Some reference code if you want to throw your agent at it. https://github.com/rapatel0/rq-models

150M is small in comparison to the 20B he overpaid by. Investors were well compensated.

The RyanAir CEO was even quoted that he expected some tickets to be come "zero-fare" Link: https://www.theguardian.com/business/2016/nov/22/ryanair-fli...

The point stands, airlines don't make money on flights. Flights are loss leaders.

So if they tend to compete themselves into oblivion, or need to turn into banks to subsidize their product, then it might make sense that they should be regulated monopolies.

Still you're probably right, if they can turn into banks and stay profitable, then maybe that's a better market outcome overall.

I'm not saying that this a better outcome (power companies have their problems too). I was just commenting that this issue parallels the historical solution that was applied to utility companies.

Unless this initiative will turn into a credit card company (which nobody likes or wants to do) it won't go anywhere

Private equity will likely sell the company for parts. There is no operational improvements for cash flow that they can do.

Useful watch (skip to 2:20): https://youtu.be/ggUduBmvQ_4?si=cyysP7aH_CIEDZRq

"Before SpaceX, launching rockets was costly because industry practice used expensive materials and discarded rockets after one use. Elon Musk applied first-principles thinking: What is a rocket made of? Mainly aluminum, titanium, copper, and carbon fiber. Raw material costs were a fraction of finished rocket prices. From that insight, SpaceX decided to build rockets from scratch and make them reusable."

Everything including humans are made of cheap materials but that doesn't convey the value. The AI got close to the answer with it's first sentence (re-usability) but it clearly missed the mark.

Experience, success, credentials none of it matters anymore. The left thinks everything on the right is stupid and evil, the right does the same, and everyone drinks their own kool aid.

We’ve all stopped listening.

The article walks through the coordination patterns to address types of error:

- Single-writer: one agent writes, others review read-only. Eliminates oscillation. Maps to the single-writer principle from concurrent systems.

- Sequential planning: parallel planners cluster even across different models. Sequential divergence acts as a covering algorithm — 3 sequential planners explore more than 5 parallel.

- Sequential vs parallel review: parallel voting catches common issues (mean quality). Sequential review compounds scrutiny but risks scope creep. Both are useful.

- Human interview gating: open-ended questions yield ~5x more useful context than closed ones. "REST or GraphQL?" vs "What should we know about how this API will be consumed?"

- Adversarial validation: separate environment, separate agent, explicit goal of breaking the application. Tests the spec, not the implementation.

Hope it's useful reading

Comments URL: https://news.ycombinator.com/item?id=47606164

Points: 1

# Comments: 1

Normal:

  L1 -> L2 -> L3 -> L4 -> out

  L1 -> [L2->L3] -> [L2->L3] -> L4 -> out

       --<--loop----
       |           |

  L1 -> [L2->L3] x N --> L4 -> out

Note: ascii rendering HN is not trivial

Have you tried a simple inline loop over the duplicated layers? Would be interesting to see performance. Also, would be interesting to compare with a MOE model. See if these layers are acting like different agreeing "experts" or if there is reasoning happening in the latent space.