HackerTrans
トップ新着トレンドコメント過去質問紹介求人

rfdearborn

no profile record

投稿

The Galaxy Brains Have ADHD

robdearborn.com
2 ポイント·投稿者 rfdearborn·7 か月前·0 コメント

LLMs Need Better Executive Function

robdearborn.com
7 ポイント·投稿者 rfdearborn·7 か月前·2 コメント

コメント

rfdearborn
·昨年·議論
> Sending a full-resolution screenshot every five seconds gets expensive fast.

For now.
rfdearborn
·昨年·議論
These are best understood as scheduled tasks for the AI instead of tasks for the user.
rfdearborn
·2 年前·議論
Yeah: the value of (good) OKRs is as a proof of work for the process of aligning teams' vectors with business objectives / each other.
rfdearborn
·2 年前·議論
This integration is way more limited and frictioned. Whereas with search Apple's fully outsourced and queries go straight to your 3rd-party default, Siri escalates to GPT only for certain queries and with one-off permissions. They seem to be calculating that their cross-app context, custom silicon, and privacy branding give them a still-worthwhile shot at winning the Assistant War. I think this is reasonable, especially if open source AI continues to keep pace with the frontier.
rfdearborn
·2 年前·議論
The trendline is definitely toward increasing dynamic routing, but I suspect it's more so that MoE/MoD/MoDE enable models to embed additional facts with less superposition within their weights than enable deeper reasoning. Instead I expect deeper reasoning will come through token-wise dynamism rather than layer-wise -- e.g., this recent Quiet-STaR paper in which the model outputs throwaway rationale tokens: https://arxiv.org/abs/2403.09629