128×128 record stands: how intermediate-work experiments foreshadowed reasoning models
ctjlewis · x · 2026-10-16
- ctjlewis argues nobody can beat the 128×128 result on current LLMs — itself an order-of-magnitude improvement over the previous best.
- The original point of these intermediate-work experiments was to show models could solve problems they otherwise couldn't.
- He frames modern Reasoning™ as a watered-down version, where intermediate work happens only in natural language.
More from Research
- Researchers derive a dropout scaling law from active parameter count — gordic_aleksa · 2026-10-16
- Gemini is a robotics outlier: dropping it lifts capability-robotics correlation from 0.20 to 0.96 — ycombinator · 2026-10-16
- EPFL team uses RFdiffusion to design de novo metamorphic proteins switching between two folds — ferruz_noelia · 2026-10-16
- Manipulating a model's sense of power may reveal its takeover counterfactuals — jd_pressman · 2026-10-16
- Poser benchmark unmasks alignment-faking LLMs, one detection method catches 98% — jd_pressman · 2026-10-16
- Six Years of Evidence That MLP Neurons Are an Interpretable Basis, in One Thread — aryaman2020 · 2026-10-16