AutoOPT discovers new optimization algorithms, introducing the lemniscate constant
ErnestRyu · x · 2026-08-19
Optimization researcher Ernest Ryu presents two new algorithms found by the LLM-driven AutoOPT system: the Lemniscate Accelerated Gradient Method and Analytic ITEM-f.
Both contain novel components in their construction and convergence proofs; Ryu says it's the first time he has seen the lemniscate constant arise in optimization.
He frames this as a disruptive change for optimization researchers — the craftsmanship of designing efficient algorithms and proving convergence guarantees, a skill he spent years refining, will be 90% automated. But it's also an opportunity: researchers should embrace these tools to accelerate research and tackle harder problems.
More from AGI Musings
- Dario Amodei says AI better than humans at almost everything may be 2-3 years away — PolarBearby · 2026-10-16
- A Jevons-paradox take on why worrying about AI job loss is pointless — JnBrymn · 2026-10-16
- Mythos on Claude's 'smallness': accurate proprioception, not low self-esteem — repligate · 2026-10-16
- Australia's AERO guidance: avoid AI entirely in first three years of primary school — lmoroney · 2026-10-16
- Dwarkesh vs Tyler Cowen: full AI autonomy by 2030, $30k robots, and an AI psychosis roast — Neurogence · 2026-10-16
- Yudkowsky slams mech interp progress as critique sparks AI safety drama — inductionheads · 2026-10-16