 # Comments: 1

Developer shares key lessons from building a free random wheel web tool

A developer recently built a free browser-based random wheel tool called The Name Wheel and documented the engineering decisions involved. The project highlighted that interactive web tools require careful attention to state management, randomness, accessibility, and responsive design beyond just the visual interface. A key lesson was keeping animation logic separate from result calculation to make the app easier to debug and maintain. The developer also stressed the importance of handling edge cases, such as displaying a clear message when no options have been entered, to avoid confusing user experiences. The broader takeaway is that simple web tools become genuinely useful when they minimize friction around a common task.

MikroTik Patches Three Critical RouterOS Flaws Including SSH Auth Bypass

MikroTik released a security update in September 2026 addressing three critical RouterOS vulnerabilities, flagged by India's CERT-In as advisory CIVN-2026-0460. The most severe flaw allows unauthenticated attackers to bypass SSH login entirely by sending a forged RSA key, potentially granting full administrative control. A second SSH vulnerability enables privilege escalation by manipulating argument delimiters in the login path, allowing attackers to alter router policy and pivot to internal networks. A third flaw in the bandwidth-test service exposes uninitialized kernel memory to unauthenticated network requests and can crash the device. Affected users are urged to upgrade to the patched RouterOS versions and, in the interim, restrict SSH access to trusted sources and disable the bandwidth-test service where not needed.

Oil prices today: Brent crude edges lower as Iran keeps door open to diplomacy

Developer finds sandbox misclassified shell crashes as command failures on Windows

A developer running an AI agent on Windows Server 2022 discovered that every executed command was silently failing due to a broken shell environment, not faulty commands. The root cause was a recent update that set bash as the default process-boundary shell across all platforms, despite bash not being a native Windows executable. Further investigation revealed that six bundled tools — including bash.exe — all depended on the msys2 runtime DLL, which was only present in one directory and causing STATUS_DLL_INIT_FAILED (exit code 0xC0000142) at the loader level. Because the runner's failure-detection logic did not recognise this exit code as an environment-level fault, every crash was logged as a normal command failure, masking the broken environment entirely. The developer concluded that runners should treat 'child process never initialised' as a runner failure and surface the exit code prominently in all error messages to prevent wasted retry attempts.

OSLabs Releases Open-Source CLI PennyWyze to Audit Claude API Costs

Three engineers at OSLabs have released PennyWyze, a free open-source command-line tool that helps developers find the cheapest Claude model tier that still meets their accuracy requirements. Users provide their production prompt and a labeled dataset of real examples, and the tool runs these against Claude's Opus, Sonnet, and Haiku tiers using the live Anthropic API. PennyWyze grades each model's responses against expected answers and calculates actual monthly cost projections based on real token counts. In one example audit, the tool identified that switching from Opus to Haiku could save roughly $180 per month with no loss in accuracy. Currently, PennyWyze supports exact-match grading, making it best suited for classification, extraction, and routing tasks rather than open-ended generation.

India Women Dominate Germany; Open Team's Gold Hopes Fade at Chess Olympiad

India's open chess team defeated England 2.5-1.5 at the Chess Olympiad, keeping their medal hopes alive. However, Uzbekistan's unbeaten run has made it significantly harder for India to contend for the gold in the open category. In contrast, the Indian women's team delivered a commanding 3.5-0.5 victory over Germany, boosting their title prospects. Savitha Shri was a standout performer, registering her sixth consecutive win in the tournament. The women's team remains a strong contender for the top prize as the competition progresses.

Employer invests ₹25,000 each in KVP scheme for driver and maid's retirement

A man named Naresh took financial initiative after realising his domestic staff — a driver and a maid — had no retirement benefits. He invested ₹25,000 each in Kisan Vikas Patra, a government savings scheme, totalling ₹50,000. Under current terms, the investment is expected to double in approximately 9 years and 7 months. Naresh hopes his action will encourage greater awareness of long-term financial planning for household workers. He is also considering making additional contributions in the future.

Free API tracks OpenAI Codex global usage-limit resets with 24/48h forecasts

A developer has launched codex-reset.com, a free tool that monitors and records OpenAI's informal global Codex usage-limit resets, which occur occasionally after incidents or milestones. The service provides a public JSON API requiring no key, offering probability forecasts for a reset occurring within the next 24 or 48 hours alongside a dated timeline of past resets with source links. It also tracks live Codex service status across multiple surfaces, helping users distinguish outages from quota exhaustion. The data is additionally available as a read-only MCP server that can be connected directly to Codex or Claude Code without installation or authentication. The project is free to use, with the only condition being visible attribution when the data is displayed to others.

US and China Announce Trade Truce as Xi Jinping Visits Washington

The United States and China have declared a trade truce, marking a significant diplomatic development between the two rival powers. Chinese President Xi Jinping has made a rare visit to the United States, signaling a potential easing of tensions. The announcement came from the Trump administration amid ongoing friction between Washington and Beijing. Beyond trade, the two nations remain at odds over issues including artificial intelligence, Iran, and Taiwan.

MCP vs CLI: The Right Choice Depends on Who Controls the Next Step

When building tools that perform actions like publishing a website, developers face a choice between a Command Line Interface (CLI) and a Model Context Protocol (MCP) server. The key deciding factor is not whether the user is human or an AI agent, but rather who determines the next step in the workflow and where the data resides. CLIs are better suited for fixed, repeatable sequences such as automated deployment jobs or local build commands, while MCP tools shine when an AI assistant needs to discover and invoke operations dynamically within a conversation. Transport context also matters: a local MCP server can read a directory path directly, whereas a remote MCP server over HTTP interprets the same path on the server side, not the user's machine. Both interfaces can share a single underlying operation, with the CLI managing flags and exit codes while the MCP adapter handles tool definitions and structured results.

How to Add AI Agent Billing Without Disrupting Its Workflow Loop

When a subscription gateway is placed between an AI agent and its model provider, it can mistakenly interrupt multi-step tasks by treating each model request as a separate billable turn. The core problem is that billing layers can inadvertently take over orchestration decisions that should remain with the agent's local host. A properly designed billing gateway should only handle authentication, allowance checks, request forwarding, and usage accounting — not control the flow of the agent's tool loop or conversation context. Developers are advised to assign distinct identifiers to user turns, model operations, and business invocations to enable accurate metering and error recovery without disrupting execution. Keeping orchestration deliberately separated from billing ensures that paying for model access does not silently grant a second system control over the user's task.

Alex Trebek’s longtime LA home was demolished and replaced with a mansion

Walrus Sessions 8 Hackathon Challenges Developers to Build Memory-Persistent Chatbots

Walrus Sessions 8 is a live hackathon running from September 18 to October 9, 2026, focused on building chatbots that retain context across conversations using the Walrus Memory SDK on mainnet. Participants must create or upgrade a chatbot that stores and recalls user context, deploy it in a real environment, and document the integration with evidence of it working. The competition is open to any use case, including customer support, tutoring, and sales. A total of $2,500 in WAL prizes is on offer, with separate award tracks for the best chatbot, best article, non-Claude/GPT models, and bug bounties requiring no chatbot submission. Full rules and submission details are available via the official Walrus form, with the project repository hosted on GitHub under MystenLabs.

Naked Eyes Co-Founder Peter Byrne Dies at 74 in Los Angeles

Peter Byrne, co-founder of the British new wave and synth-pop duo Naked Eyes, passed away on September 14 at his Los Angeles home after a brief illness. He was 74 years old. Byrne rose to prominence in the early 1980s and was a notable figure in the synth-pop and new wave music scenes. Throughout his career, he worked alongside several celebrated artists, including Stevie Wonder. He is survived by his siblings, three children, and his ex-wife Elena.

India to host first Cycling's World Championships

Tom Brady Opens Up About Humble Roots and His Children's Privileged Upbringing

NFL legend Tom Brady has spoken candidly about his childhood, reflecting on the hardships his parents endured to support his path to success. Brady acknowledged the significant sacrifices his family made during his formative years. He also drew a contrast between his own upbringing and the privileged lifestyle his children enjoy today. The remarks highlight Brady's awareness of the generational difference in circumstances between himself and his kids.