I saw somewhere that you guys had All Hands where juniors were prohibited from pushing AI-assisted code due to some reliability thing going on? Was that just a hoax?
> Much of the coverage of the service incidents has focused on a weekly Amazon Stores operations meeting and a planned discussion of recent outages. Reviewing operational incidents is a routine part of these meetings, during which teams discuss root causes with the goal of continuing to improve reliability for customers.
This is something that's a part of every FAANG afaik. I know for a fact that there's no prohibition on pushing AI-assisted code. How would that even technically work? It'd basically mean banning Kiro/CC from the company.
> Only one of the incidents involved AI-assisted tooling, which related to an engineer following inaccurate advice that an AI tool inferred from an outdated internal wiki, and none involved AI-written code.
and this doesn't seem as "AI caused outage" as it was portrayed.
Not a hoax, saw it in the news. I'm not at Amazon but can confirm massive productivity gains. The issue is reviewing code. With output similar to a firehose of PR's we need to be more careful and mindful with PR's. Don't vibe code a massive PR and slap it on your coworkers and expect a review. The same PR etiquette exist today as it did years ago.
> You should start a new session for the code review to make sure the context window is not polluted with the work on implementation itself.
I'm just a sample size of one, but FWIW I didn't find that this noticably improved my results.
Not having to completely recreate all the LLM context neccessary to understand the literal context and the spectrum of possible solutions (which the LLM still "knows" before you clear the session) saves lots of time and tokens.
Interesting, I definitely see better results on a clean session. On a “dirty” session it’s more likely to go with “this is what we implemented, it’s good, we could improve it this way”, whereas on a clean session it’s a lot more likely to find actual issues or things that were overlooked in the implementation session.
The situations are not comparable at all. That was the collapse of an authoritarian (wasn’t totalitarian anymore by the time it’d collapse) system running (badly) on command economy. Most of the points you mention are therefore just really off.
Say, the Baltics flipping. Where the hell are we supposed to flip to? Russia? Where ethnic minorities are sent to die in expansionist wars in disproportionate numbers?
I believe OP was referring to Baltics flipping from USSR to the West (the EU). Some US analogues might include Canada flipping (already happening), no more coups in South American countries that vote in a "wrong" government, or the Middle Eastern countries allying with China (no longer impossible).
Good lord, Canada is not "flipping" anywhere. We've always had trade with China, and the US to this day has far more trade with China! We're the same we've always been, it's the US that has gone bananas, and decided to threaten annexation and purposeful economic collapse.
As a result, we've just stopping traveling, and as a country, buying from the US. We're sourcing 100+ billion over the next few years from other Western allies, not China.
That's not flipping anything. We always bought from other Western nations and allies in the past. We're just doing more of that, because, you know, you guys have turned into back stabbing asshats, who stab their friends in the back.
You may wonder the reaction, but your statement (while I'm sure was just meant as an observation) is quite harsh to take. Imagine if a friend tries to steal your car, then later calls you unloyal if you don't trust them. You'd be baffled.
With all due respect. If _any idiot_ can prompt their way to the _same_ software you’d have written, and your primary value proposition is to churn out code, then you’re… a bit of an outlier when it comes to principal engineers.
https://hackmyclaw.com/
reply