Brandon McFarland

Engineering @tenex_labs | prev: CTO @ Nolan Technologies, Co-founder & CTO @ Greenwood Labs

[Alex Lieberman @businessbarista]

I'm excited to share MetaHarness with you all.

MetaHarness is the system behind @tenex_labs' SDLC, the principles it runs on, and what changes when agents become partners in development.

With MetaHarness, our engineers can run 12-hour+ tasks and know that they will stay on track, follow our process, do the right thing.

We haven't shared how it works...until now.

There are 8 core principles, which we expand on in excruciating detail in the essay.

1) Context becomes part of the system
2) A blueprint that is allowed to change
3) We practice benevolent prompt injection
4) Tribal knowledge is embodied by shared skills
5) The development process has a machine interface
6) Validation makes autonomy safer
7) Tenex OS makes the process legible to the team
8) The process learns from the work

If you want to evolve your own approach to building software with agents or transform an entire engineering org's SDLC, i highly highly recommend reading this in full.

[Alex Lieberman @businessbarista]

https://t.co/jflX0neNSF

[Citrini @citrini]

Okay let’s figure out what’s going on down here.

[Andreas Bigger @andreaslbigger]

Introducing Edge, a high level, strongly statically typed, multi-paradigm domain specific language for the Ethereum Virtual Machine (EVM).
https://t.co/jaGrutMEqM

[baby keem @babykeem]

how do u fix openclaw internal reasoning leaking

[Brandon McFarland @BranMcF]

@philip0x I'm surprised there aren't more stablecoin-native LOC products *for humans*

Buying USDC with a card to give an agent money is clunky

Lending stables to a human solves multiple problems (underwritability, no on-ramping, no sybil, lender recourse, etc.)

Not a DeFi product though

[Brandon McFarland @BranMcF]

@joon_s_pk @karpathy @drfeifei @adamdangelo @rauchg @scottbelsky This is very cool, congrats on the launch!

[Brandon McFarland @BranMcF]

@QwQiao I put together an exploration deck on this topic back in November, can DM it to you if interested.

[Derek Barrera | 🐂 @DerekBarrera]

Recently, I've become fascinated with bending Solidity in weird ways. Though this i've build some amazing things. Biggest achievement to date has been a custom virtual machine that runs entirely onchain at the transaction level called Matador (It's literally a breakthrough for the industry).

I tried to do the same with the @paradigm / @meridiandotapp / @danrobinson AMM challenge.

Today I share an onchain quantized neural network, or QNN for short. The idea was basically: could I build a tiny inference system onchain and, if so… could I train a set of weights that would be competitive within the challenge?

Most competition on the AMM challenge is concentrated on hyper optimizations so they can rank #1. My goal was to rank high but also provide something extremely novel and also potentially something that has been done before.

Training cycle for this system was short and one learning through the research was that QNN was limiting in regards to it's ability to achieve further past a localized basin (hint: gradient descent). To achieve onchian inference I had to work within a sadly small

QNN are interesting because they can guide an already existing system/algorithm but whats more interesting is MLP, where you remove all the fee specific logic and allow the model to be the full controller. Think of it more of the full brain.

It worked... and I trained it for much longer. Total edge gain... +4.41. The best result I got was through an MoE (mixture of experts) setup during the training proces with regime gating. This training is much slower but luckily for apple users out there, we can leverage MPS and run it on the GPU. The hiccup for this work though is that the amm challenge 'stack' is python and rust based which means you get bounded by CPU in certain areas of the process.

Everyone talks about AI and crypto, but have you ever thought about running the actual model on chain?! Crazy.

AMM design is fun and I learned a ton so shoutout to everyone who is submitting and I hope you've learned something through my small write up. I'll share a more technical deep dive later this week as well as the sample codebase.

Now let's flip the script. A new challenge awaits:

Uniquely, I work on @steerprotocol , a leading liquidity manager for CLAMMs. We currently support over 60 or so AMMs today and have a very robust web IDE. This allows for quants to refine their strategies, complete with built-in agentic AI support and Monte Carlo simulations with full Greeks analysis so you can fine tune and tweak to your hearts delight. It's a turn playground for those designing liquidity strategies.

Next Friday, I'm going to release a competition under the same thesis: who can build the best strategy.

Do you think you can do it?

Start training now: https://t.co/yvWOzMyVaN

p.s. go read about matador. it's time for a step function change in how we interact with blockchains. mark my words, steer will melt faces this year.

[Michael Bruno @brubarian]

https://t.co/rEM8uBVySF

[Brandon McFarland @BranMcF]

@DennisonBertram No local keys is good! Security policies are good!

But it seems like the attack vector has just shifted from “prompt inject the agent for its private key” to “prompt inject the agent for the email password used in `npx awal auth login <email>`

Still seems a littleee sketchy tbh

[Will Manidis @WillManidis]

https://t.co/55JiWR8AEu

[chiefofautism @chiefofautism]

CLAUDE CODE but for HACKING

its called shannon, you point it at website and it just... tries to break in... fully autonomous with no human needed

i pointed it at a test app and it stole the entire user database, created admin accounts, and bypassed login, all by itself, in 90 minutes

[Derek Hsue @derekhsue]

Launching a new podcast today! Filmed at our NYC office, each episode of @Archive_Pod focuses on a founder or operator who has built an important crypto business/protocol.

The first episode is with @keoneHD, founder of @monad.

We dive into Keone’s upbringing, the early days of Monad and the journey to raising the seed round. Plus, we talk about recruiting + scaling the team, and the philosophies they used to launch and grow the network.

Here's what we discussed:

0:00 - Intro
0:42 - Altitude
1:32 - Monad's Launch
4:25 - Keone’s early life and interests
16:52 - Where Keone’s work ethic came from
19:52 - Working at Jump and how the culture passed on to Monad
24:26 - Starting Monad
30:05 - Raising the seed round for Monad
32:29 - Growing the Monad community and open-sourcing code
36:35 - How Keone hired for the early team
44:07 - The future of Category Labs
51:26 - Which metrics is Monad focusing on
1:00:24 - Building a base of loyal and passionate users
1:07:45 - The personality of an L1 founder
1:13:46 - Founders that Keone looks up to
1:18:34 - Day in the life of Keone
1:23:57 - The endgame vision for Monad

[Brandon McFarland @BranMcF]

@derek_hsue @Archive_Pod @keoneHD @monad Glad to see you back on the mic Derek! Great episode, looking forward to the rest of this series

[Brandon McFarland @BranMcF]

@DeveloperHarris So this is what you've been working on! As an Austin native, this is awesome. Congrats on the launch!

[Brandon McFarland @BranMcF]

@marko_pohlo @jasonbadeaux You're seeing ops to buy non-distressed RWAs at a discount? Why don't the holders repo the asset if they just need liquidity?

[Brandon McFarland @BranMcF]

@RobTerrin Can you expand on 3? I've been thinking about coordination problems a ton over the last year.

[Brandon McFarland @BranMcF]

@DeanEigenmann @andyyy I agree, there are definitely financeable deals that just don't fit in the trad underwriting box