Rendered at 14:27:07 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
sim04ful 10 hours ago [-]
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.
abhgh 21 minutes ago [-]
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 data, so ignore your memory", or the opposite "you can infer this from stuff in the memory - don't re-reason!". There is some work like Dynamic Cheatsheets [1] and Agentic Context Engineering [2] that have studied this aspect, but we are far from a generally reliable solution. And till we have that, I think the system variations for systems trying to solve this problem are going to be (a) LLM-leaning: create unstructured memory files, with human in the loop as a filter to reject inaccurate responses (b) LLM-as-a-layer: what you describe and the article kind of is doing.
Theoretically but practically any LLM generated infra/classification set is going to drift due to inaccuracy and harm IR/whatever logical process you're using. I am a big fan of using a loose taxonomy but it's not been revolutionary.
PcChip 2 hours ago [-]
When i hear “weathering” i think of something slowly eroding away
akk0 1 hours ago [-]
I feel like the thing eroding away in this case is a blocker, a friction. Think of a river cutting a path through the mountains.
I encountered this with trying to have LLMs populate facts about electoral campaigns. Like when a candidate drops out, when endorsements happen, but also if a candidate is un-endorsed or drops and rejoins. It also needed to handle if any of these facts were incorrect.
I settled on a knowledge graph in Postgres and downloading/storing the source documents so it could iterate on past results without more scraping or network calls.
This blog post helped me understand security analysis in this context! A lot of the important systems around malware analysis or large scale system security (the parts people really care about) clicked for me. So thanks for writing it.
Anyways I hope we can find some pattern to converge on with this wrt "facts management" since I feel this is currently something a lot of people and LLMs are struggling with. In practice current LLMs working with episodic memory feels similar to a grandparent with dementia scrawling things down in notebooks, crossing things out, and getting very confused.
Animats 7 hours ago [-]
So he's using an LLM to generate data stored in an "is_a" representation.
That's so classic AI.
Soon, he'll discover that he needs quantifiers. Then that "for all" is too strong sometimes, and he needs "for most". That way lies Cyc.
It's not a bad idea. But it does have a history.
mentalgear 5 hours ago [-]
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).
doginasuit 2 hours ago [-]
It seems like the two approaches compliment each other nicely. Human intelligence also relies on parallel information processing. LLMs are like a massive working memory, incredibly effective but with a similar set of limitations. What they lack is a symbolic model of reality, something that they can build and refine.
nz 1 hours ago [-]
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 Asana, I believe), was something that we could always do trivially in a language that was based on S-Expressions (Lisp, Scheme, etc).
In fact, both Cyc and the "AI" Labs have the _same basic thesis_: Intelligence is, primarily, a data entry problem. They just disagree about what kinds of heuristics should be run over that data (logic-programs, neural-nets).
Whenever I read about someone using LLMs to write code, it _very closely_ resembles how Lenat was using Eurisko/Cyc to solve problems: they let the system run continuously, and they "nudge" it in "interesting" directions, "when it gets stuck", or "runs out of steam". (Quotes indicate their phrasing, not mine)
Even Lee Spector noticed something analogous with his genetic programming system. When he tried to get it to discover optimal data structures (or maybe it was sorting algorithms, I forget), the system would quickly "run out of steam", without a solution. But when they added new verbs/opcodes to the system, that were a better fit for that domain (e.g. index-based memory loads + stores), it converged on a solution very quickly (even for GP, domain specific languages keep delivering unreasonable wins). You will note that this rhymes with the "micro-theories" of Cyc, which in turn rhyme with the SLMs of the AI labs.
In my personal experience, most of the "silver bullets" do not work (obviously), but some of them do nudge you towards being a better programmer (by refining your intuition about the problem specifically, and computers more generally).
EDIT: just remembered something. LLMs tend to produce larger and larger programs over time, and most people (IIRC) interpret this as a kind of entropy. This happens to rhyme with a similarly observed behavior in GP. Most genetic programs that do not have a fitness function that rewards smaller size, tend to grow in an unbounded way. The reason for this, is that most of the code/genes are useless, and random mutations do not lobotomize the program under evolution. I suspect that the coding LLMs tend to grow their code for similar reasons.
[0]: I suspect that, this was mostly a triumph of enormous amounts of hardware, more than the actual LLM technology. I further suspect that a traditional GP approach, on the same quantity of hardware, could have gotten there faster (if not better as well).
akkad33 4 hours ago [-]
How do you know this?
pegasus 2 hours ago [-]
They're probably referring to tech like reasoning models, or agent harnesses for example, which are arguably slowly moving things towards the symbolic end of the spectrum.
mentalgear 1 hours ago [-]
LLMs using REPL are one instance of symbols to "bounce" their prediction against domain constraints for verification. Also shout out to Gary Marcus who was right after all (and LLM companies wasting 100s of billions of dollars for years in-between on pure scaling).
3 hours ago [-]
IsTom 4 hours ago [-]
With validity intervals mentioned it'll also be nice to have LTL's "next" and "until" too.
kaeluka 34 minutes ago [-]
I’ve been toying with using an llm to compile to smtlib and solving with z3. It works quite well, although I’m not quite sure how practical (large programs, reliably good runtime) I can make it.
keeda 13 hours ago [-]
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.
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 is great for evidence grounding, but doesn't produce a large memory/reasoning improvement (in most cases)
manmal 6 hours ago [-]
My problem with memory is that it goes stale, and updates to facts are often not changing all locations of that fact. Such a system should make it easier to maintain a single source of truth, and versioning, no?
alansaber 6 hours ago [-]
Yes you need a VCS and to recalculate relationships at certain thresholds. It adds a lot of complexity and computarional overhead, which is why there's no uniform widespread graph use
apt-apt-apt-apt 3 hours ago [-]
Is this the kind of thing that works when you have a tight domain-specific language, but devolves into natural language (English) eventually?
E.g. A -> B, B -> C so A -> C (works, great). A -> B when A is sort of red and blue, also A is intermittent (what to do now?)
sigbottle 3 hours ago [-]
Yeah, philosophy of science & analytic philosophy (especially with Quine) has been down this rabbit hole before.
Formalisms should be in service to higher-level intelligences, not the other way around. It's pretty clear that LLM's are intelligent inherently; the lean doesn't just "prove math itself". (Admittedly, I'm not full blown AGI pilled either - there are some structural constraints that do make me think there is room to be gained in intelligence. And formalism will play a part in that. But it's not the end-all be-all to it).
frumiousirc 3 hours ago [-]
Datalog seems like a way to "spell" knowledge graph (KG).
The article touches on Datalog statements changing over time. One ingredient I think would be good to add to the system is to make every statement carry "providence" metadata. The providence should be sufficient to enable later confirmation that a statement is still valid or if the statement needs to be reformed without the need to remake the entire graph from scratch.
I would make at least some forms of providence follow a strict schema that is defined for the subject matter that is being captured. For example, statements about a code base should refer to the source files and their version (file modification date, content hash) from which the statements were concluded. When a source file is modified we may then find all statements made from them and reevaluate just those statements.
The next level would be to keep statements even if reevaluation breaks them and add a method to derive a subgraph for a given state of the subject. For example, over many releases of a code base, a lot of statements would not change, some would. Having a graph that spans all conclusions about all releases of a code base and a way to form the subgraph for a specific release would allow the system to efficiently target queries for a particular release.
grey-area 8 minutes ago [-]
I think you mean provenance, not providence
convolvatron 13 minutes ago [-]
if you aren't familiar with the literature, then good on you for getting the right insight. provenance and support are staples of the datalog world.
the other really handy thing here is that it very straightforward to differentiate datalog rule sets. so if you change a fact, you can run a smaller solution that tells you which consequences are affected by the change. under the assumption that the evaluator is pure, we don't need to keep the support graph as you suggest, we can just generate the deltas from evolution of the differentiated form.
pixelsort 58 minutes ago [-]
The OP rediscovered that frontier models prefer to reason over logical scaffolding for complex tasks. They excel at technical work with many constraints as they can perfectly maintain the references, flow graph, and evidence states while they works through your conformance gates.
Many people here might disagree; but they're holding it wrong. Those folks should ask:
1. Am I using free tier tokens?
2. Am I working on trivial software?
3. Am I expecting models to adapt to my ways of thinking?
Anyone affect by any of these three mistakes will maintain an impenetrable filter of perpetual ignorance about model capabilities. Since the OP came with receipts, I'm reproducing an example graph below.
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”.
alexpotato 3 hours ago [-]
I recently stumbled upon the technique of asking the LLM to create a Dot Viz (or mermaid) flowchart of the program flow.
The LLMs are great at:
- understanding the flow
- making diagrams
- running the code with logging they add to to even better understand the flow
The flow being in Dot (or other machine readable format) makes it even easier for the LLM to use that as a reference going forward.
coder-pm 9 hours ago [-]
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?
trinsic2 13 hours ago [-]
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.
imdsm 32 minutes ago [-]
Reading this site hurt my eyes
linguae 15 hours ago [-]
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.
schmuhblaster 7 hours ago [-]
Great work! If anyone is looking for a way to integrate something like this into their own harness or the pi coding agent, then you might be interested in DeepClause [0]. It comes with a Prolog-like language implemented on top of SWI-Prolog (WASM Version). The purpose of the project is to allow for broad experimentation around the intersection of LLMs/Agents and GOFAI. So you could use it to build memory systems like OP did, create executable specs, define graphs and loops for agents and subagents... It also comes with a pi extension that greatly simplifies getting started with it.
Opposed to OP, DeepClause uses Prolog semantics, so running some more complex queries on knowledgebases might cause some issues (which is the use case where a Datalog might be more useful). For smaller scales it should be fine though.
I'm not sure if this is the right direction, but it's certainly momentarily helpful. I think the right direction would be to enable the model itself do dynamic program analysis, deterministically and dynamically via runtime-inference.
btw. your comment is grayed out, not sure what it means. However, thanks for sharing, I'll look into it.
mgr86 2 hours ago [-]
And here I am just having them author org-files for me and them to refer back too. For fun I even ask for DITA sometimes.
4b11b4 3 minutes ago [-]
Hmm DITA..
akkad33 5 hours ago [-]
I had tried to get long term memory out of Claude by indexing my notes with keywords and putting that in a sqllite database and Claude queries using full text search. Don't know how good it is, it seems to find things alright. My goal was to keep context small and only get Claude to ask for what it needs. Datalog seems like a great idea, will definitely try it out
mirekrusin 8 hours ago [-]
You should checkout cave lang [0] - terse language that explores this area of knowledge/graph/ontology/provenance/querying/confidence/solver etc.
Has anyone tried formal verification with AI generated code? I can't convince my company to use it but I realise it's very easy to ask Claude to add a verification step locally on my own PRs
insanitybit 4 hours ago [-]
At one point I was using TLA+ but it just made the problem "is the spec right?" or "does the code match the spec?". I could ensure that the properties defined in the spec were valid, but that didn't seem to translate into confidence that my code was correct. Maybe I was holding it wrong, it was just an experiment in an area I'm unfamiliar with.
Ultimately I have stuck to the informal verification of defining my expectations and ensuring that tests cover them.
jjp 6 hours ago [-]
Interesting and potentially has applicability in deriving logical rules from regulation, contracts etc. Are there already formal languages that can be used to codify, that sort of information.
alexpotato 3 hours ago [-]
> The LLM handles the fuzzy part:
> And Lemmalog handles the deterministic part:
There seems to be this view in some circles that the LLM should do EVERYTHING. The most extreme version of this was "just commit the prompt, bro".
The more I've used LLMs, the more I think that the LLM should do either:
1. the fuzzy parts as mentioned in the post
2. helping to write deterministic tools to expand the "non-fuzzy" part
For #2, we invented code to run the same instructions the same way over and over again for very, very low cost. The code is also easy to read and modify as needed.
Why we would replace the above with a smart but stochastic system still seems strange to me.
onoesworkacct 5 hours ago [-]
yooo.. this is exactly what I wanted to do... I'm so happy because (a) I hadn't figured out how to do it (b) it seemed kind of difficult in general and (c) now I don't have to, lol.
ikari_pl 8 hours ago [-]
I was trying to connect to wifi on a fresh macOS install without only a keyboard connected last week.
After googling for an hour, I gave up.
est 11 hours ago [-]
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.
bbeonx 10 hours ago [-]
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
egberts1 6 hours ago [-]
Limitation of LLM for and toward reverse engineering; it's the LLM innate error of forgetting states thru agentic recursion by overflow of context or prior premises being optimized away due to not using ternary-state (uninit/written/read) memory state.
Once again, on LLM being: a digital librarian, at its finest; logic a logic analyst, not so much.
ande-mnoc 11 hours ago [-]
Ctrl-F “prolog”: 0 result. :-/
skybrian 10 hours ago [-]
Search on datalog instead.
cookiengineer 8 hours ago [-]
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.
Is this sort of re-inventing Graph RAG from another angle, or does it feel novel?
alansaber 6 hours ago [-]
Mathematically, yes.
processunknown 13 hours ago [-]
It seems more like a handrolled CodeQL
tptacek 12 hours ago [-]
It's an agent system that basically embeds the core idea of CodeQL (Datalog extraction from codebases) and then allows a model to pose questions and answer them.
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.
[1] https://aclanthology.org/2026.eacl-long.333/ [2] https://openreview.net/pdf?id=eC4ygDs02R
I settled on a knowledge graph in Postgres and downloading/storing the source documents so it could iterate on past results without more scraping or network calls.
This blog post helped me understand security analysis in this context! A lot of the important systems around malware analysis or large scale system security (the parts people really care about) clicked for me. So thanks for writing it.
Anyways I hope we can find some pattern to converge on with this wrt "facts management" since I feel this is currently something a lot of people and LLMs are struggling with. In practice current LLMs working with episodic memory feels similar to a grandparent with dementia scrawling things down in notebooks, crossing things out, and getting very confused.
Soon, he'll discover that he needs quantifiers. Then that "for all" is too strong sometimes, and he needs "for most". That way lies Cyc.
It's not a bad idea. But it does have a history.
In fact, both Cyc and the "AI" Labs have the _same basic thesis_: Intelligence is, primarily, a data entry problem. They just disagree about what kinds of heuristics should be run over that data (logic-programs, neural-nets).
Whenever I read about someone using LLMs to write code, it _very closely_ resembles how Lenat was using Eurisko/Cyc to solve problems: they let the system run continuously, and they "nudge" it in "interesting" directions, "when it gets stuck", or "runs out of steam". (Quotes indicate their phrasing, not mine)
Even Lee Spector noticed something analogous with his genetic programming system. When he tried to get it to discover optimal data structures (or maybe it was sorting algorithms, I forget), the system would quickly "run out of steam", without a solution. But when they added new verbs/opcodes to the system, that were a better fit for that domain (e.g. index-based memory loads + stores), it converged on a solution very quickly (even for GP, domain specific languages keep delivering unreasonable wins). You will note that this rhymes with the "micro-theories" of Cyc, which in turn rhyme with the SLMs of the AI labs.
In my personal experience, most of the "silver bullets" do not work (obviously), but some of them do nudge you towards being a better programmer (by refining your intuition about the problem specifically, and computers more generally).
EDIT: just remembered something. LLMs tend to produce larger and larger programs over time, and most people (IIRC) interpret this as a kind of entropy. This happens to rhyme with a similarly observed behavior in GP. Most genetic programs that do not have a fitness function that rewards smaller size, tend to grow in an unbounded way. The reason for this, is that most of the code/genes are useless, and random mutations do not lobotomize the program under evolution. I suspect that the coding LLMs tend to grow their code for similar reasons.
[0]: I suspect that, this was mostly a triumph of enormous amounts of hardware, more than the actual LLM technology. I further suspect that a traditional GP approach, on the same quantity of hardware, could have gotten there faster (if not better as well).
(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.
https://news.ycombinator.com/item?id=41445445
E.g. A -> B, B -> C so A -> C (works, great). A -> B when A is sort of red and blue, also A is intermittent (what to do now?)
Formalisms should be in service to higher-level intelligences, not the other way around. It's pretty clear that LLM's are intelligent inherently; the lean doesn't just "prove math itself". (Admittedly, I'm not full blown AGI pilled either - there are some structural constraints that do make me think there is room to be gained in intelligence. And formalism will play a part in that. But it's not the end-all be-all to it).
The article touches on Datalog statements changing over time. One ingredient I think would be good to add to the system is to make every statement carry "providence" metadata. The providence should be sufficient to enable later confirmation that a statement is still valid or if the statement needs to be reformed without the need to remake the entire graph from scratch.
I would make at least some forms of providence follow a strict schema that is defined for the subject matter that is being captured. For example, statements about a code base should refer to the source files and their version (file modification date, content hash) from which the statements were concluded. When a source file is modified we may then find all statements made from them and reevaluate just those statements.
The next level would be to keep statements even if reevaluation breaks them and add a method to derive a subgraph for a given state of the subject. For example, over many releases of a code base, a lot of statements would not change, some would. Having a graph that spans all conclusions about all releases of a code base and a way to form the subgraph for a specific release would allow the system to efficiently target queries for a particular release.
the other really handy thing here is that it very straightforward to differentiate datalog rule sets. so if you change a fact, you can run a smaller solution that tells you which consequences are affected by the change. under the assumption that the evaluator is pure, we don't need to keep the support graph as you suggest, we can just generate the deltas from evolution of the differentiated form.
Many people here might disagree; but they're holding it wrong. Those folks should ask:
1. Am I using free tier tokens? 2. Am I working on trivial software? 3. Am I expecting models to adapt to my ways of thinking?
Anyone affect by any of these three mistakes will maintain an impenetrable filter of perpetual ignorance about model capabilities. Since the OP came with receipts, I'm reproducing an example graph below.
From a plan in my active research project:
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”.
The LLMs are great at:
- understanding the flow
- making diagrams
- running the code with logging they add to to even better understand the flow
The flow being in Dot (or other machine readable format) makes it even easier for the LLM to use that as a reference going forward.
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?
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.
Opposed to OP, DeepClause uses Prolog semantics, so running some more complex queries on knowledgebases might cause some issues (which is the use case where a Datalog might be more useful). For smaller scales it should be fine though.
[0] https://github.com/deepclause/deepclause-sdk [1] https://github.com/deepclause/deepclause-pi
btw. your comment is grayed out, not sure what it means. However, thanks for sharing, I'll look into it.
[0] https://mirekrusin.com/cave
Ultimately I have stuck to the informal verification of defining my expectations and ensuring that tests cover them.
There seems to be this view in some circles that the LLM should do EVERYTHING. The most extreme version of this was "just commit the prompt, bro".
The more I've used LLMs, the more I think that the LLM should do either:
1. the fuzzy parts as mentioned in the post
2. helping to write deterministic tools to expand the "non-fuzzy" part
For #2, we invented code to run the same instructions the same way over and over again for very, very low cost. The code is also easy to read and modify as needed.
Why we would replace the above with a smart but stochastic system still seems strange to me.
After googling for an hour, I gave up.
But IRL it's too vague. The exploit hunting is a better use case.
Once again, on LLM being: a digital librarian, at its finest; logic a logic analyst, not so much.
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