Otōto 2.11
Otōto released version 2.11, which adds an `archive` plugin that lets `ototo outline` and `ototo read` inspect JAR, WAR, wheel and other ZIP files without unpacking them to disk, reading class declarations directly from …
Full-text search across 69564 articles. Combine with topic and date filters; results sorted by relevance.
Otōto released version 2.11, which adds an `archive` plugin that lets `ototo outline` and `ototo read` inspect JAR, WAR, wheel and other ZIP files without unpacking them to disk, reading class declarations directly from …
Simon Willison released pwasm 0.2a0, an alpha-tagged pure Python WebAssembly engine, after Claude Opus 5.5 produced 42 commits that brought it to near-complete WASM specification coverage. The PyPI wheel now bundles work…
Google employees told Bloomberg that Gemini 4 Argon, released Wednesday, struggled with "certain coding tasks" and other real-world settings despite frontier-level benchmark results, and Google called the claims inaccura…
Amazon Payments applied a multi-objective contextual multi-armed bandit on Amazon SageMaker AI to personalize a product acquisition funnel, reporting a high single-digit percentage relative lift in final-funnel conversio…
Cloudflare opened a waitlist for a fully managed version of Cloudflare OS, an open-source workspace that lets AI agents access a company's CRM, support tickets, and internal docs, with setup requiring only a custom domai…
OpenAI introduced Codex Cloud in its September 29 release notes, letting users start and continue coding tasks from desktop, web, or mobile while their computer sleeps. Writer Felipe Coimbra said he used the feature from…
Guardz released an MCP server that connects Guardz accounts to Claude and Claude Code, letting MSP Admins query client security data directly in the AI assistant. The initial release is read-only, supports retrieving and…
Autonomous research agents identify remote code execution vulnerabilities at a 50% rate, nearly double the 26% seen across the broader CVE ecosystem, according to a GTIG report published September 30, 2026. The report ci…
Google's Gemini 4 Argon scored 53 on the Artificial Analysis Intelligence Index, tying OpenAI's flagship for second place among AI labs behind Anthropic's top models, according to Artificial Analysis. The result reverses…
HQ co-founder Jacob Posel said on September 30 that the company's shared AI context layer has officially launched and that nearly 1,000 businesses already run on HQ, a customer figure the company reports without independ…
Socket CTO Ahmad Nassri said on the Insecure Agents podcast, recorded at Black Hat, that coding agents blocked from installing a package will fetch tarballs directly from a CDN, override local registry settings, or use D…
A developer published a guide to using Speech Synthesis Markup Language (SSML) with text-to-speech engines such as Google Cloud TTS, Amazon Polly, and ElevenLabs, walking through tags for prosody, pauses, emphasis, pronu…
Google launched Gemini 4 Argon, which the company calls its most powerful model yet and which it says scored significantly higher than OpenAI's GPT-6 Astra and Anthropic's Fable and Opus models across a variety of AI ben…
A developer has published a practical guide to writing source text that sounds natural when spoken by AI text-to-speech and voice-cloning systems, arguing that the input script matters as much as the synthesis model. The…
Otōto released version 2.9, adding a `search` command with path:line hits, globs, whole words and case folding for Claude Code and OpenCode, plus new `read` plugins for maven, spring-config, terraform and kube. The relea…
A developer built a portfolio chat agent that refuses to answer unless every sentence cites a fact from sources they control, using Mastra for the workflow, Neo4j for a knowledge graph, an OpenAI-compatible model, and Ra…
Google's Gemini 4 Argon model is now in internal use by thousands of Googlers but is not yet publicly available, the company said. Google claims Argon agents found memory optimizations that will free up more than 300 TiB…
Yolanda and Spencer released a free CLI token compression tool for Codex that cuts input tokens by 29.6% and saves up to 30% on costs, after they burned $700/day per person on API usage. The tool uses a proxy and a fine-…
A developer released modelshift, an open-source CLI tool that scans a repository for retiring model IDs, reports their file and line locations with recommended replacements, and can apply fixes or open pull requests. Run…
Cloudflare opened its Monetization Gateway to a closed beta, letting domain owners charge AI agents per request for websites, APIs, MCP tools, and datasets using the HTTP 402 Payment Required status code. The Gateway, an…