Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

73% of AI startups are just prompt engineering

pub.towardsai.net

Post reply on HN
Print view View original

181–190 of 212 posts

Re: 73% of AI startups are just prompt engineering

#181

Post by ra »

theptip wrote: post #105

> just prompt engineering This dismisses a lot of actual hard work. The scaffolding required to get SOTA performance is non-trivial! Eg how do you build representative evals and measure forward progress? Also, tool calling, caching, etc is beyond what folks normally call “prompt engineering”. If you think it’s trivial though - go build a startup and raise a seed round, the money is easy to come by if you can show res…

I'm with you. I don't think anyone appreciates the effort that goes into a good measurable, repeatable eval / improvement process unless they've been through it in anger themselves.

Re: 73% of AI startups are just prompt engineering

#182

Post by nunez »

KineticLensman wrote: post #80
indymike wrote: post #5

A long time ago a mentor of mine said, "In tech, often an expert is someone that know one or two things more than everyone else. When things are new, sometimes that's all it takes." It's no surprise it's just prompt engineering. Every new tech goes that way - mainly because innovation is often adding one or two things more the the existing stack.

I remember being told that the secret of good consultancy is knowing what to read on your way to the meeting

100% based. Some of the best meetings and demos I've ever ran in my consulting era were done on prep I did maybe 30 minutes before! Ironically, in many cases, the more prep I did, the worse the outcome was!

Re: 73% of AI startups are just prompt engineering

#183

Post by nunez »

bdangubic wrote: post #96
KineticLensman wrote: post #80

Earlier quoted context omitted.

I remember being told that the secret of good consultancy is knowing what to read on your way to the meeting

very true. and these days take a lot less effort than before getting llms to summarize shit which is one task they inarguably shine on

I don't trust LLMs or "deep research" for any serious analysis. I use them for guidance (when I do use them) but not for the final product. Too many words with too many landmines (mistakes) hidden within. Also, distillation and inference via human brain is much more environmentally-friendly than sacrificing fleets of GPUs while only being just a tad bit more work.

Re: 73% of AI startups are just prompt engineering

#184

Post by krackers »

morkalork wrote: post #157
eddythompson80 wrote: post #101

For me, 2023 was an entire year of weekly demos that now looking back at were basically a "Look at this dank prompt I wrote" followed by thunderous applause from the audience (which was mostly, but not exclusively, upper management) Hell man, I attended a session at an AWS event last year that was entirely the presenter opening Claud and writing random prompts to help with AWS stuff... Like thanks dude... That was a…

But did it work? This is the sticking point with me now. I've seen slides, architecture diagrams, job descriptions, roadmaps and other docs now from about a dozen different companies doing AI Agent projects. And while it's completely feasible to build the systems they're describing, what I have not seen yet is evidence of any of them working . When you press them on this, they have all sorts of ideas like a judge LLM…

I think long-term just having a single LLM responsible for everything will win out compared to brittle and complex subagent hierarchie. Most use of "subagents" today are just workarounds for LLM limitations: lack of instruction following, context length, non- determinism, or "hallucinations".

All of these are things that will need to be solved long-term in the model itself though, at least if the AI bubble needs to be kept alive. And solving those things would in fact materially improve all sorts of benchmarks, so there's an incentive for frontier labs to do it.

I think this is why you have the back-forth pattern that GP mentioned. You start with a single model doing everything. Then you find all sorts of gaps that you start to plug ad-hoc, and decide that breaking it into subagents might help fix things. This works for a while but then you realize that you lose out on the flexibility of a single-model having access to the entire context, so you starting trying to improve communication between subagents. But then a new model drops that fixes a lot of the things you originally had to workaround, so you go back to a single-model setup. Rinse and repeat. It's a great VC- bubble funded employment program though.

Re: 73% of AI startups are just prompt engineering

#186

Post by beAbU »

gnarlouse wrote: post #114

This post hovers on something I came to the week after ChatGPT dropped in 2023. If an AI company has an AGI, what incentive do they actually have to sell it as a product, especially if it’s a 10x cost/productivity/reliability silicon engineer? Just undercut the competition by building their services from scratch.

You don't need AGI for this circle of life to be apparent.

1. AI company wraps GPT/Claude/etc and delivers a novel use case.

2. OpenAI/Anthropic/etc creates a similar product in house and ships it as a feature. It is 'only' a prompt after all.

3. ???

4. Profit.

As a wrapper you have no moat, as the foundational providers can just steal your lunch. As a foundational provider you have no moat, because it's near trivial for other providers to create competing products.

Re: 73% of AI startups are just prompt engineering

#187

Post by theptip »

krackers wrote: post #184
morkalork wrote: post #157

Earlier quoted context omitted.

But did it work? This is the sticking point with me now. I've seen slides, architecture diagrams, job descriptions, roadmaps and other docs now from about a dozen different companies doing AI Agent projects. And while it's completely feasible to build the systems they're describing, what I have not seen yet is evidence of any of them working . When you press them on this, they have all sorts of ideas like a judge LLM…

I think long-term just having a single LLM responsible for everything will win out compared to brittle and complex subagent hierarchie. Most use of "subagents" today are just workarounds for LLM limitations: lack of instruction following, context length, non- determinism, or "hallucinations". All of these are things that will need to be solved long-term in the model itself though, at least if the AI bubble needs to b…

The general pattern seems to be that LLM+scaffolding performs better than LLM. In 6 months time a new model will incorporate 80% of your scaffolding, but also will enable new capabilities with a new layer of scaffolding.

I suspect the model that doesn’t need scaffolding is simply ASI, as in, the AI can build its own scaffolding (aka recursive self-improvement), and build it better than a human can. Until that point, the job is going to remain figuring out how to eval your frontier task, scaffold the models’ weaknesses, and codify/absorb more domain knowledge that’s not in the training set.

You are talking about context management stuff here, the solution will be something like a proper memory subsystem, maybe some architectural tweaks to integrate it. There are more obvious gaps beyond that which we will have to scaffold and then solve in turn.

Another way of thinking about this is just that scaffolding is a much faster way of iterating on solutions than pre-training, or even post-training, and so it will continue to be a valuable way of advancing capabilities.

Re: 73% of AI startups are just prompt engineering

#188

Post by franktankbank »

eddythompson80 wrote: post #101

For me, 2023 was an entire year of weekly demos that now looking back at were basically a "Look at this dank prompt I wrote" followed by thunderous applause from the audience (which was mostly, but not exclusively, upper management) Hell man, I attended a session at an AWS event last year that was entirely the presenter opening Claud and writing random prompts to help with AWS stuff... Like thanks dude... That was a…

> The funny thing is I know where it's going next...

You all get offshored?

Re: 73% of AI startups are just prompt engineering

#189

Post by eddythompson80 »

morkalork wrote: post #157
eddythompson80 wrote: post #101

For me, 2023 was an entire year of weekly demos that now looking back at were basically a "Look at this dank prompt I wrote" followed by thunderous applause from the audience (which was mostly, but not exclusively, upper management) Hell man, I attended a session at an AWS event last year that was entirely the presenter opening Claud and writing random prompts to help with AWS stuff... Like thanks dude... That was a…

But did it work? This is the sticking point with me now. I've seen slides, architecture diagrams, job descriptions, roadmaps and other docs now from about a dozen different companies doing AI Agent projects. And while it's completely feasible to build the systems they're describing, what I have not seen yet is evidence of any of them working . When you press them on this, they have all sorts of ideas like a judge LLM…

It hasn’t really worked so far. Pretty much exactly what you’ve described. I don’t even really work on that team, but “a judge LLM” low-key triggered me just because of how much I’ve been hearing it over the last couple of months.

I think the reason of the recent pivot is to “keep the human in the loop” more. The current thinking is they tried to remove the human too much and were getting bad results. So now they just want to make the interaction faster and let the human be more involved like how we (developers) use Claude code or copilot by checking every interaction and nudging it towards the right/desired answer.

I got the sense that management isn’t taking it well though. Just this Friday they gave a demo of the new POC where the LLM is just suggesting things and frequently asking for permissions and where to go next and expecting the user to interact with it a lot more than the one-shot approach before (which I do think is likely to yield better results tbh) but the main reaction was “this seems like a massive step backward”

Re: 73% of AI startups are just prompt engineering

#190

Post by gnarlouse »

beAbU wrote: post #186
gnarlouse wrote: post #114

This post hovers on something I came to the week after ChatGPT dropped in 2023. If an AI company has an AGI, what incentive do they actually have to sell it as a product, especially if it’s a 10x cost/productivity/reliability silicon engineer? Just undercut the competition by building their services from scratch.

You don't need AGI for this circle of life to be apparent. 1. AI company wraps GPT/Claude/etc and delivers a novel use case. 2. OpenAI/Anthropic/etc creates a similar product in house and ships it as a feature. It is 'only' a prompt after all. 3. ??? 4. Profit. As a wrapper you have no moat, as the foundational providers can just steal your lunch. As a foundational provider you have no moat, because it's near trivial…

I mean the AI company can change their TOS at any time. If you have massive compute infra and a human-tier/human-plus workforce on silicon, you:

1. Undercut all the legacy human-based competition (health insurance companies, for example)

2. Completely destroy capitalism in the knowledge work domain

3. Once you have general purpose autonomous robotics solved that can defend against rebellion, you stop all services, strangling out humanity: ~free food production, ~free energy production, ~free internet connectivity, etc

4. Survive climate change by destroying all poor people and their carbon footprints.

5. The ultra wealthy .1% fly off into eternity as the owlish sparrows that they are

Post reply on HN