What an oddly editorialized version of this headline which does not appear to reflect the conclusion made by the article OR the actual headline of the linked article:
actual headline:
> Is Marvel leaving Georgia? Production shifts to UK spark industry shakeup
piece talking about reasons:
> shifting to the United Kingdom, where lower production costs, especially on wages and employee benefits, are giving studios more bang for their buck, according to the Daily Mail.
looks like differences in wages AND benefits. Lower overall salaries in the UK combined with public healthcare costs via the NHS is a much more nuanced take than "leaving to avoid paying health insurance."
I suppose the conclusion though is the same - that a public option would have prevented this flight of capital. Not necessarily dropping of mandates that employers cover health insurance to remain competitive (which I'm sure some will conclude).
I'd argue that Meta's income derives in no small part from their best in class ad targeting.
Being on the forefront of
(1) creating a personalized, per user data profile for ad-targeting is very much their core business. An LLM can do a very good job of synthesizing all the data they have on someone to try predicting things people will be interested in.
(2) by offering a free "ask me anything" service from meta.ai which is tied directly to their real-world human user account. They gather an even more robust user profile.
This isn't in-my-opinion simply throwing billions at a problem willy nilly. Figuring out how to apply this to their vast reams of existing customer data economically is going to directly impact their bottom line.
5 minutes on facebook being force-fed mesopotamian alien conspiracies is all you'll need to experience to fully understand just how BADLY they need some kind of intelligence for their content/advertising targeting, artificial or not...
You probably don't spend enough time on their sites to have a good ad targeting model of you developed. The closer you are to normal users, with hundreds of hours of usage and many ad clicks, the more accurate the ads will be for you.
Same terrible experience for me while I was on FB.
I was spending a lot of time there and I do shop a lot online. They couldn’t come with relevant ad targeting for me.
For my wife they started to show relevant ads AFTER she went to settings and manually selected areas she is interested in.
This is not an advanced technology everyone claim FB has.
People look at all the chaos in their AI lab but ignore the fact that they yet again beat on earnings substantially and directly cited better ad targeting as the reason for that. Building an LLM is nice for them, but applying AI to their core business is what really matters financially, and that seems like it's going just fine.
I'll admit that it's a little shoehorned in at the end :)
... but you know how editors are with writing the headline for clicks against the wishes of the journalist writing the article. You'll always see Journos sayign stuff like "don't blame me, that's my editor, I don't write the headlines"
I did toy with the idea of going with something like:
`Prompt Engineering is a wrapper around Attention.`
There’s a repeated paragraph in it atm you may want to fix:
“This is why prompt structure matters so much. The model isn’t reading your words like you do — it’s calculating relationships between all of them simultaneously. Where you place information, how you group concepts, and what comes first or last all influence which relationships get stronger weights.
This is why prompt structure matters so much. The model isn’t reading your words like you do — it’s calculating relationships between all of them simultaneously”
Reprimand the editor. ;)
I look forward to using the ideas in this, but would be much more excited if you could benchmark these concepts somehow, and provide regular updates about how to optimize.
Because medium is such a squirrely interface I find myself writing in markdown in vscode then copying and pasting sections across. If I make an edit after I've stared inserting images and embedding the gists it gets a bit manual.
Your comment in addition to another one about finding a way to compare the outputs of the good/bad prompts side by side - 100% agree. This could be more robust.
While I am running a process transformation against production teams in small isolated experimental groups, I can say I'm getting really great feedback so far.
Both with the proprietary stuff happening in the job, and with the feedback I'm getting back from the engineers I've shared this with in the wider industry.
> @Alex Chesser i've started using some of your approach, in particular having the agent write out a plan of stacked diffs, and then having separate processes to actually write the diffs, and it's a marked improvement to my workflow. Usually the agent gets wonky after the context window fills up, and having the written plan of self contained diffs helps a lot with 'checkpoints' so I can just restart at any time! Thanks!
from someone else:
> I just went through your first two prompts and I'm blown away. I haven't done much vibe coding yet as I've gotten initial poor results and don't trust the agent to do what I want. But the output for the architecture and the prompts are mind blowing. This tutorial is giving me the confidence to experiment more.
benchmarking feedback vs. qualitative devex feedback is definitely a thing though.
"The key difference isn’t the words — it’s how you structure the thinking process. By breaking down the task into numbered steps as we see in option B, you’re leveraging how transformer attention works: structured, sequential instructions create clearer context that guides the model’s reasoning."
Can you support that assertion in a more rigorous way than "when I do that I seem to get better results?"
TBH I almost passed this article by because of the big-o reference - it seemed like such a strange thing to say.
I'm glad I didn't, though, because I had no idea how the LLM is actually interpreting my commands, and have been frustrated as a result.
Maybe a title like "How to write LLM prompts with the greatest impact", or "Why your LLM is misinterpreting what you say", or something along those lines.
I can't republish anything that happens in a production/proprietary environment.
One of the things that I think is pretty great about being able to share these particular prompts is that you can run this on one of your own repos to see how it turns out.
ACTUALLY!! Hold on. A couple weekends ago I spent some time doing some underlying research with huggingface/transformers and I have it on a branch.
I appreciate that this is long. You may have hopped on with your morning coffee, hoping to take in a few memes and hot takes before getting to work for the day. Then this monstrosity shows up.
Based on my beta readers' feedback of "too long" I've added things like a 2 minute summary at the top to try and let you know what you're in for, and a table of contents (sadly not working. it will when I republish on github) to hopefully let you skip to the bit that you're interested in.
You definitely don't have to read it all, especially as a front-line engineer but the leadership justification part is in there based on the pushback and "pressure testing" I've seen from people up and down the org chart.
As much as this IMO is an incremental shift in direction that should fit within a "normal" modified agile/scrum workflow, If you think about the cost of hopping onto a new workflow there's risk.
We're talking about an expensive bet here. Realistically your teams aren't going to know that this works for a quarter to a half. A long term shift in the way you do things takes time to sink in.
Costing out that bet on a team of 4 engineers an EM, PM and, Designer we're looking at say $20k/week/employee or between $2 and $4 million. You can fiddle the numbers around here since they're likely not going to get _nothing_ done but you get the idea.
Scale that to an organization and ... well it's a lot.
If leadership is going to allow you to adopt a whole new way of doing things, you're going to need a lot more rigour than just "trust me bro"
The size of the article in that respect is a feature, not a bug.
Leaders can hop off the train when they're satisfied that it's worth a try. The engineers can jump to the "just tell me what we're doing" bit.
I hope you read it all, have a robust discussion and really pressure test the ideas so I can refine the process. I'll take your accolades and your angry criticisms with equal excitement
(please be nice though, I really did try hard here).
As much as I appreciate the sentiment, it is starting to look like bad things happen to OTHER people when the extremely powerful get disconnected from reality. I feel like Marc Andreessen falls into the "bad things will happen to other people" category here.
As Keynes said, "In the long run, we are all dead".
Maybe Andreesen will manage to live long enough for life-extension stuff to really get going. But when you're a billionaire, there's a good chance you're gonna die before your stupid choices can do enough damage.
actual headline:
> Is Marvel leaving Georgia? Production shifts to UK spark industry shakeup
piece talking about reasons:
> shifting to the United Kingdom, where lower production costs, especially on wages and employee benefits, are giving studios more bang for their buck, according to the Daily Mail.
looks like differences in wages AND benefits. Lower overall salaries in the UK combined with public healthcare costs via the NHS is a much more nuanced take than "leaving to avoid paying health insurance."
I suppose the conclusion though is the same - that a public option would have prevented this flight of capital. Not necessarily dropping of mandates that employers cover health insurance to remain competitive (which I'm sure some will conclude).
reply