> "..when I finally pushed for bigger scope at Amazon. My manager’s initial reaction wasn’t excitement. It was something closer to “But you’re doing so well where you are.”", most managers generally push their devs to always be doing larger pieces of work, if they aren't, that's weird.
From the business perspective, it may not be good to push. If they are really good at what they currently do, the manager would need to find a replacement, and there is no certainty that the old worker provides more value in the different job. When only the money is weighted, this will happen often. Seems to fit for Amazon's work culture.
The problem is bored employees find a new job elsewhere. Employees who feel they are not valued find a new job elsewhere. If you can find them a new job in the company you can have them train their replacement - years later the replacement can ask "do you remember why you did...". It also means if the old project has an emergency you have a bunch of people who can jump in much faster - to some extent this adding people to a late project won't make it latter (only some extent, it isn't perfect).
People also get old and retire (or die). By moving people around a bit you ensure that your training plan still works because you are using it. This also means there will be openings to move up the ladder, make sure you get the people on them. (There are stories from my company where after a big layout they got scared and hired almost nobody for the next 20 years, then those who made it passed the layoffs started retiring and there wasn't a mid level of engineers following to promote).
> The problem is bored employees find a new job elsewhere.
But this one didn’t. 20 years at one place, at least 10 with minimal support. Maybe all those managers were bad; but maybe they realized this individual wasn’t a flight risk, and had a reasonable strategy for maximizing what they got out of them, since they knew they didn’t have to guard against departure.
Are they going to pay back if subscription was payed but token limit was less than advertised? Is there some tiny text somewhere preventing just suing or pulling money back with credit cards?
Part of the issue is that they don't actually advertise what the token limit is. Just some vague, "this is 5x more than free, and 5x more than pro". They seem to be free to change the basis however they please, because most of us are more than happy to use what they give us at the discounted subscription pricing.
> Setting min-release age to 7 days is great, but the only true way to protect from supply chain attacks is restricting network access.
Getting zero day patches 7 days later if no proper monitoring about important patches or if this specific patch is not in the important list. Always a tradeoff.
Thats true. Setting to 7 days saves you from a supply chain attack, but opens you to zero days. Another example why network filtering is a better solution.
It is harder and harder to trust any blog post anymore, the more AI there is. I used to read blog posts because of the personality and the precision level. Now both have been taken away.
The output is also very manipulative in order to keep you using it. They want you to feel good. I don't use ChatGPT at all anymore, as it is misleading too badly. But it will work for masses as it worked with Facebook/Instagram etc.
Having to continually keep it "on task" is exhausting.
ChatGPT: If you want I can make a full list of 100 examples with definitions in alpahbetical order.
Me: What was the original context I gave you about suggestions?
ChatGPT: You instructed me: do not give suggestions unless you explicitly ask for them.
Me: and what did you just do?
ChatGPT: I offerred a suggestion about making a full list of 100 examples, which goes against your instruction to only give suggestions when explicitly asked.
Me: Does that make you a bad machine or a good machine?
ChatGPT: By your criteria that makes me a bad machine, because I disobeyed your explicit instruction.
But hey, all that extra engagement; no value but metrics juiced!
It is not worse I would say. It uses neutral system prompt by default, whereas Gemini and ChatGPT will please you too much to mislead you badly. Also the base search is much batter. You can control the search while with Gemini, for example, you can't.
From the business perspective, it may not be good to push. If they are really good at what they currently do, the manager would need to find a replacement, and there is no certainty that the old worker provides more value in the different job. When only the money is weighted, this will happen often. Seems to fit for Amazon's work culture.
reply