Loading…
Machine Learning
67 posts about Machine Learning. Every summary links to the original.
Ideas Worth a Longer Conversation: The JetBrains Research Podcast
The JetBrains Research Podcast investigates foundational software development and computer science questions through discussions with industry researchers. In team psychology, Cat Hicks demonstrates that collaborative culture and organizational belonging reduce developer anxiety around automated tooling while curbing the risks of overproduction pressure. Historical analysis by Tomáš Petříček shows that programming spans five competing cultures rather than pure specification implementation, explaining why automated code generation historically encounters limits. Regarding artificial intelligence evaluation, Ibragim Badertdinov details how SWE-rebench isolates model capability through dataset decontamination, leveraging the strict verifiability of software test execution for training feedback. Additionally, conversations with Alexander Kulikov and Anna Kogan examine how foundational mathematical understanding aids AI oversight and address adoption hurdles for open-source computer vision infrastructure.
Katie FraserFrom Prediction to Action: How to Turn AI Outputs Into Decisions
Salesforce addressed an operational challenge where sellers faced roughly 12,000 dashboards and over 20 applications outputting machine learning predictions without clear next steps. The engineering team reframed machine learning outputs as raw signals rather than standalone answers. To bridge the gap between assessment and action, they built a Next Best Action layer that combines model signals, business logic, and contextual institutional knowledge into actionable recommendations. They integrated this layer with an AI agent using Model Context Protocol (MCP) tool contracts, enabling dynamic discovery and explicit handling of missing data. Finally, rather than introducing a separate dashboard destination, the agent serves on-demand recommendations directly inside Slack where sellers already collaborate.
Scott NybergMeta ·
MTIA 300: Meta’s First Training Chip with Built-in NICs and Communication-Offloading Engines
Training recommendation models poses distinct network bottlenecks because massive embedding tables trigger frequent collective operations that compete with computation on standard GPUs. Meta designed the MTIA 300 accelerator to overcome this by embedding two network chiplets containing twelve 800 Gbps RDMA NICs directly inside the chip package. The architecture offloads communication from its compute grid to sixteen dedicated message engines equipped with RISC-V cores and near-memory compute reduction blocks. Working alongside the co-designed HCCL library, the chip autonomously compiles and executes collective communication subgraphs without host CPU intervention. On a 150-billion-parameter production recommendation model, MTIA 300 delivered communication speeds 3.9 times faster than an equivalent GPU cluster while keeping concurrent compute degradation under 0.5 percent.
By Rajiv Krishnamurthy, Wes BlandSay it once: introducing Bot Preference Sync
Cloudflare announced Bot Preference Sync, a feature across all customer tiers that automatically reflects dashboard AI bot configurations directly in a site's robots.txt file. Website operators previously faced challenges synchronizing static robots.txt directives with edge enforcement rules, which led some crawlers to ignore stated preferences or attempt bypasses. Under this system, Cloudflare generates and prepends directives for Search, Agent, and Training categories to existing robots.txt files using crawler lists tracked in BotBase. Mixed-use crawlers performing both search indexing and training must meet strict transparency criteria, including honoring opt-outs and providing page-level visibility, to avoid edge blocks when training is disallowed. Additionally, onboarding workflows allow ad-supported publishers to automatically set AI model training to Disallow by default while retaining search visibility.
Jin-Hee LeeGrab ·
Building Jarvis Pro: Route first, answer later
Grab designed Jarvis Pro as an AI assistant for account managers turning complex account data into actionable merchant conversations. Early prototypes generated polished but operationally unsound advice, such as pushing promotions when order drops were caused by outlet pauses and fulfillment issues. To address this, the team implemented a "route first, answer later" design that uses a prompted LLM classification step constrained by a routing guide to dictate context, tool paths, answer structure, and guardrails before generation. The pipeline also isolates narrow memory decisions, reconciles metric freshness across data sources, and caps tool calls to maintain usability. In offline evaluations across 351 realistic prompts, routing matched safe routes 99.4% of the time while answer quality scores in a portfolio subset improved from 78.5 to 91.0.
Christian CoffrantAirbnb ·
How we knew COVID was over (and what our models had to unlearn)
Airbnb's forecasting team outlines their framework for managing production models that experience drift or external shocks. Rather than treating model updates as a generic retraining task, they distinguish between refitting with new data, respecifying the underlying model structure, and intentionally holding without changes. This discipline prevents teams from chasing temporary noise, carrying obsolete crisis assumptions, or over-engineering solutions during disruptions.
Harrison KatzMeta ·
How We’re Building Scam Alert on WhatsApp With End-to-End Encryption and Verifiability Guarantees
WhatsApp is introducing Scam Alert, an optional feature designed to detect scam messages from non-contacts while preserving end-to-end encryption guarantees. The system executes text classification entirely on-device using a machine learning model trained on conversational patterns from user reports, ensuring raw message content never leaves the client. To evaluate feature accuracy without compromising privacy, the client transmits minimal pre-aggregated telemetry—consisting only of warning and action counts—over Oblivious HTTP relays to Trusted Execution Environments. These confidential virtual machines securely aggregate metrics and apply differential privacy noise before exposing population-level statistics to servers. System integrity and non-targetability are maintained by requiring clients to attest backend binaries against public transparency ledgers before transmitting any telemetry.
Grab ·
Grab Bench: Evaluating AI on Grab-shaped production work
AI models evaluated on internal tasks often produce subtly plausible errors, such as altering metric definitions in SQL queries or missing hidden stateful invariants in code patches. To address this, Grab built Grab Bench, a configurable evaluation harness that executes model providers through specialized task plugins. The platform evaluates synthetic or redacted datasets that preserve production constraints across domains like query generation, tool use, passenger-profile reasoning, and agentic coding. By recording granular row-level outputs with deterministic scorers and LLM judges, the harness exposes failure modes rather than relying solely on aggregate leaderboards.
Christian CoffrantUnveiling good and bad behaviors on the Agentic Internet
Web traffic increasingly shifts between human interaction and automated agents, rendering point-in-time security checks ineffective against sophisticated automation. Cloudflare addresses this shift through continuous behavioral analysis designed to evaluate trust across entire user sessions rather than relying on static point-in-time hurdles. Its CDN-injected client-side system, Precursor, tracks continuous behavioral indicators like cursor movements to catch mid-session automated takeovers. To counter rapid bot adaptation, Cloudflare is introducing self-adjusting machine learning models under Adaptive Intelligence and non-deterministic defenses such as the AI Labyrinth. These tools allow site owners to poison scraper training data, trap crawlers in synthetic webs, or queue legitimate agents while dynamically penalizing abusive traffic.
Jin-Hee LeeMeta ·
From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking
Scaling sequence models for real-time ad recommendations faces latency bottlenecks and scaling ceilings when hybrid configurations process both long user histories and sparse feature interactions online. Meta addresses these trade-offs with a multi-stage architecture that decouples heavy, asynchronous offline user modeling from lightweight, real-time online ranking. Deep upstream transformer models process sequences of thousands of actions to generate cached user embeddings, which downstream online models combine with candidate ad features using dense tokenization and target-aware multi-head attention. This framework produces predictable, LLM-style log-linear scaling curves between compute and normalized entropy without disproportionate increases in online serving costs. Implemented as part of Meta's Generative Ads Recommendation Model, the design achieved a cumulative 6% lift in Instagram conversions and a 3% lift in Facebook conversions.
By Steven De Gryze, Parshva Doshi, Sean O'Byrne, Arnold Overwijk, Dinesh Ramasamy, Lee XiongMeta ·
GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model
Meta's Generative Ads Recommendation Model (GEM) trains across thousands of GPUs using a hybrid architecture featuring trillions of sparse embedding parameters and billions of dense parameters. Standard training infrastructure built for large language models struggles with recommendation-specific workloads characterized by jagged user activity histories, asymmetric attention patterns, and numerical sensitivity. To overcome these bottlenecks, engineering teams introduced custom kernels like Jagged Flash Attention and Generalized Dot-Product Attention alongside MXFP8 mixed-precision execution. Pairing these kernel optimizations with topology-aware 5D parallelism doubled end-to-end training efficiency to 20–25% Model FLOPs Utilization while scaling total training FLOPs fourfold over twelve months.
Netflix ·
GenRec: Towards LLM-Native Recommendation at Netflix
Netflix developed GenRec, an LLM-backed recommendation ranker built by adapting an internal foundation model for large-scale personalization. Traditional recommendation stacks rely on thousands of hand-crafted features and specialized architectures that are costly to maintain across diverse content types. To replace manual feature pipelines, GenRec verbalizes user histories, metadata, and contexts into natural-language prompts and trains with multi-objective losses, including catalog-aware ranking and reward-weighted alignment. At inference time, the model executes in prefill-only mode on vLLM without decoding text. In large-scale online A/B testing against a mature production ranker, GenRec achieved statistically significant improvements in short-term and long-term metrics while using fewer labeled examples.
Netflix Technology BlogGrab ·
Crowdsourced taxonomy verification: A feedback-driven framework for refining knowledge graph relationships via online search interactions
Maintaining accurate Knowledge Graphs in dynamic domains like e-commerce and food delivery is challenging because automated language models frequently hallucinate relationships while manual curation cannot scale. To validate structural taxonomy links continuously, a closed-loop verification framework operationalizes search interfaces by injecting unverified candidate edges as hypotheses into live user traffic. The system uses an exploration-exploitation strategy to place candidate relationships in lower-risk interface slots, tracking contextually anchored micro-interactions such as clicks, dwell times, and purchases. An offline verification engine aggregates these weighted interactions into normalized confidence scores, automatically promoting verified links to permanent graph edges and pruning refuted relationships.
Junpeng NiuAirbnb ·
Eval-driven development: Lessons from evaluating GenAI at scale
Airbnb outlines its framework for eval-driven development (EDD), treating GenAI evaluation as a continuous engineering discipline rather than an afterthought. The strategy combines programmatic checks, calibrated LLM-as-a-judge evaluators, and human review to detect subtle quality regressions. By inspecting intermediate agentic execution traces and real-world failure modes, teams ensure generative models remain reliable and aligned with product requirements.
Rohit GirmeHow AI Rebuilt Salesforce’s Decades-Old Localization Pipeline
Salesforce needed to deliver major releases across 34 languages as product localization volume surged by more than 35% under fixed budgets and unchanged delivery windows. To address these scaling constraints, the engineering team replaced their legacy translation workflows with an LLM-powered orchestration pipeline integrating prompt engineering, context engineering, and multi-stage validation. The architecture transforms existing style guides, glossaries, and terminology databases into structured context, routing interface strings through specialized prompt stages—up to 85 stages for some languages—to enforce product context, grammar, and branding rules. Combined with an automated validation loop spanning AI editing, AI validation, and human review, this system reduced localization costs by 50 to 90% while accelerating turnaround times across enterprise releases.
Scott NybergAirbnb ·
Personalizing Airbnb search by learning from the guest journey
Airbnb replaced hundreds of hand-crafted ranking features with a Transformer-based sequence model that captures both long-term booking history and short-term browsing behavior. To keep latency low and throughput high, sequence representations are generated via daily batch jobs and combined with real-time queries using a co-trained setwise ranker.
Daochen ZhaNetflix ·
In-House LLM Serving at Netflix
Netflix established an in-house serving platform to run large language model inference directly inside existing production environments alongside traditional machine learning models. Built upon NVIDIA Triton Inference Server and vLLM, the unified architecture handles member-scale routing, candidate generation, feature fetching, and model execution over gRPC and OpenAI-compatible HTTP endpoints. The team shifted their primary engine from TensorRT-LLM to vLLM to support custom architectures, simpler debugging, and non-trivial constraint logic. Addressing production obstacles required patching Triton's frontend for guided decoding, pinning dependent library versions, rewriting logits processors in C++ for vLLM V1, and handling state machine resets during engine preemptions. The resulting platform unifies deployment flows while preserving operational stability across evolving model schemas.
Netflix Technology BlogMeta ·
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Meta developed Hierarchical Interest Representation as an upstream representation layer to optimize deep funnel ad ranking across its platforms. The architecture organizes interactions among users, advertisers, and products into a heterogeneous, time-decayed graph and projects sparse raw edges into multi-level super-graphs of latent interest primitives. To encode these structures, a transformer-based hierarchical encoder incorporates multimodal product semantics processed via language models alongside topology-aware attention biases. Computation scales across billions of entities by pairing deep hash ID embeddings with FlexAttention to evaluate graph biases on the fly without materializing full matrices. Self-supervised cross-view distillation trains student representations against broader teacher graph views to yield universal embeddings and interest tokens.
By Yuhui Ouyang, Di Wang, Sreedal Menon, Jie TianAirbnb ·
From weeks to a day: how we made LLM evaluation fast enough to iterate on
Airbnb built a four-layer LLM infrastructure framework to reduce iteration and evaluation turnaround from weeks to a single day. By using per-sample caching for generated references and judge scores, they established a deterministic evaluation foundation that separates genuine model drift from measurement noise. This setup enables rapid, bounded model hotfixes using micro LoRA adapters and comprehensive end-to-end validation across component boundaries.
Baharak SaberidokhtMeta ·
Meta’s AI Storage Blueprint at Scale
Meta redesigned its BLOB-storage architecture on top of the foundational Tectonic block layer to eliminate GPU stalls and accelerate AI training workflows. The legacy storage system suffered from multi-layered metadata lookups, cross-region latency, and dataplane proxy bottlenecks that conflicted with the millisecond access requirements of flash-based AI clusters. To resolve these issues, the team collapsed disparate metadata into a single flat schema backed by ZippyDB for O(1) path lookups and introduced a fat client SDK capable of streaming data directly from storage servers. The updated stack also leverages spare GPU host memory as a distributed data cache alongside distributed read-plan caches to handle severe traffic spikes during checkpointing and model loading. These protocol and architectural changes deliver predictable latencies, reduce power consumption, and maintain high throughput during distributed training.
By Sidharth Bajaj, Venkatraghavan Srinivasan