Michael Dempsey

This is one of the best pieces I've read on AI in some time. "How can anyone stop being fascinated for long enough to be angry?"

Perhaps the biggest constraint surrounding further intelligent autonomy in robotics is training data. Enter: Using diffusion models to generate long-tail and hard to gather robotics training data. Great thread by @xf1280

Another great and tangible thread on how robotics can move forward from this time of optimism productively. Continue to believe this is a very slept on category for foundation models & LLMs as everyone looks at AI + SaaS.

One of the more thought-provoking ML papers I've read in awhile. Researchers built a model to determine Remaining Life (years till you die) based on a photo. Their model predicted within 8 years (SOTA age detection models are within 2-3 years).

Great thread again from @hausman_k on utilizing LLMs within robotics

One of my favorite podcasts ever was @pmje73 on @tseides Capital Allocators last year. At 14:00 Paul starts talking about thesis-driven investing and then portfolio management. A few highlights from the transcript of this section (+ link below).

This is a very good post by @chrissyfarr and co. which near perfectly sums up our views @CompoundVC on investing in healthcare today after seeing companies struggle to impact outcomes materially for the past decade without services.

In this dive also came across this great 2015 article by @nathanbenaich on AI that relates to other part of AGM We say being too early is indistinguishable from being wrong, but really being too early allows you to compound unique wisdom across cycles:

Straightforward but thoughtful post on how managing the protocol + product/app-layer should be default state for emerging builders in crypto

Also check out this awesome video on some of the work the @wayve_ai team has accomplished thus far.

For years we've been looking at DNA synthesis @CompoundVC with the belief that demand will continue to increase & incumbents like Twist may see new, formidable competitors. @shelbynewsad pushed forward our thesis here materially along with @Nima_Ronaghi in this great post.

Thought provoking post on structures of governance. Agree with Holden and believe that we need to think less of "what's commonly done" here as we try to invent new structures of organizations, whether that's governance, compensation, or roadmap building.