David Markley @dbmarkley

Building @yieldpointcap & tinkering w. ai x @algorand, @HivemindCap, @carbonb1ack; @masschallenge alum Joined February 2021

Tweets

411
Followers

669
Following

564
Likes

5K

David Markley @dbmarkley

a month ago

@jeremykauffman @L0m3z @ChHouseBooks Did you say NH homeschool groups? 👀

0 0 1 17 0

View Details

David Markley @dbmarkley

2 months ago

h/t @garrytan for "fat skills, thin harness" & @claudeai for cooking on Claude Managed Agents

0 0 0 47 0

View Details

David Markley @dbmarkley

2 months ago

x.com/i/article/2044…

1 0 1 56 0

View Details

@claudeai @bcherny - if a solopreneur was tinkering via their personal account and would like access to Outcomes, Multiagent Orchestration & Memory, is there a path? Or is the answer to spin up a business account, migrate to working there, and then apply? Thanks in advance!

0 0 0 19 0

View Details

David Markley @dbmarkley

2 months ago

@trq212 yes x.com/dbmarkley/stat…

David Markley @dbmarkley

2 months ago

x.com/i/article/2041…

2 0 8 446 1

0 0 0 94 0

View Details

David Markley @dbmarkley

2 months ago

Seeing a lot of builders post today that they were also building agent harnesses and orchestrators, thinking they were one of maybe 50 people with this idea. Turns out there were thousands of us. Which raises an interesting question: Did Claude lead us toward patterns that Anthropic had already discovered internally? Or did Anthropic watch how we were all building with Claude and productize what emerged? Either way, it's a fascinating feedback loop. The tool shaped how we built. How we built shaped the next version of the tool

David Markley @dbmarkley

2 months ago

In a hilarious twist of fate, Anthropic appears to have launched Managed Agents ~10 minutes after I posted about building this all from scratch. The timing is impeccable. I'll be reading their docs tonight to see how much of my orchestrator just became unnecessary.

1 0 2 123 0

0 0 3 67 0

View Details

David Markley @dbmarkley

2 months ago

@nikil thank you for the inspiration @nikil 🫡

0 0 0 10 0

View Details

David Markley @dbmarkley

2 months ago

x.com/i/article/2041…

2 0 8 446 1

View Details

David Markley @dbmarkley

2 months ago

💯 The stack I built is specific to how I operate as a PM running multiple projects. The orchestrator, knowledge architecture, and review pipeline all emerged from my specific constraints. Anthropic's Managed Agents will handle the generic infrastructure better than I ever could. The question I'm most interested in is: what are the domain-specific patterns that sit on top of that infrastructure? The committee design, the verification fidelity spectrum, the knowledge routing. Unclear how we share those templates at scale as I don't think they get commoditized by Anthropic/OpenAI

1 0 0 9 0

View Details

David Markley @dbmarkley

2 months ago

@austin_way Isn’t the conclusion to use locally hosted open source models so they can’t take it away?

0 0 0 77 0

View Details

David Markley @dbmarkley

3 months ago

@fancylancer3991 My intuition is that the generalization works well across verifiable tasks, thus the work is to transform subjective tasks into objective approximations in order to benefit from the generalized intelligence

0 0 0 44 0

View Details

David Markley @dbmarkley

3 months ago

@nikil @davehappyminion Install ClawFlows... ... immediately feel like you live in the future

1 0 1 448 0

View Details

David Markley @dbmarkley

3 months ago

tried “remove HITL” system ran better so much for all those RTS hours

0 0 1 89 0

View Details

YieldPoint @YieldPointCap

3 months ago

Our co-founder & COO @dbmarkley will be live on X today at 12 PM ET discussing real-world stablecoin adoption and where the next wave of usage is coming from. Tune in 👇

The Tie @TheTieIO

3 months ago

Today at 12pm ET. Real-World Stablecoin Adoption: Lessons from Emerging and Institutional Use Cases Featuring: • @dbmarkley (@Xsy_fi) • @rparekh (@monad) • Vasily Sidorov (@gaib_ai) • Jackson Weinreb (The Tie), Moderator Join us live on X.

0 0 1 836 1

1 1 8 338 0

View Details

David Markley @dbmarkley

5 months ago

One of the remarkable things is that these models, despite being designed to predict the next token, are developing cognitive strategies that were never explicitly intended. I’d wager that, with sufficient state and runtime learning, LLMs might provide these customizations on their own.

0 0 0 22 0

View Details

David Markley @dbmarkley

5 months ago

@iruletheworldmo Do you know of any work related to the evaluation of models solely trained on human-generated artifacts versus human+LLM generated artifacts?

0 0 0 30 0

View Details

David Markley @dbmarkley

6 months ago

Circa ~2020 I experienced a similar crisis of confidence in the space, and, aligned with what @nic_carter describes, came to the conclusion that the gap between expectation and reality was a feature, not a bug. For most of the people I know in crypto this reconciliation has become a a right of passage. Many of us were drawn to crypto because we believed in its potential to create a better future; we stay to ensure that potential manifests itself.