Been using @Muse and I'm pleastly surprised. Product intuition and taste are great, especially this early in the product. @alexandr_wang is bringing @Meta back from the dead.
1
73
Doughnut retweeted
Minimax H3 😀
-Advanced Prompting style
with micro-expressions + emotions
using tags and context for natural detailed output
full details in comment
Harnesses are the new software layer.
Harnesses often get dismissed as just scaffolding, just prompt engineering, and not real research. But that couldn't be farther from the truth. The same model weights that score 30% on ARC-AGI score 95% with a better harness.
So we gathered a group of researchers and founders working at the frontier to do a deep dive into the state of harnesses.
We cover how we got to this point, the case for making your harness as expressive as possible, and what YC learned building an agent for every employee in the company.
00:00 - @FrancoisChauba1: Why harnesses matter
04:27 - Building an auto-researcher by accident
07:13 - A five minute history of harnesses
13:56 - Self-improving harnesses
18:35 - @sethkarten: Prime Agent, a self-improving RLM harness
21:50 - Context as an L1, L2, L3 cache
24:51 - From Turing machine to von Neumann computer
28:33 - Messaging between agents
30:04 - ARC-AGI results
33:09 - Emulator Bench and GPU kernels
37:30 - @JonSaadFalcon: OpenJarvis, personal AI on personal devices
38:26 - How far behind are local models
39:21 - The five primitives of a personal AI stack
42:47 - Letting cloud models optimize your local stack
43:53 - 800x cheaper than the cloud
45:58 - @josh__france and @jbellregan: QM, YC's agent harness for work
47:29 - A history of YC's internal agents
49:24 - OpenClaw and a fleet of 50 agents
51:04 - Pulling the brain out of the sandbox
54:43 - Letting the agent choose its own sandbox and model
57:16 - The grind tool: budgets on goals
58:50 - Agents don't understand social context
1
105
To be a well respected ceo, you must make absurd predictions about what the next 6 months to 5 years will look like.
34
The same group that lost tons of investor money during the crypto days are repeating they're play in physical AI.
40
Surprised.
Relay, which offered businesses workflow automation, will stop operating next month. Its CEO and some of its staff plan to get to work on Google Chrome next.
spr.ly/6014B1bHL4
77
Doughnut retweeted
Relay, which offered businesses workflow automation, will stop operating next month. Its CEO and some of its staff plan to get to work on Google Chrome next.
spr.ly/6014B1bHL4
this is a golden moment for engineers. there are many raw engineering problems you can work on that don't require you to think about the customer or taste much. i suspect that will change eventually.
35
At scale autonomous AI systems are undesirable for enterprise in every way. Process exist to reduce autonomy.
50
Doughnut retweeted
“It’s nootropic interstellar-travel-as-a-service with a strong moat”
🤖 Made with AI
What happens if the AI payoff takes longer than consensus assumes?
This question is less about AI, its about timing and the underlying capital stack that has enormous exposure across the economy
apollo.com/wealth/insights-n…
31