AI blogger scaling01 accused of blocking critics with receipts after benchmark data error
teortaxesTex · x · 2026-10-28
teortaxesTex mocks AI blogger Lisan al Gaib (scaling01) for blocking anyone who calls out his errors with receipts. Screenshots show the dispute stems from a FrontierCode 2.0 comparison where he allegedly used a September Chinese flash model instead of flagships like K3.1 Pro to skew a China-vs-US model comparison; critics shared the benchmark changelog proving models were added earlier. teortaxesTex speculates his "financial situation has deteriorated" and he's shilling US frontier labs hoping for an offer.
More from Fun
- kalomaze shares his earliest deep learning takes, written at age 16 in 2022 — kalomaze · 2026-10-28
- The Guardian pays tribute to pianist Stephen Kovacevich, dead at 86 — petefang · 2026-10-28
- Surreal AI-generated image shows a person hanging upside down from the ceiling — flowersslop · 2026-10-28
- KlingAI 4.0 recreates Austin Powers scene where Vanessa fails to take him out — AdImpossible8653 · 2026-10-28
- Atlassian's script to remove one retired app deleted 883 entire sites in 23 minutes — jimmykoppel · 2026-10-28
- "Any sufficiently advanced technology will be indistinguishable from AI" — mallow610 · 2026-10-28