Loading…
Browse by type
Explainer reads
Explainer posts on Yomu, summarised newest first.
- 1,328 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.
Explainer posts
How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code
Papers with Code needs a search engine that supports exact titles and arXiv identifiers, semantic requests, navigational queries, typos, and fast responses when model services are cold or unavailable. The system uses hybrid retrieval: PostgreSQL full-text search provides a lexical baseline, pgvector stores dense embeddings, and reciprocal rank fusion combines them. Full-corpus embeddings for more than 110,000 papers run in burstable GPU Jobs from repeatable-read database snapshots, with checksummed JSONL inputs and resumable Parquet outputs stored in Buckets. An Inference Endpoint serves low-latency query embeddings and bounded hourly updates for changed papers, while lexical retrieval remains a fallback. The embedding contract pins the model revision, dimension, prompts, normalization, and source hash; production uses Qwen/Qwen3-Embedding-0.6B with 256-dimensional L2-normalized vectors, and stored vectors also support related-paper retrieval without a request-time model call.
AI Won't Replace Project Managers, But It is Reshaping How Work Gets Done
Technical project managers historically spend 60 to 70 percent of their working time managing routine coordination tasks, including manual spreadsheet updates and obsolete status reporting. Engineering organizations are addressing this overhead by integrating generative artificial intelligence, large language models, and agentic workflows into delivery pipelines. Automated agents ingest telemetry directly from Git commits, pull request comments, and CI/CD logs to assess system state while machine learning models execute Monte Carlo simulations to forecast delivery risks. Although this automation reduces administrative overhead below 30 percent, implementations face practical obstacles like inconsistent ticket definitions across teams and algorithmic over-reliance on uncontextualized historical patterns. Consequently, technical project managers are transitioning into strategic roles that coordinate hybrid human-agent workforces while providing critical judgment and organizational context.
Securing Software at the Speed of AI
Palantir describes how its Product Security Team built an agentic software security strategy around multi-agent review, vulnerability hunting, triage, and runtime validation. The approach treats models as replaceable components within a governed harness that controls tools and data access, preserves evidence, coordinates specialized stages, independently challenges findings, and deduplicates reports using source-to-sink paths. Foundry supplies organizational context and lineage across code, services, findings, decisions, and remediation, while Apollo provides a controlled path for delivering verified fixes across heterogeneous software environments. The strategy positions remediation, rather than vulnerability identification, as the central bottleneck and extends these capabilities through Security Forge, a model-agnostic platform for customer cyber defense.
Quantum-Augmented Applications: Integrating Quantum Subroutines into Classical Software Stacks
Quantum-augmented applications treat Quantum Processing Units (QPUs) as targeted coprocessors for NP-hard subroutines rather than standalone computing replacements. Near-term noisy intermediate-scale quantum systems handle tasks like combinatorial optimization, high-dimensional state sampling, and kernel mapping while classical stacks retain business logic and pipeline control. A hybrid runtime architecture routes parameterized ansatz circuits through middleware to the QPU, returning raw measurements for error mitigation and classical optimization. A Python implementation using Qiskit demonstrates this interaction by running a parameterized variational ansatz inside a classical COBYLA minimization loop. Operating this hybrid model requires navigating physical constraints including coherence limits, circuit transpilation latencies, and network bandwidth bottlenecks across the classical-QPU boundary.
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.
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.
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.
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.
Building Federated Multimodal AI Workflows with NVIDIA FLARE
Federating vision-language models (VLMs) across institutions requires keeping images, text, and prompts local while coordinating training and combining updates from sites with different task and modality mixes. NVIDIA FLARE addresses this workflow through server-scheduled rounds, client-local execution, and an explicit update contract, while supporting large-object externalization, pull-based tensor streaming, and disk-backed aggregation for large payloads. The post presents FedUMM as an adapter-based design in which clients train LoRA adapters over a frozen BLIP3o backbone and send only adapter updates, while full-model training remains possible when required. In reported eight-client experiments, adapter-only federation reduced per-client communication from 28.6 GB to 0.094 GB per round, improved VQA v2 by 0.7 points, and retained about 97% of centralized performance on VQA v2 and GenEval; the evaluation used simulated sites and does not establish clinical performance or formal privacy guarantees.
Gisting: Compressing LLM Agent context to ↑ throughput and ↓ cost
Long system prompts improve agent behavior but increase inference time, cost, and the GPU capacity needed to serve a given traffic level. Shopify compresses the Sidekick GraphQL agent’s roughly 6,000-token system prompt into about 1,500 gist tokens, using special vocabulary tokens whose embeddings are learned by knowledge distillation while the model weights remain frozen. Training compares teacher logits from the full prompt with student logits from the gist-token prompt using KL divergence; at inference, the prompt is replaced with the gist-token string, requiring no custom serving path. In load tests at 350 requests per minute, compression reduced median time to first token from 438ms to 354ms and end-to-end latency from 6.8s to 4.2s, while raising throughput from 20.2 to 23.4 QPS and enabling 14% fewer GPUs in production without losing prediction quality.
The P-Completeness of Inverted Index Traversal: On the Complexity of Evaluating Boolean Query DAGs
Modern artificial intelligence agents increasingly rely on search infrastructure to run complex, neuro-symbolic reasoning workflows that compile into deeply nested, non-monotonic Boolean queries. Standard inverted index evaluation methods struggle with these query structures, facing either exponential query complexity under Document-at-a-Time models or universe-scale space penalties under Term-at-a-Time models during logical negation. To address these theoretical limitations, the author formalizes a DAG-based retrieval language named L_R and proves its query evaluation problem is strictly P-Complete. The paper introduces ComputePN, a deterministic and sparsity-aware algorithm that employs a Positive-Negative dual representation alongside native DAG memoization. This mechanism bounds evaluation time to O(|Q| · |U_active|), effectively evaluating P-Complete queries natively over the index while bypassing combinatorial tree expansion and universal scan overhead.
Run Massive-Scale UMAP in Minutes Using Multiple GPUs—Without Losing Accuracy
UMAP workflows on tens to hundreds of millions of vectors are constrained by the cost of constructing an all-neighbors k-nearest-neighbor graph, especially when repeated runs support exploration and parameter tuning. The NVIDIA cuML and cuVS 25.06 feature distributes this graph-construction stage across multiple GPUs while retaining the out-of-core design that partitions data into balanced clusters, overlaps vectors across nearby clusters, computes local graphs, and merges them into a global graph. knn_n_clusters and knn_overlap_factor expose the memory, runtime, and graph-quality trade-off: more clusters reduce per-GPU data, while more overlap can improve nearest-neighbor recall at higher computational and memory cost. On eight NVIDIA H100 GPUs, the reported evaluation found up to 74x end-to-end speedup over a projected CPU runtime for the 106M-vector MIRACL dataset, completing it in 8 minutes. The post states that performance continues to improve from one to eight GPUs while preserving comparable embedding quality across configurations.
17,600 Actions: Agent Security Is a Systems Problem
Security incidents involving AI agents, such as the OpenAI and Hugging Face event where attackers executed 17,600 actions, demonstrate that system security cannot rely entirely on manual human review. Managing agent velocity requires dedicated system-level controls to properly constrain, observe, and govern their behaviors during execution. To secure autonomous development workflows, Docker Sandboxes allow AI agents to operate within GitHub Actions, run Testcontainers tests, adjust code, and automatically generate draft pull requests inside isolated environments. In addition, escalating software supply-chain threats and the increased volume of AI-generated code drive the adoption of Docker Hardened Images and Docker Extended Lifecycle Support. These updates incorporate software built from source into container images, extend security patch coverage past end-of-life milestones, and move organizational policy enforcement directly onto developer machines.
When it comes to Governance, Retailers need a control plane for context
Retailers are moving from isolated generative-AI pilots to enterprise-wide adoption, where each store, headquarters, and digital workflow needs different data, permissions, models, and cost controls. The post argues that useful AI depends on governed business context, while fragmented tools can produce separate provider contracts, logs, permission models, cost centers, and answers to the same question. It proposes an open control plane that centralizes governance and model access without forcing employees into one application or vendor. The described Databricks design combines Unity Catalog for data and business context, Unity AI Gateway for routing and oversight, Foundation Model APIs for commercial, open-source, and custom models, and Genie for natural-language queries over governed data; the intended result is faster experimentation and deployment with visibility into access, spending, lineage, and auditability.
What's New with Monitoring in PostgreSQL 19
PostgreSQL 19, still in beta when this was written, adds monitoring and observability changes spanning lock contention, logging, WAL, wait events, remote messages, and multixacts. The default for log_lock_waits changes to on, while log_min_messages gains per-process-type levels and autoanalyze receives its own duration setting. A new wal_fpi_bytes counter exposes full-page-image volume cluster-wide, per session, per query, and in VACUUM and ANALYZE logs; new wait events expose WAL write, flush, and replay stages plus COPY file, pipe, and program I/O. Remote server messages now use normal PostgreSQL logging with origin prefixes, and pg_get_multixact_stats() surfaces multixact usage that previously required filesystem inspection and educated guessing. The post also lists upgrade work for parsers, metric collectors, wait-event dictionaries, configuration UIs, and alert thresholds, while noting that final release notes may differ.
Building Shared Memory for AI Agents in Notion
Lore is an open-source, MIT-licensed tool from Notion for giving AI agents shared, persistent memory backed by Notion, addressing experiential knowledge, follow-up tasks, decision records, and procedures that can disappear between sessions. A Lore vault uses five related Notion databases—Projects, Topics, Memories, Entities, and Facts—with MCP tools for agents, Notion or a CLI for humans, and hooks intended to retrieve context and save information in the background. The design emphasizes memory maintenance: facts expire by default, relationships such as supersedes and conflicts_with clarify updates, and the CLI can identify orphaned or duplicated information. In a 500-query SkillRet retrieval evaluation, Lore achieved 84% success, while a paired model evaluation found seeded memory recovered about 46% of failures on tasks never solved without memory. The results indicate that relevant, well-maintained memory can improve agent performance, while stale or irrelevant content can harm it.
Agent Memory Inside the Harness
The post distinguishes agent state, the run-bound working data of a single execution, from agent memory, knowledge that outlives the run and is read across sessions. Context compaction, which decides what to keep when the window fills, is lossy by construction and sets both token cost and reliability; Chroma’s study found models become unreliable well before their advertised 200k-token window, and teams compact at 95% or proactively at 60%. System prompts and skills must be versioned, governed infrastructure, not text files, with prompt registries and the SKILL.md standard for procedural memory, and skills are executable so they require sandboxing. Enterprise data enters memory through pipelines like change data capture, not migrations, with chunking, embedding, and provenance stamps. The database choice caps filtered recall under selective scoping, the consistency window, and temporal modeling, setting the ceiling for later decisions.
How Databricks Feature Store serves features with sub-second freshness
Databricks Feature Store addresses the lag between batch-computed machine-learning features and decisions that depend on events from seconds earlier. It lets a feature definition drive both offline batch processing and online streaming pipelines, orchestrating Kafka ingestion, Spark Real-Time Mode (RTM), Lakebase, and Model Serving. For a rolling 10-minute transaction sum, RTM updates per entity state in local RocksDB, expires contributions per event, and writes revised values to Lakebase through a streaming JDBC sink. The described path reports end-to-end p99 200ms latency from Kafka arrival to online feature availability, while Model Serving retrieves declared dependencies automatically at inference. Tumbling and sliding windows remain options when fewer, cheaper updates are acceptable.
Build zero-trust AI agents with Google's Agent Development Kit
Connecting an autonomous Agent Development Kit (ADK) agent to databases, internal APIs, and code execution turns model decisions into production-state changes that system prompts cannot securely constrain. The post presents an open-source Customer Support & Returns Agent built with ADK and Gemini, using an example where prompt injection could produce an unauthorized refund or leak environment secrets. Its zero-trust design combines hardware-backed signing for database mutations, gVisor isolation with no network egress and resource limits for generated Python, and deterministic semantic gateways for prompts, tool calls, and database updates. Local equivalents use HMAC keys, a database ingress verifier, a constrained Docker runner, and Python validation tests, while production mapping uses Cloud KMS, HSM, and VPC Service Controls. The conclusion is that infrastructure-enforced boundaries let the model reason dynamically within strict limits.
Measuring campaign impact with social and search data
Campaign post-mortems often report reach, engagement, impressions, and sentiment without establishing whether a campaign changed perception or behavior. It argues that social listening should measure sentiment, themes, mention volume, and audience conversation shifts, while search intelligence measures category and branded demand, promoted benefits, and share of search. A client example contrasts a campaign that generated strong social buzz while category search declined with a later campaign that reversed declining demand, captured two-thirds of share of search, and grew search intent 134%. The difference was attributed to combining socially engaging creative with media strategy and messaging designed to drive search demand. The proposed framework aligns measurement with campaign goals and uses gaps between social sentiment and search intent to identify awareness without demand, existing intent without audience expansion, or stronger market impact.
Top topics
- Architecture830
- Performance812
- LLMs655
- Machine Learning619
- Open Source562
- AI Agents546
- AI458
- Developer Experience447
Weekly digest
The best engineering reads, once a week.