Topic
Ensemble Methods
4 episodes
-
Theoretical Limits of Language Model Alignment
The paper derives a theoretical ceiling for alignment under a KL-divergence budget, offers a way to estimate that ceiling before training, and finds that best-of-N sampling gets close while PPO and GRPO leave substantial performance on the table. Justy and Cody explore what this means for reward hacking, production alignment, and the cost of inference-time search.
-
TrustedRouter launches three new encrypted 'fusion' models that combine multiple LLMs, including one with exclusively U.S. models
TrustedRouter just shipped three “combo” models that sit behind one OpenAI-style endpoint but quietly fan your request out to multiple LLMs, with optional encrypted routing and even a U.S‑only panel. The interesting bit isn’t just reliability; it’s turning “which model, at what cost and privacy level?” into a preset you call like any other model.
-
Introducing TabFM: A zero Shot foundation model for tabular data
Justy and Cody examine TabFM, Google Research’s zero-shot foundation model for tabular classification and regression. They unpack its hybrid row-column attention design, synthetic-data training, TabArena evidence, the trade-off between out-of-the-box convenience and tuned ensembles, and whether BigQuery integration could make this genuinely useful in everyday data workflows.
-
Micro Agent: Beat Frontier Models with Collaboration inside Model API
Justy and Cody dig into vLLM Semantic Router's Micro-Agent argument: the real product isn't a bigger model, it's a router that turns one model call into a bounded collaboration loop. They like the serving-layer abstraction, push on where the benchmark story is still thin, and land on who should actually care right now.