I built non-autoregressive decision models with RL a year ago
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
I built non-autoregressive decision models with RL a year ago
Unofficial Hacker News client; not affiliated with Y Combinator.
Oras · · focus · HN ↗
It’s a bit faster and bit cheaper, but this is compared to LLM. The consistency was nice to see, BUT, as someone who trained NLP models prior to LLMs, it’s just BERT with more data. I can see why people would want ready made one shot classifier, and I can see the value of sending multiple classifier in one call, but I wouldn’t call it breakthrough. And I believe many labs will replicate it in no time and might have it as part of their harness.
I see it as a wake up call for the tech community to go back to basics for most tasks instead of relying solely on generic LLMs.
tchalla · · focus · HN ↗
dominotw · · focus · HN ↗
We ripped out custom homegrown ml models that were developed in last 10 yrs and put an llm in its place. Its the opposite of wasteful. Even local gemma models are vastly superior.
tchalla · · focus · HN ↗
ramses0 · · focus · HN ↗
Mode switching has a cost. Usually std::sort is good enough compared to picking the prime optimal algorithm for your expected shape. Just call the function and get on with your day.