Live data from Hacker News

I accidentally turned LLM memory into program analysis

pwning.systems

81–88 of 88 posts

Re: I accidentally turned LLM memory into program analysis

#81
post #68

I reached a similar conclusion: LLMs should only really sit at the terminals of request fulfilment. 1. User request understanding: natural language -> a more rigorous representation, in my case Datalog. 2. Result interpretation: facts and derived facts -> natural language. Between those terminals, the work should be mechanical reasoning over some ontology or formal knowledge structure. That connects to another princi…

What you call "Weathering" has been a constant gripe of mine. We have LLM-driven softwares toward that almost seem to start from scratch every time a request comes in - there are mechanisms to learn or generalize, like writing out a memory, but they are not reliable or reliable in general. There is no convenient lever to be able to say "yes this is in the memory but the request seems like it needs a fresh scan of dat…

I’ve been thinking about this.. the same idea behind Dynamic cheat sheets paper and the ACE paper. Thanks for those links! Nice to see those ideas academically studied.

My problem is the context of today’s models (that I’ve been using - Claude Opus 5 and GPT-Sol) are a black box to a user like me. I cannot tell what they already hold in their context over the duration of a coding session. I cannot tell influencers a little by using/not using MCP tools, AGENTS.md like MD files, but what they _actually_ use at inference time is still opaque.

For example, if I insist that GPT-Sol use a size bounded dynamic cheat sheet for my project, and even have those reflector&curator agents refine them concurrently, what is to say GPT-Sol doesn’t have an intrinsic cheat sheet like that already, and it is just reading/curating/managing this one in addition and only getting confused needlessly along the way?

Similarly, all those codegraph like tools and semantic search addons.. what is to say the model genuinely uses them instead of relying on its own inference techniques and just “perform” for the user audience as if they are using these fancy tools?

This is not to say we shouldn’t try more ways of managing context and just give up to our AI provider overlords. Just thinking through the logic of what we are working with.

Re: I accidentally turned LLM memory into program analysis

#83
That’s practically what i’m working on! But i’m training the models to do this natively. It gets complex given the inherent relevant uncertainties (aka making it resilient to their bullshit). Luckily, datalog and monotonic logic in general is reasonably amenable to packed representations of the possible knowledge bases, and reasoning from them in a way that lends itself to decent UX, but it’s been a huge amount of elbow grease to get working with reasonable complexity end-to-end.

Re: I accidentally turned LLM memory into program analysis

#84
post #68

Earlier quoted context omitted.

What you call "Weathering" has been a constant gripe of mine. We have LLM-driven softwares toward that almost seem to start from scratch every time a request comes in - there are mechanisms to learn or generalize, like writing out a memory, but they are not reliable or reliable in general. There is no convenient lever to be able to say "yes this is in the memory but the request seems like it needs a fresh scan of dat…

I’ve been thinking about this.. the same idea behind Dynamic cheat sheets paper and the ACE paper. Thanks for those links! Nice to see those ideas academically studied. My problem is the context of today’s models (that I’ve been using - Claude Opus 5 and GPT-Sol) are a black box to a user like me. I cannot tell what they already hold in their context over the duration of a coding session. I cannot tell influencers a…

> My problem is the context of today’s models (that I’ve been using - Claude Opus 5 and GPT-Sol) are a black box to a user like me.

Would it even help if it weren’t a blackbox? Maybe to the frontier labs with resources, but even trying to read through the thinking traces of an open model doing a nontrivial task easily takes me an entire day to do correctly (i.e. actually looking at the code it read in) and much more if I’m trying to tune a specific repeatable task.

Applying that to agentic coding seems like a losing proposition. The only way to manage it seems to be more agents and that’s its own rabbit hole of compounding errors (like Claude’s useless comments).

Re: I accidentally turned LLM memory into program analysis

#85
post #61

Earlier quoted context omitted.

In general, what all the big LLM providers are doing is moving towards classical & neural (neuro-symbolic) AI - even though they dont publicly admit it because that would counter their claims for years of "scale is all you need" (which has vanished with diminishing returns, see $MS / altman's GPT-5 bet).

The various advances in LLM technology tend to rhyme with the advances in computer programming in general. For example, the stunts that involved getting LLMs to create compilers and browsers are really just extremely expensive[0] versions of genetic programming (none of it would have worked without using the test-suite as a fitness-function). The recent news of migrations from one test-framework to another (featuring…

I find your perspective on LLM generated programs to be an interesting and fresh take

Re: I accidentally turned LLM memory into program analysis

#86

Earlier quoted context omitted.

In general, what all the big LLM providers are doing is moving towards classical & neural (neuro-symbolic) AI - even though they dont publicly admit it because that would counter their claims for years of "scale is all you need" (which has vanished with diminishing returns, see $MS / altman's GPT-5 bet).

It's strange to frame this as classical vs scale. Us humans have a powerful inference engine in our heads. We also use a calendar to avoid re-deriving everything from first principles before we've had our morning coffee. Businesses couple many creative (human) agents together. They also have processes and rules.

It isn't, and it is not what was described: its about unbounded imagination (neural / LLM) that needs reality constraints (symbols / rules) to produce useful output.

Think of it like human imagination may do anything (flying cars), but the real world has constraints and we use language/writing (symbols) and rules bound to them to simulate and reconcile our imagination with reality to actually flow our energy into something that may work in the real world.

Re: I accidentally turned LLM memory into program analysis

#88
post #21
post #5

Very cool. I recall an HN submission (which I can't find offhand unfortunately) that did something similar -- it used an LLM to decompose articles into a set of statements which were used to construct an entity-relationship graph of facts and events. It then queried that using conventional graph query methods, much like DataLog / Lemmalog is doing here. I remember it was particularly effective at answering timeline-b…

Is it this one: https://news.ycombinator.com/item?id=41445445

Yes, thank you!
Post reply on HN