Click any tag below to further narrow down your results
Links
Perplexity's new Context API lets AI agents pull up to 10 web pages at once and get back clean Markdown, HTML, links, and query-matched passages instead of raw HTML full of ads and navigation. Developers can control how fresh the content must be, from cached copies to live fetches.
- Returns clean Markdown with boilerplate like cookie banners, navigation, and ads stripped out, and can return only passages relevant to a query, so the model processes less text.
- Freshness is adjustable: by default it uses a cached copy from the last two days, but max_age_seconds set to 0 forces a live read, and cache_only prevents live requests entirely.
- In Perplexity's own evaluation, 92.3% of URLs returned usable content, 87.9% of key facts were recovered, and content precision was 80.3%.
A comparison of NudeNet, an open-source nudity detector, against a cloud NSFW moderation API covering 10 categories. The author tests both on the same three images to show where each one succeeds and fails.
- NudeNet only detects nudity, while the API also flags violence, drugs, alcohol, gambling, hate symbols, and other categories that matter for brand safety.
- In the author's tests, NudeNet misclassified the male subjects as female on two of three images and missed the smoking and alcohol content entirely.
- NudeNet is AGPL-3.0 licensed, which the author says creates legal questions for SaaS distribution, and its model hasn't been updated since 2023.
Fish Audio is offering a limited-time discount on their Drama 3 API with free trial periods for new enterprise customers. The page directs users to contact their sales team to discuss pricing plans and features.
- Drama 3 API is discounted 80% for new enterprise customers
- New customers get 1 month free, or 3 months free if switching from a competitor
- Promotion expires October 31st
- Sales contact available to match customers with appropriate plans
This is documentation for Etherscan's API endpoint that converts ENS names (like etherscan.eth) into their corresponding Ethereum addresses. It shows how to call the endpoint across multiple programming languages and explains the rate limits and caching behavior.
- The endpoint resolves ENS names and onchain subdomains to Ethereum addresses via a simple GET request to the Etherscan API
- Free tier is throttled to 1 call per second, with results cached for up to 5 minutes before reflecting onchain changes
- Names requiring offchain resolution (EIP-3668 CCIP Read, ENSIP-10 Wildcard Resolution) like jesse.base.eth are not supported
Google launched two new speech models for developers: Gemini 3.8 Live handles real-time voice conversations with reasoning and background tool execution, while Gemini 3.5 Transcribe converts speech to text across 85+ languages with a 4.0% error rate.
- Gemini 3.8 Live can execute API calls in the background while streaming audio responses, handle visual context, and support 97+ languages with accent consistency
- Gemini 3.5 Transcribe achieves 4.0% word error rate (streaming) and 2.6% (non-streaming), with automatic code-switching and custom vocabulary biasing for domain-specific terms
- Extended Thinking variant adds multi-step reasoning capabilities, ranking #1 on Artificial Analysis' Speech-to-Speech leaderboard
- Google's full audio suite includes speech translation (70+ languages), text-to-speech, and music generation all available in the Gemini API
Firecrawl is an API service that extracts clean, usable data from the live web for AI agents—handling everything from searching and scraping to parsing PDFs and navigating dynamic sites. It consolidates what teams typically do with multiple tools (Puppeteer, Playwright, SerpAPI) into a single interface with compliance built in and sub-3-second response times. The platform offers hosted APIs, open-source SDKs, CLI tools, and integrations with Claude, Cursor, and other AI coding environments.
- Firecrawl claims sub-3-second scraping on real-world sites and consolidates six functions (search, scrape, parse, crawl, map, interact) that teams previously stitched together from Puppeteer, Playwright, Bright Data, Zyte, and SerpAPI
- It outputs standardized Markdown (stripped of headers/footers/ads) or custom JSON schemas, aimed at making data immediately usable in AI agent loops
- Built-in compliance (ZDR, DPA, US data residency, SOC 2 Type 2) targets enterprise teams that can't store scraped payloads on their own infrastructure
- Ships as open-source API, hosted service, MCP integration for Claude/Cursor, CLI, and prebuilt agent skills for tasks like research, SEO audits, and lead generation
Xberg is a single engine for detecting, reading, OCR’ing, and extracting text, tables, metadata, and structured data from over 100 document formats and 115 file extensions. It offers transcription, embeddings, layout reconstruction, schema-driven JSON extraction, and code intelligence via language bindings in Rust, Python, Go, Java, and more. You can run it as a library, CLI, REST API, or MCP server with configurable Cargo features.
- One Rust-core engine handles 101 document formats (115 extensions) plus 371 programming languages for code intelligence
- Ships as 15 language bindings (Python, Go, Java, Ruby, PHP, Elixir, C#, TypeScript, etc.) plus CLI, REST API, and MCP server
- Combines OCR (Tesseract/PaddleOCR/VLM), layout reconstruction (PP-DocLayout-V3, RT-DETR), and table extraction (TATR, SLANet) with schema-driven JSON output via local or hosted LLMs
- Runs GPU-free with multi-GB streaming support and safeguards against zip bombs and excessive nesting/compression
Amazon S3 now lets you attach multiple named annotations—structured JSON or plain text—directly to objects and manage them independently via the GetObjectAnnotation and ListObjectAnnotations APIs. This feature scales to petabytes, works across storage classes, and avoids separate metadata systems.
- S3 now supports multiple independently-managed named annotations (JSON or text) per object via new GetObjectAnnotation and ListObjectAnnotations APIs.
- Annotations are billed at standard S3 rates regardless of the parent object's storage class, so archiving to Glacier doesn't cut annotation costs.
- Designed to eliminate the need for a separate metadata database by keeping context like media specs, AI summaries, or compliance data attached directly to the object.
This article details which Anthropic commercial products and API features qualify under a HIPAA Business Associate Agreement. It breaks down covered and non-covered services, notes beta and third-party integration exclusions, and highlights ZDR requirements for handling PHI in Claude Code.
- Core Claude for Work features (chat history, Artifacts, voice, web search, research, file creation/code execution without external network access) are BAA-covered, but third-party integrations like MCPs/Connectors, Enterprise Search, and Claude in Chrome are not once data leaves Anthropic.
- On the API side, Messages API and related tools (prompt caching, structured outputs, memory, web search, Bash/text-editor) plus Token Counting, Models, Org Management, and Compliance APIs are covered, while Batch API, Files API, Skills API, Code Execution, Computer Use, and Web Fetch are excluded.
- For Claude Code, only the CLI with Zero-Data-Retention enabled qualifies for BAA coverage—the web, desktop, review, and security betas don't support ZDR and fall outside it.
- Beta features like Cowork and Claude for Office are entirely excluded from BAA coverage, requiring separate data-handling safeguards for any PHI use.
ChatGPT Images 2.0 uses a new model that overcomes diffusion-driven spelling errors and renders small text, icons, and UI elements cleanly at up to 2K resolution. It adds web search, multi-image prompts, and support for non-Latin scripts, with knowledge capped at December 2025. All ChatGPT and Codex users get access Tuesday, with paid tiers unlocking higher-quality outputs and an API.
- ChatGPT's new Images 2.0 model renders text, icons, and UI elements accurately at up to 2K resolution, fixing the garbled-text problem that plagued earlier diffusion-based image generators
- It adds "thinking" features like web search, multi-image generation per prompt, and self-verification of outputs, plus cleaner rendering of non-Latin scripts (Japanese, Korean, Hindi, Bengali)
- Training data is capped at December 2025, so it may fumble very recent events
- Rolling out Tuesday to all ChatGPT and Codex users, with paid tiers getting higher-quality output and a new gpt-image-2 API priced by resolution and fidelity
This page offers a quarterly AI Fluency newsletter with research, frameworks, and resources on collaborating with AI. It also provides API guides and best practices for building Claude-powered applications, scaling deployments in organizations, and boosting individual productivity.
- Anthropic offers a quarterly "AI Fluency" newsletter with case studies, collaboration patterns, and step-by-step frameworks for integrating AI into workflows.
- The academy provides technical API resources for developers, including code samples, authentication strategies, rate-limit guidance, and troubleshooting tips.
- Enterprise deployment guides cover security models, governance checkpoints, and scaling strategies for rolling Claude out across departments.
- Individual productivity resources include specific templates and prompt structures (inbox triage, custom research assistants, creative writing) paired with performance metrics.
@dabit3 on X
The x402 Starter Kit is an open source project from dabit3 for spinning up x402 APIs quickly, with three payment facilitator options (Coinbase, local, or custom). It's built so developers can generate a working API from a single prompt and deploy it in Docker on EigenCompute.
- Configures x402 APIs in minutes, with a client-side testing service included
- Offers three facilitator choices: Coinbase, local, or a custom setup
- Runs in Docker and deploys to EigenCompute, and the repo accepts pull requests