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 principle I've been thinking about, which I call Weathering: useful reasoning should change the shape of the system. If an LLM has already had to infer a relation, mapping, rule, or abstraction, repeated use should wear that inference into the system so that the next similar request doesn't require discovering it again from scratch.

With continued use, a weathering-capable system should therefore require less and less probabilistic intelligence for recurring work. Put another way, there should be a declining marginal cost of cognition since the products of intelligence harden into structure that can subsequently be reused and evaluated mechanically.

This is the fact I’ve been struggling with for quite some time. It’s not because it forgets the facts, it’s because the invalidation doesn’t propagate.

My way of handling that is a decision log. For every project since I started doing that it’s working great. My CLAUDE.md instruct the agent to store my every decision to the file with a metadata when I made this decision and what was the context. The agent is using this file as an index of decisions and rarely lose a track. It also helps team members to find out more about the development phases.

Does your system invalidate the parts of the memory if these are not valid or relevant anymore or just store/retrieve?

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-based queries that LLMs (back then) sucked at.

(See also Cyc: https://en.wikipedia.org/wiki/Cyc)

I think approaches like this are going to be (or maybe already are?) the basis of effective grounding of LLM responses in authoritative data sources. It should be possible to pinpoint any error to an incorrect traversal or an incorrect "fact." This would work best for concrete, unambiguous facts, however; fuzzy, ambiguous or opinion-based information will probably remain the purview of LLMs.

This was a pretty awesome read, I liked it a lot!

What I found out during malware analysis is that LLM agents have a couple of quirks that you can solve by:

- optimize for short lived agent workflows

- use symbols as function contracts

- maintain decision and discovery state

- give LLMs CLI linters

- give LLMs access to knowledge bases

The linter part is mindblowing. I built linters that validate HTML or markdown or docx or Go or C files, for example, and they output what kind of structure is expected instead of useless token based errors (e.g. h4 inside h1? Must be h1 > h2 ...).

With linters the output quality of agents is just soo much better.

For program analysis, I'm currently exploring the idea of using an external ebpf daemon that programs can be observed with via a public API (which is the tool for the agent to use). Not sure if it'll do the trick yet, but I think it has lots of potential.

My stuff in case you're interested:

[1] https://github.com/cookiengineer/exocomp

[2] https://github.com/cookiengineer/gobayashi

[3] https://github.com/cookiengineer/gonano

Something of this capacity would be useful in investigating obscure hardware failures in the logs that I couldn't confirm because the problem was not being observed while the device was in my shop. the problem was surfacing in another location probably due to some set of circumstances in the software that I could recreate, or some particular peripherals that were attached.

I ran into the very same problem of the LLM forgetting that we ruled out a conclusion that was verified not to be the cause as it came up further in the conversation history while I was exploring possibilities.

I had to keep reminding we ruled out that conclusion prior.. I just carried on with having the LLM capture some of the supporting sources of other people experiencing the same problem and kept having to refine those sources because it was focused only on summaries, but eventually i got the sources to a point where they were good enough hypothesis that we could formulate a better conclusion on what the potential cause was.

This really matches up to my experience on long research projects with Claude.

It’s very hard to remove information - Claude has a habit of recording things all over the place and will happily treat things as facts even after they’ve been disproved.

What is currently true can get easily contaminated with old “facts”.

This summer I’ve been investigating agentic coding with local LLMs, and while I’m far from an expert, one thought that has been on my mind is leveraging techniques from “old-school” AI such as heuristic search to guide agents when it comes to planning. The use of Datalog in this article resonates with me, since logic programming was a major part of old-fashioned symbolic AI. I’m very curious about this combination of “old-school” AI and LLMs.

Eventually lambda prolog will rise again

Very cool article. I had a similar idea where "fact checking" should be real programs for logic correctness.

But IRL it's too vague. The exploit hunting is a better use case.

It seems like you might be inventing a form of non-monotonic logic. Check out answer set programming, it actually does exactly what you want of "unlearning" facts that you've learned. Not sure if it helps in your particular instance, but it's very cool stuff and IIRC there is an implementation that extends datalog. https://en.wikipedia.org/wiki/Answer_set_programming

Ctrl-F “prolog”: 0 result. :-/

Is this sort of re-inventing Graph RAG from another angle, or does it feel novel?

[flagged]

[dead]

[flagged]