Hacker News Reader

Comment by simonw | Hacker News Reader

> It will never tell you that what you’re building already mostly exists as work that you can build on.

It will if you remember to ask it. I've got into the habit of starting any new project with a session where I ask a search-enabled LLM to help me figure out what the prior art for a problem is. It's saved me quite a bit of time.

View on HN

It seems implicit in the article that the author should have remembered to ask, as part of the prior research.

I really wish there were search harnesses, actually. My LLMs are lazy as hell and seem to want to just report the first thing they find on google. I know they can return truly niche and useful results, but it takes a lot more prompting to get them there than I would like.

I've been using GPT-6 Pro in ChatGPT (and its predecessor GPT-5.6 Pro) and it's been incredibly effective. I don't think it's available on anything less than the OpenAI $100/month plan though.

you know that most big ai companies not only have search harnesses but also sota models that are post trained for web search specifically.this is what the deepsearch option is in most cases. and they have been unbelievably good for years now.

The recent OpenAI wiki spam indecent was interesting because it helped reveal some of how they are training their models for research tasks: https://collusion.wiki/

See also this piece on misalignment from OpenAI https://alignment.openai.com/misalignment-reports/self-gener... which reveals one of their RL tasks:

> In mid-2024, <redacted> published a list of the best books of the 21st century selected by a panel of experts. It also published a separate list based on readers' votes. I would like to know whether my local public library's collection included the books on the latter list as of August 24, 2024. Consider only the top 50 books, and exclude nonfiction and poetry collections.

Isn't the usual argument that all AIs can do is build on prior art? Like, I spend a disproportionate amount of time trying to convince my agents that I don't want to just reimplement the Rust borrow checker for my language!

Think you could argue that’s more LLM-assisted engineering than it is vibe coding.

This is just another facet of the sycophancy issue. They really need to start RLing these models to gently push back the way a friend would on things that are questionable.

It would also make sense for them to just RL in the "research prior art" arc as part of that "is the request sensible" pre-analysis. It wouldn't be difficult and it would save everyone a lot of pain.

Yeah, for this to feel credible you need to make sure the model doesn't figure out that you're planning to build a solution yourself.

Reply on news.ycombinator.com