OpenAI's Ted Sanders offers a rule for choosing GPT models
He says pick Astra for quality, Sol if somewhat price-sensitive, and Terra or Luna when price matters most.
Stories per day · 30 days
Relatedbellman-residual1distributed-training1fedavg1federated-learning1gpt1language-models1off-policy-evaluation1openai1pricing1reasoning1reinforcement-learning1self-evolving-models1
8 stories, newest first · one card per story
Stories tagged #model-selection
CovFedAvg selects federated models using local low-loss curves
On width-16 gas-sensor clients, balanced accuracy rose from FedAvg's 88.88% to 89.84%, below matched fine-tuning.
Pairwise Bellman validation selects off-policy estimators without extra critics
Unweighted PBV is competitive on Hopper and Deep OPE; target-occupancy weighting can help under controlled overlap.
HeirCommit and EvoHeir filter updates in self-evolving language models
HeirCommit cut harmful accepted updates 68-83% versus random inheritance; EvoHeir raised the math average 5.3% over Agent0.
FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing
FlexRouter selects complementary LLM subsets with DPPs to maximize answer coverage without a fixed inference budget.
Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing
SaveRouter trains LLM routers on 33–41% of feedback and shortens cost payback by up to 9.5 times.
Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing
RouteFM pretrains a frozen LLM router that generalizes to new models using behavioral context alone.
Choose your fighter: Balancing competing requirements to select models for your AI SOC
Cisco Talos guidance explains how SOC teams should balance competing requirements when selecting AI models for SOC and DFIR tasks.