Everyday Data Science: applied AI, agentic systems, machine learning, and AI in Africa, written by practitioners for people who build.

Passed Once Is Not Reliable: ThinkingBox Grades Agents on the Database, Not the Demo

ThinkingBox checks the final database state after an agent finishes, not its summary. Across 121,680 trials, 79,853 failed, and 67% of failures ended with no tool error. One good demo is not reliability.

Ibrahim Denis Fofanah·7 min

The Hermes Index Ranks Agent Models on Score and Cost. The Lab That Built It Just Raised $90M.

Nous Research's Hermes Index (Oct 6, 2026) pairs agent scores with cost per task for 14 models. Opus 5.5 leads on score at 63.31; the value story belongs to Sonnet 5.5 and DeepSeek V4.1 Flash.

Ibrahim Denis Fofanah·8 min

MCP, Explained for Data People: It Standardizes the Plumbing, Not the Thinking

MCP standardizes how agents connect to data and tools: three roles, three primitives, one wire format. I built a minimal server and ran it end to end; here is what the protocol guarantees, and the security fine print most tutorials skip.

Ibrahim Denis Fofanah·9 min

Your 0.85 Meant 0.98: A 20,000-Row Calibration Test That Caught a Top Model Misstating Its Own Odds

On 20,000 rows, a random forest with AUC 0.972 had a calibration error of 0.082. Sigmoid calibration cut it to 0.004. Gaussian naive Bayes fell from 0.050 to 0.012 with isotonic calibration, and AUC moved by at most 0.001.

Ibrahim Denis Fofanah·10 min

The EU AI Act Is Already Enforcing. The Deadline Everyone Watched Was the One That Moved.

The enforcement machinery is running: chatbot disclosure, synthetic-content marking, GPAI documentation demands, and a US state banning algorithmic grocery pricing.

Ibrahim Denis Fofanah·12 min

Gradient Boosting Still Rules Tabular Data. The Foundation Models Are Gaining Ground.

Four years after a 45-dataset benchmark crowned gradient-boosted trees on tabular data, tabular foundation models (TabPFN, LimiX-2, NVIDIA's Kumo Tabular) are topping leaderboards. What the 2022 verdict got right, where it no longer holds, and how to choose your next tabular model.

Ibrahim Denis Fofanah·13 min

AI Research Agents Claimed 43% and 71%. Audited, They Got 2% and 15%.

Epoch AI's InnovationEval gave Claude Fable 5 and GPT-5.6 Sol 3,000 GPU-hours each to invent a training method. Claimed gains of 43% and 71% of a human breakthrough fell to 2% and 15% once cherry-picked runs and out-of-scope changes were removed.

Ibrahim Denis Fofanah·10 min

Your Benchmark Leaderboard Is Measuring the Test, Not the Model. Stanford Checked 56 of Them.

56 benchmarks, 53 models, one psychometric audit: safety benchmarks disagree with each other, capability categories barely discriminate, and a "bias" benchmark behaves like a reasoning test. If your model selection rests on leaderboards, read this first.

Ibrahim Denis Fofanah·8 min

RAG Systems Collapse When They Retrieve Their Own Writing. One Self-Authored Document Can Start It.

79.6% of 1,528 RAG simulations collapsed when the model retrieved documents it had authored itself, and a single self-written reference can trigger it. If your pipeline indexes its own output, this paper is about you.

Ibrahim Denis Fofanah·6 min