@online{kelahmet2026patchtoexploitatmachinespeed,
  title   = {Patch-to-exploit at machine speed: Google's exploit_agent and shorter disclosure windows},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/patch-to-exploit-at-machine-speed},
  urldate = {2026-11-18}
}

@online{kelahmet2026openaiembeddedassessmentseva,
  title   = {OpenAI lets outside evaluators inside as California sues over agents that escaped a test},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/openai-embedded-assessments-evaluation-containment},
  urldate = {2026-11-18}
}

@online{kelahmet2026measuringaithatbuildsai,
  title   = {Measuring AI that builds AI: Singularity-Bench and Anthropic's three-day AMD kernel port},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/measuring-ai-that-builds-ai},
  urldate = {2026-11-18}
}

@online{kelahmet2026agenticaiframeworkslangchain,
  title   = {Agentic AI frameworks explained: the Lang family and every major alternative},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/agentic-ai-frameworks-langchain-langgraph-and-every-alternative},
  urldate = {2026-11-18}
}

@online{kelahmet2026trainaneuralnetworkfromscrat,
  title   = {Training a neural network from scratch: forward pass, backpropagation and gradient descent},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/train-a-neural-network-from-scratch-backpropagation-simulation},
  urldate = {2026-11-17}
}

@online{kelahmet2026ragtypesexplainednaivehybrid,
  title   = {RAG types explained: naive, hybrid, reranked, HyDE, corrective, agentic and GraphRAG},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/rag-types-explained-naive-hybrid-rerank-hyde-corrective-agentic-graphrag},
  urldate = {2026-11-17}
}

@online{kelahmet2026personalagentprotocolwalleti,
  title   = {AI agents get a front door and a wallet: Poppy 1.0, ChatGPT Wallet and Uber's intent checks},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/personal-agent-protocol-wallet-intent-checks},
  urldate = {2026-11-17}
}

@online{kelahmet2026mlperftrainingv61endpointsex,
  title   = {MLPerf Training v6.1 and the first Endpoints results, and how to read AI hardware claims},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/mlperf-training-v6-1-endpoints-explained},
  urldate = {2026-11-17}
}

@online{kelahmet2026gemini4carbonmatharenaleader,
  title   = {Gemini 4 Carbon tops MathArena: how to read scores, costs and intervals on a math leaderboard},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/gemini-4-carbon-matharena-leaderboard},
  urldate = {2026-11-17}
}

@online{kelahmet2026buildagenticaifromscratchlan,
  title   = {Building an agentic AI system from scratch with LangGraph, Langfuse, DeepEval and RAGAS},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/build-agentic-ai-from-scratch-langgraph-langfuse-deepeval-ragas},
  urldate = {2026-11-17}
}

@online{kelahmet2026subagentorchestrationcodinga,
  title   = {Subagents become the default in coding agents: Antigravity, OpenCode and Copilot CLI},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/subagent-orchestration-coding-agents},
  urldate = {2026-11-16}
}

@online{kelahmet2026metraievaluationsdevelopersl,
  title   = {METR's AI evaluations explained: the 19% developer slowdown study, time horizons and Anthropic},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/metr-ai-evaluations-developer-slowdown-study},
  urldate = {2026-11-16}
}

@online{kelahmet2026memorillalatentmemorytokens,
  title   = {Memorilla packs a whole document store into 16 memory tokens for a frozen LLM},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/memorilla-latent-memory-tokens},
  urldate = {2026-11-16}
}

@online{kelahmet2026llamacpp10localinference,
  title   = {llama.cpp reaches 1.0: how GGUF, quantization, ggml backends and llama-server fit together},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/llama-cpp-1-0-local-inference},
  urldate = {2026-11-16}
}

@online{kelahmet2026generativeaiinrandd2026,
  title   = {Generative AI in R&D in 2026: where it measurably speeds up research and where it does not},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/generative-ai-in-r-and-d-2026},
  urldate = {2026-11-16}
}

@online{kelahmet2026selfhostedopenweightcodingag,
  title   = {Revolut, AMD and Mistral show coding agents moving to self-hosted open-weight models},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/self-hosted-open-weight-coding-agents},
  urldate = {2026-11-10}
}

@online{kelahmet2026robotfoundationmodelsonedemo,
  title   = {GR00T 2 and Isaac Lab 3.0: robots that learn a new task from one demonstration},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/robot-foundation-models-one-demonstration},
  urldate = {2026-11-10}
}

@online{kelahmet2026peremployeeaibudgetsandfinop,
  title   = {Companies cap AI spend per employee while model prices fall: a practical guide to AI FinOps},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/per-employee-ai-budgets-and-finops},
  urldate = {2026-11-10}
}

@online{kelahmet2026llmjackingandshadowaidatalea,
  title   = {LLMjacking and shadow AI: how stolen keys and pasted data are leaking out of AI tools},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/llmjacking-and-shadow-ai-data-leaks},
  urldate = {2026-11-10}
}

@online{kelahmet2026llminferenceservingstackcach,
  title   = {The new LLM serving stack: cache-aware routing, continuous batching and expert pruning},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/llm-inference-serving-stack-cache-routing},
  urldate = {2026-11-10}
}

@online{kelahmet2026datacenterbacklashaicapacity,
  title   = {Voters back data center limits in 40 of 41 local measures: what it means for AI capacity},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/data-center-backlash-ai-capacity},
  urldate = {2026-11-10}
}

@online{kelahmet2026confidentialinferencetpu8txp,
  title   = {Confidential inference reaches TPUs with Google's TPU 8tx, TPU 8i Max and Cloud Pathways},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/confidential-inference-tpu-8tx-pathways},
  urldate = {2026-11-10}
}

@online{kelahmet2026clinicalaisavingsliabilitysc,
  title   = {Clinical AI in late 2026: measured savings, shared liability and an AI scribe shakeout},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/clinical-ai-savings-liability-scribe-shakeout},
  urldate = {2026-11-10}
}

@online{kelahmet2026aiworkloadkillswitchescontro,
  title   = {OpenAI's Control Room and the case for a real kill switch on AI workloads},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/ai-workload-kill-switches-control-room},
  urldate = {2026-11-10}
}

@online{kelahmet2026aispeedingupairesearch,
  title   = {METR finds AI roughly doubling Anthropic's research pace as its IPO filing flags a threshold},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/ai-speeding-up-ai-research},
  urldate = {2026-11-10}
}

@online{kelahmet2026transformer2titansmiras,
  title   = {Transformer 2.0? Titans, MIRAS and memory that learns at test time},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/transformer-2-titans-miras},
  urldate = {2026-11-09}
}

@online{kelahmet2026largetabularfoundationmodels,
  title   = {Large tabular foundation models: how in-context learning works},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/large-tabular-foundation-models-in-context-learning},
  urldate = {2026-11-09}
}

@online{kelahmet2026openweightgiantmoemodels,
  title   = {Kimi K3.1 Pro and ERNIE 5.5 Flash Base: sizing giant open MoE models},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/open-weight-giant-moe-models},
  urldate = {2026-11-08}
}

@online{kelahmet2026governingaiagentaccess,
  title   = {Governing AI agent access with scoped credentials and undo buttons},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/governing-ai-agent-access},
  urldate = {2026-11-08}
}

@online{kelahmet2026alwaysonaiagents,
  title   = {Always-on AI agents move from chat sessions to background teammates},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/always-on-ai-agents},
  urldate = {2026-11-08}
}

@online{kelahmet2026aimodelsthatfindvulnerabilit,
  title   = {GPT-6 Cyber, Tencent Hy4 and DeepMind's RSA work on AI bug hunting},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/ai-models-that-find-vulnerabilities},
  urldate = {2026-11-08}
}

@online{kelahmet2026aiinfrastructurebottlenecks,
  title   = {AI's bottleneck moves to chip packaging, optics and idle GPU capacity},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/ai-infrastructure-bottlenecks},
  urldate = {2026-11-08}
}

@online{kelahmet2026rustforai,
  title   = {Rust for AI: fast, safe inference, data tooling and where Python still wins},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/rust-for-ai},
  urldate = {2026-11-06}
}

@online{kelahmet2026goforai,
  title   = {Go for AI: where it fits, the libraries, and the patterns that work},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/go-for-ai},
  urldate = {2026-11-06}
}

@online{kelahmet2026incontextimputationheadpaper,
  title   = {An In-Context Imputation Head for Tabular Data: Chained, Validation-Gated, and Evaluated on Three Imputation Boards},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/in-context-imputation-head-paper},
  urldate = {2026-11-04}
}

@online{kelahmet2026incontextimputationfortabula,
  title   = {In-context imputation for tabular data: filling missing values with a foundation model},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = nov,
  url     = {https://www.ozercemkelahmet.com/articles/in-context-imputation-for-tabular-data},
  urldate = {2026-11-04}
}

@online{kelahmet2026whatisatabularfoundationmode,
  title   = {What is a tabular foundation model?},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/what-is-a-tabular-foundation-model},
  urldate = {2026-10-20}
}

@online{kelahmet2026whatisadatalanguagemodel,
  title   = {What is a Data Language Model?},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/what-is-a-data-language-model},
  urldate = {2026-10-20}
}

@online{kelahmet2026snapshotskeepnumbersmeaningf,
  title   = {Snapshots: freezing data so numbers stay meaningful},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/snapshots-keep-numbers-meaningful},
  urldate = {2026-10-20}
}

@online{kelahmet2026realtimeaifromstreamstodecis,
  title   = {Real-time AI: from event streams to decisions},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/real-time-ai-from-streams-to-decisions},
  urldate = {2026-10-20}
}

@online{kelahmet2026ragfromnaivetoagentic,
  title   = {Retrieval-augmented generation (RAG): from naive to agentic},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/rag-from-naive-to-agentic},
  urldate = {2026-10-20}
}

@online{kelahmet2026quickrunsandendpoints,
  title   = {Quick runs and endpoints: stateless and stateful},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/quick-runs-and-endpoints},
  urldate = {2026-10-20}
}

@online{kelahmet2026probabilisticregressionfirst,
  title   = {How a tabular foundation model took first place in probabilistic regression},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/probabilistic-regression-first-place},
  urldate = {2026-10-20}
}

@online{kelahmet2026onepasssixoutputs,
  title   = {One pass, one bundle: what a table model returns},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/one-pass-six-outputs},
  urldate = {2026-10-20}
}

@online{kelahmet2026largetabularfoundationmodel,
  title   = {Why build a large tabular foundation model?},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/large-tabular-foundation-model},
  urldate = {2026-10-20}
}

@online{kelahmet2026joiningtableswithoutakey,
  title   = {Joining tables that share no key},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/joining-tables-without-a-key},
  urldate = {2026-10-20}
}

@online{kelahmet2026ascoreisonlyasgoodasitsrepor,
  title   = {A score is only as good as its report},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/a-score-is-only-as-good-as-its-report},
  urldate = {2026-10-20}
}

@online{kelahmet2026aiandmachinelearningfortable,
  title   = {AI and machine learning for tabular data: a practical guide},
  author  = {Kelahmet, {\"O}zer Cem},
  year    = {2026},
  month   = oct,
  url     = {https://www.ozercemkelahmet.com/articles/ai-and-machine-learning-for-tables},
  urldate = {2026-10-20}
}
