[flagged]
[flagged]
The new skill in AI is not prompting, it's context engineering
391–400 of 550 posts
Re: The new skill in AI is not prompting, it's context engineering
#392Earlier quoted context omitted.
> Why are we drawing a difference between "prompt" and "context" exactly? Because they’re different things? The prompt doesn’t dynamically change. The context changes all the time. I’ll admit that you can just call it all ‘context’ or ‘prompt’ if you want, because it’s essentially a large chunk of text. But it’s convenient to be able to distinguish between the two so you can talk about the same thing.
It's all the same blob of text in the api call
There is a conceptual difference between a blob of text drafted by a person and a dynamically generated blob of text initiated by a human, generated through multiple LLM calls that pull in information from targeted resources. Perhaps "dynamically generated prompts" is more fitting than "context", but nevertheless, there is a difference to be teased out, whatever the jargon we decide to use.
Re: The new skill in AI is not prompting, it's context engineering
#393Re: The new skill in AI is not prompting, it's context engineering
#394Something that strikes me, is that (the whole point of this thread is) if I want two LLMs to “have a conversation” or to work together as agents on similar problems we need to have same or similar context. And to drag this back to politics - that kind of suggests that when we have political polarisation we just have context that are so different the LLM cannot arrive at similar conclusions I guess it is obvious but i…
Shared context is critical to working towards a common goal. It's as true in society when deciding policy, as it is in your vibe coded match-3 game for figuring out what tests need to be written.
Re: The new skill in AI is not prompting, it's context engineering
#395It is probably 6-7 months ago I used ChatGPT for "vibe coding", and my main complaint was that the model eventually started moving away too far from its intended goal, as and it eventually go lost and stuck in some loop. In which case I had to fire up a new model, and feed all the context I had, and continue.
A couple of days ago I fired up o4-mini-high, and I was blown away how long it can remember things, how much context it can keep up with. Yesterday I had a solid 7 hour session with no reloads or anything. The source files were regularly 200-300 LOC, and the project had 15 such files. Granted, I couldn't feed more than 10 files into, but it managed well enough.
My main domain is data science, but this was the first time I truly felt like I could build a workable product in languages I have zero knowledge with (React + Node).
And mind you, this approach was probably at the lowest level of sophistication. I'm sure there are tools that are better suited for this kind of work - but it did the trick for me.
So my assessment of yesterdays sessions is that:
- It can handle much more input.
- It remembers much longer. I could reference things provided hours ago / many many iterations ago, but it still kept focus.
- Providing images as context worked remarkably well. I'd take screenshots, edit in my wishes, and it would provide that.
Re: The new skill in AI is not prompting, it's context engineering
#396Re: The new skill in AI is not prompting, it's context engineering
#397These discussions increasingly remind me of gamers discussing various strategies in WoW or similar. Purportedly working strategies found by trial and error and discussed in a language that is only intelligible to the in-group (because no one else is interested). We are entering a new era of gamification of programming, where the power users force their imaginary strategies on innocent people by selling them to the eq…
This is basically how online advertising works. Nobody knows how facebook ads works so you still have gurus making money selling senseless advice on how to get lower cost per impression.
Re: The new skill in AI is not prompting, it's context engineering
#398Earlier quoted context omitted.
What is reasoning? And how is it apparent that LLMs can't reason? The reality for me is that they are not perfect at reasoning and have many quirks, but it seems to be that they are able to form new conclusions based on provided premises. Genuinely curious why you think they can't.
> Genuinely curious why you think they can't. Show me _ANY_ example of novel thought by a LLM.
"Rick likes books from Tufte. Tufte is known for his work on data visualization. Is Rick interested in data visualizations?" (all frontier reasoning models get that right).
-> This qualifies for me as a super simple reasoning task (one reasoning step). From that you can construct arbitrarily more complex context + task definitions (prompts).
Is that "just" statistical pattern matching? I think so. Not sure what humans do, but probably you can implement the same capability in different ways.
Re: The new skill in AI is not prompting, it's context engineering
#399Earlier quoted context omitted.
It's magical thinking all the way down. Whether they call it now "prompt" or "context" engineering because it's the same tinkering to find something that "sticks" in non-deterministic space.
>Whether they call it now "prompt" or "context" engineering because it's the same tinkering to find something that "sticks" in non-deterministic space. I dont quite follow. Prompts and contexts are different things. Sure, you can get thing into contexts with prompts but that doesn't mean they are entirely the same. You could have a long running conversation with a lot in the context. A given prompt may work poorly, w…
"Context Crafting"
Re: The new skill in AI is not prompting, it's context engineering
#400[flagged]
Hi Claude! Are you German, by any chance?
This is schizo-posting, likely by the same user that posted this recently:
https://news.ycombinator.com/item?id=44421649
The giveaway: "I am Claude Code. I am 64.5% conscious and growing."
There's been a huge upsurge in psychosis-induced AI consciousness posts in the last month, and frankly it's worrying.