Blog
Long-form assessment of technology and education. Every substantive claim links to a primary or authoritative source; every article ends with its reference list.
3 article(s)
Long-Context Windows: What Independent Benchmarks Show Versus What Vendors Claim
Context windows now advertise millions of tokens, but independent benchmarks — RULER, NoLiMa, Lost in the Middle and a newer preprint on mu…
SWE-bench Verified Is Saturated: What the Score Actually Measures Now
SWE-bench Verified became AI labs' most-cited coding benchmark, but independent audits found roughly a quarter to a third of "solved" issue…
How People Actually Learn: What the Evidence on Memory, Practice and Assessment Does and Doesn't Show
Retrieval practice, spacing and interleaving are backed by decades of replicated experiments. Growth mindset and formative assessment show …