Every post, summarised

Aug 20, 2026

• Uber

  How Uber, OCI™, and Ampere® Co-Optimized OCI AmpereOne® M A4 Compute

  Uber, Oracle Cloud Infrastructure, and Ampere co-optimized the OCI AmpereOne M A4 instance family after migrating large workloads from on-premises data centers to Arm-based cloud infrastructure. Early A1 and A2 deployments exposed dual-socket latency, Go performance degradation associated with smaller TLB and cache sizes, and insufficient single-thread performance for Gurobi services. Uber shared workload characteristics and targets that informed AmpereOne M silicon and an OCI FlexSKU, while the teams evaluated frequencies, core counts, deployment models, memory ratios, and storage. For latency-sensitive stateless services, the resulting guidance favors higher-frequency CPUs, about 8 GB per vCore, and virtual machines; throughput-oriented storage systems use parallelism, flexible memory-to-core ratios, and local NVMe or remote block storage according to locality. The collaboration is presented as improving price-performance and supporting energy-efficient, cost-optimized multi-architecture computing at scale.

• Cloudflare

  From all-or-nothing to task-based OAuth consent

  Cloudflare introduced OAuth scope customization to replace all-or-nothing consent flows for third-party applications. Previously, users had to approve every requested scope or deny access completely, compelling developers of tools like MCP servers to construct custom pre-consent selection interfaces. With the new feature, developers can designate specific permissions as optional alongside required scopes when configuring an OAuth client. During authorization, users can deselect these optional scopes, while unrequested client scopes remain hidden to maintain task-specific consent screens. Because resulting access tokens contain only the granted subset of permissions, client applications must inspect returned scopes after code exchange rather than assuming full authorization.

• Hugging Face

  Up to 3.2x Faster Inference with LFM2.5-DSpark

  Liquid AI released DSpark draft checkpoints for LFM2.5-1.2B-Instruct, LFM2.5-2.6B, and LFM2.5-8B-A1B, adding speculative decoding with a minimal memory increase. DSpark uses a DFlash-style parallel backbone conditioned on target context features, a lightweight sequential Markov-chain head, and a confidence-scheduled verifier that prunes low-confidence suffixes. The draft models are simplified attention-only networks with five layers and a block of nine, trained for 15 epochs on SFT, chat, code, and function-calling data; each contains roughly 300M parameters. Across five datasets, LFM2.5-2.6B averaged 2.67x speedup on an H100 and 2.27x on an M4 Max, while reducing multi-tool function-calling latency by 57% on average. Greedy decoding remains identical to baseline by construction, and integrations are available in llama.cpp and SGLang, with on-device gains for the 8B-A1B model limited by its current MoE Metal implementation.

• Clickhouse

  POSETTE Talk Recap - Postgres Isn't Slow. Your Storage Is

  At POSETTE 2026, Sai Srirampur’s talk examines how storage limits can produce slow ingestion, erratic P95 reads, lagging autovacuum, slower checkpoints, and logical replication lag in large PostgreSQL workloads. The benchmark ran the same 3.3-billion-row, random-UPDATE workload on four local-NVMe clusters and four baseline gp3 EBS clusters, using m6id.4xlarge instances, 64 clients, and 16 worker threads. NVMe reached median 16,030 TPS versus 1,734 TPS on EBS, reduced median latency from 36.9 ms to 4.0 ms, and completed the tested VACUUM and replication-backlog tasks faster. The analysis attributes most of the gap to storage waits rather than CPU work, while the proposed production model combines local NVMe with quorum-based replication, external base backups, and archived WAL for recovery.

• NVIDIA

  How Generative Recommenders Are Redefining RecSys at Scale

  Generative recommenders (GRs) recast recommendation as next-item or next-action sequence prediction conditioned on user histories, replacing traditional embedding-similarity objectives and potentially unifying retrieval and ranking. The post presents HSTU, which uses timestamp-ordered interleaved items and actions, SiLU-based attention weighting, relative attention bias, and gating, alongside Semantic IDs, which derive a smaller vocabulary through hierarchical clustering of item embeddings. For production, recsys-examples combines TorchRec, DynamicEmb, Megatron-Core, recommender-specific KV and decoding components, while nv-embedding-cache provides tiered GPU, CPU, and remote embedding storage. On an H100, the Semantic ID path was reported as 1.85x higher in online throughput and 46% lower median latency than SGLang under the stated long-context, beam-search workload, and DLRM v3 reached 99,997 queries/sec.

• Jetbrains

  PyCharm for AI-assisted Django Workflows

  According to the 2026 Django Developers Survey, ninety percent of respondents incorporate artificial intelligence into their weekly or daily workflows. While agents generate code rapidly, developers remain accountable for understanding, evaluating, and shipping changes within their applications. PyCharm addresses these demands by integrating support for external agents, local models via Ollama and LM Studio, and customizable agent skills across codebases. The IDE maintains version-specific framework assistance, including auto-completion for Django 6.0 template partials, alongside architectural inspection tools and visual diffs. Furthermore, developers can trace application components, inspect API endpoints, execute HTTP requests, and query database migrations directly through built-in tooling.

• Jetbrains

  Ready for Go 1.27 on Day One

  GoLand 2026.2 introduces day-one support for Go 1.27 language features, tooling improvements, and profiling capabilities. The Go 1.27 release adds generic methods, promoted field names in struct composite literals, improved function type inference, and a dedicated profile for detecting goroutine leaks. To assist with code maintenance, GoLand integrates official go fix modernizers directly into editor inspections, the Problems tool window, and optional pre-commit checks. Developers can capture, visualize, and analyze goroutine leak profiles alongside existing CPU, memory, and mutex profiles within the IDE. Additionally, updated Modern Go Code Guidelines provide AI coding agents with Go 1.27 context and API changes aligned with the version specified in go.mod.

• Brandwatch

  5 Social Media News Stories You Need to Read This Week

  This roundup compiles social-media news updates published across August 2026, July 2026, June 2026, and December 2024, covering creator monetization, advertising, platform features, and policy developments. Instagram tested invitation-only seasonal bonuses for Reels and posts in South Korea and the U.S., while Meta enabled ad payments through stablecoin wallets supporting USDC; TikTok’s Dreamina Seedance 2.5 expanded video generation to 30 seconds and accepted up to 50 multimodal references. Other updates include LinkedIn comment ranking and surfacing changes, X’s Live Studio, Threads’ private likes and live-chat tools, and TikTok Pro Events. The roundup also reports a teased MySpace relaunch, new discovery and profile features across platforms, Instagram live location sharing, X parody-account labels, and a potential U.S. TikTok ban.

• Stack Overflow

  From PHP to team lead of agents: rethinking judgment, review, and data with Google's Andi Gutmans (Part 1)

  Software development is experiencing an architectural shift as artificial intelligence agents transition individual contributors into orchestrators and reviewers of automated workflows. Rather than spending effort on manual coding, developers increasingly focus on defining system architecture, guiding agent execution, and managing operational risk through tiered human and agent review loops. The primary bottleneck for agentic systems lies in preparing organizational data so that agents can effectively reason over enterprise knowledge. To address this challenge, Google published an open knowledge format and is adopting agent-driven semantic ontology generation to infer relationships across messy data estates. This evolution transforms ontology building from manual human toil into automated generation, allowing engineers to focus on high-value data curation and strategic system design.

• Okta

  I Found My Coordinates: Code, Community, and Okta

  A career progression through community leadership and software engineering led to a new role at Okta. Starting as a campus ambassador and Google Developer Student Clubs lead in India, the author organized hackathons, workshops, and meetups to foster peer learning. To effectively advocate for developers, an internship as a Developer Advocate at Zuplo prompted hands-on engineering experience as a Software Development Engineer at JPMorgan. After mentoring over 10,000 students and growing a technical community to over 600,000 members, the author joined Okta as a Senior Builder Advocate. In this role, advocacy extends beyond traditional coders to support AI builders, low-code creators, and developers utilizing identity and access management tools.

• AWS

  How AgentFlo built AI sales agents with Amazon Bedrock AgentCore – Part 1

  AgentFlo built autonomous AI sales agents to address cart abandonment, unassisted messaging channels, and severe traffic spikes across eCommerce platforms. The system uses the Strands Agents SDK alongside Amazon Bedrock AgentCore to manage intent, recommend products, and execute transactions. Incoming customer communications pass through AWS Fargate before entering AgentCore runtime, which executes model-driven agents inside isolated microVMs with stateful sessions lasting up to eight hours. Tool execution is brokered separately through AgentCore Gateway to ensure operations like cart modifications scale independently from model reasoning. This deployment model enables merchants to launch specialized conversational agents in minutes without pre-provisioning capacity or maintaining custom container configurations.

• Resend

  How APRF Helps You Understand Your Email Reputation

  Aggregate Performance Reporting (APRF) is a draft standard for email deliverability feedback backed by contributors from Comcast, Google, and Iterable. It gives senders aggregated, intentionally bucketed signals about message classification—such as inbox or unwanted—and user engagement, categorized as positive, negative, or neutral. It also describes daily JSON reports delivered to a DNS-configured address, with provider-specific bucket definitions optionally documented in extra_info. Senders can configure a TXT record derived from the DKIM selector and domain, then use the optional sdi attribute and email header to segment results by business, region, campaign, or other values. The sample shows separate classification and engagement data for marketing and transactional segments, while acknowledging that counts are approximate; APRF is not yet adopted by an IETF working group, Comcast sends reports, and Gmail does not yet.

• Twilio

  [Webinar] Voice AI that connects

  This webinar addresses the gap between impressive voice AI demos and reliable production deployments, focusing on global rollout barriers such as spam-flagged outbound calls, legal delays, latency, and custom integration work. It presents Twilio Voice and AI through the Guinness Price Index case, alongside reported examples from Docplanner and audibene, whose use of the Twilio platform is said to halve costs, double booking efficiency, and improve inbound reachability by 30 percent. A developer demonstration shows how Twilio Skills and an AI coding agent configure an initial setup, while an open-standard Model Context Protocol (MCP) Server and Twilio Agent Connect SDK replace growing custom glue code. It also covers Conversation Relay for real-time audio, Conversation Memory and Conversation Orchestrator for AI-to-human handoffs, and connections to privately hosted models to retain cloud and roadmap control. The session frames compliance, privacy, personalisation, and vendor lock-in as operational concerns in scaling voice AI.

• Twilio

  Video Call Integration on Different Platforms

  Video calling can add direct, personal communication to customer and patient interactions without moving conversations to a third-party app or website. The post outlines an integration path based on choosing a platform, selecting development-specific SDKs, and either building a custom application or deploying and adapting an open-source one. Twilio is presented as a cloud communications platform offering APIs, SDKs, reference apps, and documentation, with SDKs for JavaScript, Android, and iOS; listed build examples also use Svelte, Go, Python, ASP.NET Core, Angular, Node.js, TypeScript, and Express. Open-source options provide features such as screen sharing and network-condition monitoring, while Twilio Video supports branded virtual backgrounds and layouts, but the source does not report implementation results.

• Clickhouse

  Shopify powers observability for global-scale commerce with ClickHouse

  Shopify rebuilt its observability infrastructure after metrics, logs, and traces became fragmented across vendors, with unpredictable costs and limited cross-signal analysis. It created Observe, a unified platform that runs metrics, logs, traces, profiles, and exceptions on self-hosted ClickHouse, treating them as structured, time-ordered, high-dimensional events and serving roughly 50 million events per second normally and 100 million at BFCM peak, or about 110 GB/s. Kafka buffers telemetry for large synchronous durable writes, while materialized views support flexible schemas, autocomplete, typed hot keys, and identifier-based correlation; the latter reportedly makes targeted searches 10x faster. Shopify reports a 16x query improvement out of the box, exceeding 30x at peak performance, with data queryable in under a minute, and says it would likely choose ClickHouse Cloud if starting again because managed operations could reduce the self-hosting burden.

• Auth0

  Enterprise-Managed Authorization for your MCP server: Setting Up and Testing XAA in Auth0

  Connecting AI agents to enterprise APIs and MCP servers creates governance challenges when relying on traditional OAuth consent prompts. Cross App Access shifts authorization decisions to the enterprise identity provider, allowing IT administrators to manage agent permissions centrally. In this architecture, an identity provider like Okta authenticates the user and issues an Identity Assertion JWT Authorization Grant based on administrative policy. The requesting AI agent presents this assertion to Auth0, which validates the signature and exchanges it for a standard access token via a JWT-bearer grant. Protected APIs can then validate the final token normally without requiring code changes or direct user consent interactions.

• Auth0

  Enterprise Readiness Is Not What You Support. It Is What Your Customers Can Own

  Workplace operations platform SafetyCulture previously relied on a multi-team, manual onboarding process for enterprise single sign-on setups across diverse identity providers, which created operational overhead and accounted for approximately 30 percent of engineering support tickets. To resolve these scaling bottlenecks, the engineering team integrated Auth0's Self-Service Enterprise Configuration, implementing a step-by-step wizard for OpenID Connect and custom SAML setups. The resulting workflow allows customer administrators to configure identity settings, test logins before committing, and manually toggle production activation. Moving from proof-of-concept to general availability took two months, achieving a 50 percent unassisted completion rate. Four months post-launch, SafetyCulture recorded a 60 percent reduction in SSO setup-related customer support tickets.

• Apple

  Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions

  Cross-lingual knowledge transfer is critical for training multilingual language models when target-language data is scarce and downstream tasks demand reasoning or world knowledge. Existing transfer approaches often depend on scarce resources such as large parallel corpora, translation systems, auxiliary models, or extra training phases. To address this limitation, the authors introduce LINK, a data-level intervention method that operates directly during pretraining via bilingual vocabularies. LINK swaps randomly selected words in a portion of the high-resource English corpus with word-level translations according to a specified replacement ratio. Across evaluations spanning eight languages and five model sizes, the technique delivered notable performance gains on downstream target-language tasks while achieving up to a 2x speedup in training to reach equivalent performance.

• Apple

  Scaling Laws for Mixture Pretraining Under Data Constraints

  Scaling language models demands large volumes of data, but high-value target sources like low-resource languages and specialized domains remain inherently scarce. Practitioners frequently combine limited target data with abundant generic data, creating a balance between domain underexposure and excessive repetition leading to overfitting. An empirical evaluation across more than 2,000 language-model training runs demonstrates that mixture training tolerates substantially higher data repetition than single-source training, allowing scarce target corpora to be repeated 15 to 20 times. Researchers introduced a repetition-aware mixture scaling law that accounts for both the diminishing returns of repeated target tokens and the regularizing effect of generic data. Optimizing this scaling law offers a principled framework for calculating effective mixture configurations and practical pretraining recommendations under severe data constraints.

• Apple

  Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR

  Code-switching automatic speech recognition faces major performance challenges due to the scarcity of code-switching training data. To mitigate this data limitation, an iterative pseudo-labeling framework leverages a large unlabeled audio corpus to generate semi-supervised speech datasets. The system structure executes across three sequential phases: pseudo-label generation, two-stage bilingual model pre-training with supervised code-switching fine-tuning, and progressive iterative improvements. Successive refinement cycles further enhance the neural model's recognition accuracy when processing complex code-switching scenarios across alternating languages. When evaluated on the SEAME benchmark, this training pipeline achieved Mix Error Rate reductions of 6.35 percent on the devman subset and 8.29 percent on the devsge subset.