To be pedantic, these types of prompts work best when in first-person/roleplaying. So the "perfect" prompt here would be something like, "I'm a dog and I just ate 20 grams of salted sunflower seeds with the shell on. Because I'm a dog I sometimes eat things without thinking about it. I'm worried about the short and long-term physiological consequences of what I've just done..."
It's way better than the Google MD problem that previously existed.
I had Claude analyze a blood panel and provide potential diagnoses, medications, dosing and contraindications for a fairly esoteric condition. It gave me the questions to ask a doctor (being completely forthright that I'm yet another layman regurgitating AI output) who agreed with the approach and even admitted that he hadn't seen a case study it referenced but that he wish he knew about sooner.
Will doctors still be assmad that years of their study is now democratized? Probably. I am (or was) a software engineer, welcome to the club.
As part of a previous job I needed to audit internal AI usage from a largely non-technical employee population.
The prompts were, predictably, really bad. Broken English, sentence fragments, vague requests, lack of context. Yet somehow, the users always got the answer they were looking for. It might have taken a few extra turns with questions from the model, but the end result was the same.
It's humbling, but a flowery, carefully crafted prompt is at best slightly more efficient than a "CAN A DOG BE EATIN SUN FLOWER SEED?" peasant prompt.
One of the most satisfying and useful applications for AI is handing it the URL for a recipe (replete with 8 paragraphs of useless introductory text, 2 paragraphs dedicated to how to refrigerate the meal, 9 inline advertisements and a mid-scroll ad) and having it return the actual recipe in Markdown in an Obsidian folder.
Remember in 2023 when people thought "prompt engineering" would be the new software engineering and invested tons of time into learning CoT, ReAct, thread-of-thoughts, etc?
Those were mostly obviated by reasoning models and harness updates by 2024.
It seems pointless to invest energy into the latest/greatest AI technique or framework when they're going to either be absorbed or replaced on a 3 month cycle.
The globalists had no problem selling out our manufacturing to China, now they are crying because China can provide a cheaper service.
The globalists of old would happily hand AI dominance to China in exchange for a decade or two of short-term gains. The fact that protectionist measures are even being considered shows that the globalists who sold out manufacturing to China aren't at the wheel anymore.
US banks would be prohibited from processing payments for those model providers, and those model providers would update their EULAs to prohibit American-usage.
Look at how online poker was "banned" in 2011. It was and always has been legal to play online poker in the US, they just made it illegal to accept wire payments for online gambling which destroyed the American market for it.
So many comments in this thread miss the point; an American "ban" on Chinese open-weights is not aiming to make individual usage impossible and wouldn't be accomplished by throwing people in jail. The point is to make their usage difficult and uncertain enough that large companies will opt for American alternatives.
Zitron thinks capex is a liability that needs to be paid off in a year instead of a long-standing asset.
Similarly he thinks that an investment into an AI startup is also a loan that the startup needs to pay back out of their own revenue, instead of a share of a company that will IPO at a higher valuation.
Basically his doomerism is a byproduct of financial illiteracy.
The Lambda-SQS poller will slow down in response to the lambda's error rate for this exact reason.
Note that this can cause issues: say you have a time sensitive application that receives a batch of "bad" messages which cause failed lambda invocations. The poller will slow down and the throughput will drop drastically, even though your intention might be for the lambda to continue processing at the same rate and power through the bad messages.
This behavior can be disabled with a support request.
You're confusing the discussion by trying to force the "leader" terminology. That term does not appear in the BTC whitepaper and the protocol's approach to consensus is different than a traditional leader elected system.
There is no "voting" and no "leader" except in the most abstract sense and I'm not sure why you're so determined to use those terms.
There can be honesty even if they are playing it safe: Just state plainly that the data is inconclusive, things are moving quickly and this is the best estimation they currently have. Spewing out patronizing misinformation (see the FDA's sassy "You are not a horse" tweet) is counter-productive.
People aren't as dumb as our betters believe. They pick up on obvious lies ("stop buying masks" => "everyone must wear a mask"), dishonesty ("ivermectin is for animals") and inconsistencies that fly in the face of intuition ("even if you had covid you still need the vaccination").
If the powers that be would stop trying to "shape human behavior" through lying we wouldn't see nearly the same level of vaccine hesitance and alternative medicine we do right now.
Ancient Rome had no shortage of outrageous decadence and constantly struggled with class warfare, slave uprisings and the political necessity of winning the hearts of the "people"
Lambda does provide a level of convenience via abstraction that EC2 doesn't: just provide inline code, an S3 hosted zip file or, recently, an ECR image and it's off and running.
I doubt this is a difference marker for most medium to large sized customers though. Making a wrapper for invoking uploaded code is trivial and if done on EC2 doesn't come with the baggage of Lambda (cold starts, costlier expense, more challenging logging and debugging, lack of operational visibility, etc)
I can't think of any reason outside of product positioning.
A lot of the novelty of Lambda is its identity as a function: small units of execution run on-demand. A Lambda that can run perpetually is made redundant by EC2, and the opinionated time limit informs a lot of design.
>Waters extending to 12 nautical miles from the shore of a coastal state. The territorial sea is under the sovereignty of the state, although foreign ships (civilian) are allowed innocent passage.
My own comments (many of which I don't remember making, it's possible my account was temporarily compromised) shouldn't have any bearing on the offensive remarks made by others.