Ben Casnocha wrote up 16 lessons he learned from Reid Hoffman after having spent years with Hoffman as his chief of staff.

Here's a portion of one:

Speed

His first principle is speed. His most tweeted quote ever is, “If you aren’t embarrassed by the first version of your product, you shipped too late.” His second most tweeted quote ever is, “In founding a startup, you throw yourself off a cliff and build an airplane on the way down.”

Practically, he employs several decision making hacks to prioritize speed as a factor for which option is best—and to speed up the process of making the decision itself. When faced with a set of options, he frequently will make a provisional decision instinctually based on the current information. Then he will note what additional information he would need to disprove his provisional decision and go get that. What many do instead – at their own peril – is encounter a situation in which they have limited information, punt on the decision until they gather more information, and endure an information-gathering process that takes longer than expected. Meanwhile, the world changes.

If you move quickly, there’ll be mistakes borne of haste. If you’re a manager and care seriously about speed, you’ll need to tell your people you’re wiling to accept the tradeoffs. Reid did this with me. We agreed I was going to make judgment calls on a range of issues on his behalf without checking with him. He told me, “In order to move fast, I expect you’ll make some foot faults. I’m okay with an error rate of 10-20% — times when I would have made a different decision in a given situation – if it means you can move fast.” I felt empowered to make decisions with this ratio in mind—and it was incredibly liberating.

Speed certainly matters to an extreme degree in a startup context. Big companies are different. Reid once reflected to me that the key for big companies like LinkedIn is not to pursue strategies where being fastest is critical—big companies that adopt strategies that depend on pure speed battles will always lose. Instead, they need to devise strategies where their slowness can become a strength.

Here's another:

When there’s a complex list of pros and cons driving a potentially expensive action, Reid seeks a single decisive reason to go for it—not a blended reason. For example, we were once discussing whether it’d make sense for him to travel to China. There was the LinkedIn expansion activity in China; some fun intellectual events happening; the launch of The Start-Up of You in Chinese. A variety of possible good reasons to go, but none justified a trip in and of itself. He said, “There needs to be one decisive reason. And then the worthiness of the trip needs to be measured against that one reason. If I go, then we can backfill into the schedule all the other secondary activities. But if I go for a blended reason, I’ll almost surely come back and feel like it was a waste a time.” He did not go on the trip. If you come up with a list of many reasons to do something, Nassim Taleb once wrote, you are trying to convince yourself—if there isn’t one clear reason, don’t do it. (An analogous belief Reid has about consumer internet business models: there’s generally one main business model. Listing a blend of possible revenue streams makes investors nervous. LinkedIn is the exception that proves this rule!)

One last gem:

12. Trade up on trust even if it means you trade down on competency.

Should you start a company with friends? All things being equal, Reid says yes, because you can move more quickly with trusted friends because you already understand how each other thinks and talks. And moving quickly? That’s critical in the early days of a startup.

But what if all things aren’t equal? If you’re choosing between working with someone who’s a trusted friend and a 7 out of 10 on competence, versus a stranger who’s a 9 out of 10 on competence, who should you pick? Answer: if the trusted friend is a fast learner, pick the trusted friend.

Trade up on trust, even if it means you have to trade down on competency a bit. In other words, choose to work with someone you know who’s a fast learner over someone who’s a bit more qualified who you do not know. Assuming the person you know and trust is in Permanent Beta, he or she can round out their gaps in skills or experience in short order.

As with sports, organizations need to be aligned in both principle and process for any particular strategy to work. Some baseball teams are more analytically driven than others, but that matters little if you can't translate analytical recommendations into on-field execution. The Tampa Bay Devil Rays seemed to be a paragon of such top to bottom alignment in recent years, one reason I'm excited Joe Maddon has moved over to manage the Cubs.

If your organization is in a position where speed matters above all else but management beats the team up over errors you'd expect them to make moving at such a pace, something will give. Nitpick people to death and don't be shocked when they suddenly move much more slowly than you'd want.