Loading…
Latest reads
Every post, summarised
Grounded summaries of engineering blogs, newest first. Each links to the original.
- 4,671 posts
- 20 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Latest posts
How to Connect Your Twilio Agent to External APIs with PHP
The tutorial shows how to connect a Twilio voice agent to external REST APIs so an LLM-driven conversation can retrieve live information or support actions such as checking inventory or booking appointments. It builds the example in PHP 8.5 or later with OpenSwoole, Twilio Conversation Relay, OpenAI, and a WebSocket server, using Cat Facts as an unauthenticated API. The application exposes a POST /voice webhook that returns TwiML and connects Conversation Relay to a wss /ws endpoint, while session handling passes caller prompts into the OpenAI service. Tool calling routes the request to the Cat Facts endpoint, parses the JSON fact field, and returns either the fact, “No fact returned.”, or an error when the API response is unsuccessful or unavailable. Testing requires running php server.php, exposing port 8080 with ngrok, and configuring the Twilio number’s incoming webhook to /voice; the conclusion says external HTTP endpoints give agents real-time data.
How to Orchestrate Multi-Call Conversations with an LLM and Twilio Conversation Memory with PHP
This tutorial shows how to build a PHP voice agent that retains caller context, preferences, and action history across separate inbound calls. It uses Twilio Conversation Memory with a Memory Store, an Open Swoole service, Twilio ConversationRelay, and an OpenAI integration using gpt-4o-mini; the example models an auto-repair shop assistant. The OpenAI service appends supplied prior customer context to its system prompt, while streamed responses are sent through a WebSocket and environment variables provide API credentials and the Memory Store ID. After running the service on port 9501, exposing it with ngrok, and configuring the phone-number webhook, the tutorial tests two calls from the same number and says the second call should remember details from the first.
Adding Google Login to a React App with Auth0
The tutorial shows how to add Google login to a Vite-based React single-page app without implementing OAuth directly, using Auth0’s React SDK and Google social connection. It covers installing @auth0/auth0-react, creating an Auth0 Single Page Web Application, checking RS256 and OIDC Conformant settings, registering callback, logout, and web-origin URLs, and supplying the domain and client ID through Vite environment variables. The React code wraps the app in Auth0Provider, uses useAuth0 for loading and authentication state, and calls loginWithRedirect with connection: 'google-oauth2' to bypass provider selection. For production, it explains replacing Auth0’s shared development keys with Google Cloud credentials whose origin and redirect URI target the Auth0 domain, then storing them in the Auth0 social connection. It also points to route protection with withAuthenticationRequired, API access tokens from getAccessTokenSilently, and exact redirect-URI matching as important follow-on considerations.
DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation
DiscoSign addresses a limitation in sign language processing: systems have traditionally translated at the sentence level, overlooking discourse phenomena important to sign language comprehension. It presents a modular Large Language Model (LLM)-based framework for text-to-sign language gloss translation that handles spatial coreference resolution, Question-Answer Clauses (QACs), and concept-gloss consistency, preserving entity locations and stable English-to-ASL sign mappings across discourse. Because traditional translation metrics do not measure discourse-level quality, the authors introduce metrics for each coherence dimension targeted by the framework. Experiments on sentence-level and discourse-level datasets report improved spatial consistency and entity tracking over sentence-only translation, while maintaining competitive single-sentence gloss quality; the work describes this as the first systematic framework with a corresponding evaluation methodology.
Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering
Evaluating video captions is difficult because reference-matching metrics can penalize valid descriptions that use different wording or focus on different visual content, while offering little fine-grained diagnosis. The paper reframes quality around information fidelity: captions should cover salient visual information and remain factually accurate. It introduces CapQuiz, a reference-free benchmark that tests caption utility through human-verified, fine-grained multiple-choice questions derived from videos, organized into 10 Descriptive and Inferential question types across 24 domains. It also proposes CapF1, which combines CapP for factuality with CapR for coverage; extensive experiments report significantly stronger correlation with human judgments than existing metrics and interpretable insight into model performance.
SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign
SimpleDesign addresses protein design as a joint modeling problem involving amino acid sequences and three-dimensional structures, whose interplay determines protein function. Unlike approaches that first train autoencoders and then model their latent representations, it uses a single-stage, end-to-end objective directly in data space. The objective combines discrete cross-entropy for sequences with a regression objective for structures, while Transformer-based multimodal backbones provide modality-specific processing and global self-attention across both modalities. Trained on more than 2M sequence-structure pairs, SimpleDesign achieves competitive performance on co-design and unconditional sequence and structure generation benchmarks. The work argues, based on these results, that multi-stage training is not necessary for performant co-design models.
Autonomous LLM post-training with Tunix on TPUs
autofinetune applies autonomous research loops to LLM post-training, covering supervised fine-tuning (SFT) and reinforcement learning with GRPO through Tunix, Gemma, Cloud TPUs, Antigravity CLI, and Gemini Flash 3.7. A human defines the arena in program.md and supplies a self-contained run.py, while an agent edits hyperparameters, launches jobs, evaluates a target metric, keeps winning Git commits, reverts regressions, and logs results in results.tsv. On FunctionGemma 270M with google/mobile-actions, 20 Cloud TPU v5e-1 experiments tested LoRA settings, optimization choices, schedules, batch size, and seeds without changing the dataset, epochs, or architecture. A second study used Gemma 3 1B, GSM8K, and Cloud TPU v6e-1 for 40 GRPO experiments over two to three days, improving the combined numerical-and-format reward by about 10%.
A Developer's Guide to API Access Policies in Auth0
Auth0 API Access Policies for Applications control whether an application can obtain an access token for a registered API, separately for user-delegated and client access. The FinFlow example separates a browser application that should reach both APIs from a machine-to-machine Risk Engine restricted to the Payments API. Policies provide three choices—allow_all, require_client_grant, and deny_all—while client grants specify an application's audience and permitted scopes, with the audience determining which API policy is evaluated. The guide shows Dashboard and Management API configuration, including subject_type_authorization settings and grants for user and client access. It also explains that third-party applications still require grants under allow_all, while default third-party grants establish a baseline and per-application grants take precedence for exceptions.
[Webinar] Elevating customer engagement with WhatsApp
The webinar examines how businesses can use WhatsApp for secure account verification, one-time passcodes, operational alerts, and customer conversations. It presents notification overload, third-party portals, single-use apps, and unbranded sender numbers as reasons critical messages may be ignored, affecting deliveries and transactions. Speakers from Twilio, WhatsApp, and Orbio AI describe a verified, two-way model built around WhatsApp Utility messaging, interactive buttons, logic flows, end-to-end encryption, and visual drag-and-drop automation. Orbio AI's examples include screening candidates, scheduling interviews, reminders, onboarding, and engagement conversations for enterprise clients while the webinar claims improved deliverability, faster user action, reduced manual work, protection against SMS toll fraud, and scalable deployment. It also positions app-based delivery over WiFi and cellular networks as a more reliable alternative.
Building Pinterest’s VLM Serving Stack on NVIDIA Dynamo
Pinterest describes building a VLM serving stack on NVIDIA Blackwell B200 GPUs and NVIDIA Dynamo for multimodal products including Pinterest Assistant, hybrid search, multimodal reranking, content understanding, signal generation, and content safety. Unlike text-only workloads, requests may contain thousands of images, costly and variable prefill, long multi-turn histories, and large KV caches, making preprocessing, routing, memory, and latency central serving concerns. The implementation combines Dynamo's distributed orchestration, multimodal frontend and vLLM support, KV-aware routing, disaggregated encoder/prefill/decode serving, and LMCache-based KV offloading with vLLM, an OpenAI Chat Completions interface, model-aware routing, EKS, and custom deployment components. Production-oriented AIPerf DAG benchmarks model QPS patterns, multi-turn conversations, many-image requests, and agentic DAGs; the team concludes that payload design, cache-aware routing, offload tiers, and a shared platform are essential to meeting product targets and accelerating new launches.
Halving the Time: How Uber Eats Rebuilt Its Search Pipeline
Uber Eats rebuilt its search pipeline after accumulated architectural decisions made latency increasingly costly across retrieval, hydration, ranking, ads, and presentation. The team changed its primary metric from backend API response time to Above-the-Fold completion, then introduced paginated responses with server-side caching and concurrent template rendering; these changes improved ATF by over 200 milliseconds. Other work removed low-yield retrieval strategies, grouped items by product identity to reduce lookups by over 100 times, split ranking and presentation hydration, eliminated false DAG dependencies, added request hedging, and redesigned ad data as column-oriented in memory. The combined effort cut search latency in half, including approximately 120 milliseconds from retrieval, 100-plus from hydration changes, and 130 from ads, while planned product-based search, zero-pass ranking, and streaming target further gains.
Grocery Delivery across the US: Fees, Pricing and Membership Guide
Uber Eats grocery orders combine item prices with Delivery, Service, and possible add-on fees, while taxes are estimated at checkout and finalized on the receipt. Delivery Fees typically range from $0 with Uber One on eligible orders to $7.99 for standard orders, and Service Fees typically range from $2.85 to $7.75 depending partly on basket size. Customers can order without a membership; participating stores may offer in-store pricing, while other stores may mark up item prices. Uber One costs $9.99 monthly or $96 annually, provides $0 Delivery Fees on eligible grocery orders, and is described as breaking even after approximately two grocery orders per month. It also extends benefits to restaurant delivery and other Uber services, while listed savings options include promotions, No Rush Delivery, larger consolidated orders, EBT payments, and discounted gift cards.
McDonald's x Uber Eats Courier Appreciation Week Rules
The McDonald’s Courier Appreciation Week Sweepstakes is sponsored and administered by Uber and is limited to eligible U.S. Uber Eats delivery drivers. Participants must be at least 18, reside in Uber serviceable areas, hold a delivery account as of September 14, 2026, meet delivery-driver requirements, and have an account in good standing. During the September 14–18 Sweepstakes Period, invited drivers can receive one entry by completing the McDonald’s Courier Feedback Survey, with 100 potential winners selected randomly on or about September 25. Each winner receives $50 in Uber Cash, for a total approximate prize value of $5,000, subject to usage restrictions and possible expiration; no purchase is necessary, and odds depend on the number of eligible entries.
Higher education advisory board and AI Fluency courses
Anthropic announces two initiatives for higher education: an advisory board to guide Claude’s development for teaching, learning, and research, and three AI Fluency courses co-created with educators. The board, chaired by Rick Levin, includes academic leaders whose expertise spans university leadership, educational technology, learning science, and postsecondary policy, with a stated aim of strengthening learning and critical thinking while upholding academic integrity and student privacy. The courses address educators, students, and institutions: they cover classroom materials and assessments, responsible AI collaboration, critical thinking, personal commitments, instruction, assessment, and curriculum planning. Co-developed with Rick Dakan and Joseph Feller, all three are available under a Creative Commons license so institutions can adapt them. The announcement positions the board as strategic guidance and the courses as practical support for universities navigating AI integration.
National Security and Public Sector Advisory Council
Anthropic announced the formation of its National Security and Public Sector Advisory Council, a bipartisan group of former officials and public policy practitioners supporting work with the U.S. government and closely allied democracies. The council includes former senators and leaders from Defense, intelligence, Energy, Justice, and congressional national security offices, and will help identify applications in cybersecurity, intelligence analysis, and scientific research. It will also deepen public-private partnerships and support standards for responsible national security applications. Anthropic describes related efforts including Claude Gov models, a $200 million Department of Defense partnership, Claude access for 10,000 Lawrence Livermore National Laboratory scientists, nuclear safeguards work, $1 access for all three government branches, and voluntary testing of biological, cyber, and AI R&D capabilities.
Education Report: How educators use Claude
An analysis of educator AI adoption in higher education examines how faculty use Claude across teaching, research, and administration. The researchers analyzed approximately 74,000 anonymized conversations from Claude.ai Free and Pro accounts associated with higher education email addresses during May and June, automatically filtering educator-specific tasks and matching them to O*NET categories; they also drew on survey and qualitative research with 22 Northeastern faculty. Curriculum development was the leading use, appearing in 57% of analyzed conversations, followed by academic research at 13% and student-performance assessment at 7%. Faculty also used Claude Artifacts to build interactive games, quizzes, simulations, data visualizations, scheduling tools, and budget planners, shifting from conversational assistance toward deployable educational resources. The analysis found more augmentation for lesson design, advising, and grant writing, while routine administrative work was more automation-heavy; grading was automated in 48.9% of relevant cases despite faculty rating it AI’s least effective application.
Anthropic raises $13B Series F at $183B valuation
Anthropic has completed a $13 billion Series F led by ICONIQ and co-led by Fidelity Management & Research Company and Lightspeed Venture Partners, valuing the company at $183 billion post-money. The financing follows rapid expansion since Claude launched in March 2023: run-rate revenue rose from approximately $1 billion at the beginning of 2025 to more than $5 billion by August, while Anthropic reported over 300,000 business customers and nearly sevenfold growth in large accounts over the past year. Claude Code, fully launched in May 2025, had already surpassed $500 million in run-rate revenue, with usage increasing more than 10x in three months. Anthropic says it will use the investment to expand enterprise capacity, deepen safety research, and support international expansion while building reliable, interpretable, and steerable AI systems.
Chris Ciauri named Managing Director of International
Anthropic announces Chris Ciauri as Managing Director of International amid expanded global operations, new offices, and increasing enterprise demand for Claude. Ciauri brings more than 25 years of experience scaling enterprise technology businesses globally, including roles as CEO of Unily, president of EMEA at Google Cloud, and EVP and GM of EMEA at Salesforce, where he helped grow revenue from under $200 million to over $3 billion. He joins Paul Smith’s international leadership group with Guillaume Princen, Hidetoshi Tojo, and Kate Jensen, while Anthropic adds more than 100 EMEA roles, opens its first Asia office in Tokyo, and plans further European locations. Anthropic says this momentum reflects technical talent, safety, and frontier research, including alignment and interpretability work. The company reports run-rate revenue above $5 billion in August 2025, more than 300,000 business customers, and customer examples spanning productivity, documentation, service quality, fraud reduction, and software development.
Deloitte brings Claude to 470,000 people
Anthropic and Deloitte announced an expanded alliance that will make Claude available to more than 470,000 Deloitte people across its global network and create industry-specific solutions powered by the model. Deloitte will establish a Claude Center of Excellence, with trained specialists developing implementation frameworks, sharing deployment practices, and providing ongoing technical support to move AI pilots into production at scale. The organizations are also creating a certification program for 15,000 professionals, while combining Claude’s safety-first design with Deloitte’s Trustworthy AI framework to build compliance-oriented tools for regulated industries including financial services, healthcare and life sciences, and public services. The announcement describes the deployment as Anthropic’s largest enterprise AI deployment to date, with Claude intended for uses ranging from coding and software development to customer engagement and industry-specific advisory.
Rahul Patil joins as Chief Technology Officer
Anthropic announced that Rahul Patil has joined as its Chief Technology Officer, overseeing engineering across product, compute, infrastructure, inference, data science, and security as Claude scales to meet growing enterprise demand worldwide. Patil brings more than 20 years of experience building and maintaining industry-leading infrastructure, most recently as CTO of Stripe, where he guided technology supporting millions of businesses processing more than trillion dollars annually. Earlier roles at AWS, Microsoft, and Oracle Cloud Infrastructure developed his expertise in reliable, scalable mission-critical systems, while co-founder Sam McCandlish moves from CTO to Chief Architect to focus on large-scale model training, pretraining, research productivity, and RL infrastructure. The announcement frames Patil’s appointment as a commitment to world-class infrastructure and reliability at scale for developers building with Claude.
Top topics
- Architecture834
- Performance816
- LLMs660
- Machine Learning622
- Open Source563
- AI Agents553
- AI470
- Developer Experience448
Weekly digest
The best engineering reads, once a week.