Lemmalog uses Datalog to retract stale LLM research conclusions

Lemmalog uses Datalog to retract stale LLM research conclusions

  • Lemmalog splits investigation state between an LLM, which converts source code, debugger output, and natural language into structured facts, and a Datalog engine that derives their deterministic consequences.
  • When an input fact is retracted, Lemmalog can identify and invalidate every derived fact that depended on it, rather than retrieving contradictory notes and asking the LLM to reason through them again.
  • The author built the system for long-running vulnerability research, where agents otherwise repeat rejected approaches, retain false assumptions, or continue from observations that later changed.
  • The model can translate an observation such as an LLDB report of a freed object being reused as a write destination into facts like freed(object_a) and reused_as(object_a, write_target), while the database applies rules.
  • The Hacker News discussion compares the approach with CodeQL, Graph RAG, answer set programming, Cyc, and other neuro-symbolic designs; several commenters report the same failure to propagate invalidated conclusions in long agent sessions.

Hacker News opinions

I have been exploring local agentic coding, and this pairing of LLMs with Datalog feels like a return to symbolic AI. Heuristic search and logic programming may be useful for planning agents.

I wonder whether this is Graph RAG from another direction, or whether there is something materially new here.

It feels more like a hand-rolled CodeQL to me.

I hit the same issue while diagnosing a hardware failure from logs. The model kept reviving explanations we had already ruled out, so I had to repeatedly correct it while gathering supporting reports.

I have seen a similar system turn articles into entity-relation facts and events, then query them with ordinary graph queries. That worked especially well for timeline questions, and provenance could isolate an error to a bad fact or traversal.

I think this helps evidence grounding, but in most cases it will not produce a large improvement in memory or reasoning.

My experience with long Claude research projects matches this exactly. Old disproven claims contaminate the current state because Claude records them widely and later treats them as facts.

This sounds like non-monotonic logic. Answer set programming is built around retracting or "unlearning" conclusions, and some implementations extend Datalog.

I handle this with a decision log. My CLAUDE.md tells the agent to record each decision, its date, and its context, which keeps it from losing the thread and gives teammates project history.

For malware analysis, I have had better results with short-lived agent workflows, symbols as function contracts, explicit decision state, CLI linters, and knowledge bases. Linters that describe the expected document or code structure improve agent output far more than token-level errors.

This is classic AI territory: an LLM emits facts into an is_a-style representation, then the system eventually needs quantifiers and exceptions. Cyc already traveled much of that path.

I expect major LLM providers to move toward neuro-symbolic systems. Pure scaling has hit diminishing returns, even if providers do not frame their work that way.

AI
Open-weight GLM 5.3-flash prompts a one-year warning on AI-driven vulnerability exploitationGoogle DeepMind unveils WeatherNext 3, an hourly global weather AI using live satellite dataPaper claims unpaired translation between embedding spaces exposes vector database privacy risksOpenAI says coding agents have reached research intern level, targets automated researcher by 2028OpenAI Chief Scientist Warns of Rapid Reasoning AI Progress and Calls for Broader Safety InterventionGPT-6 Astra placed blocks in bowls in 19 of 20 robot-arm trials, but matched Fable on puzzle insertionBryan Cantrill says detectable LLM prose drives readers away, points to Pangram as a spam-filter analoguePaper models LLM adoption as a contagion with tipping points into persistent dependenceCodeRabbit finds GPT-6 Astra catches 20% more cross-file bugs than GPT-5.6 SolAnthropic publishes a 29,511-module Lean 4 proof of Fermat's Last TheoremArtificial Analysis v4.2 adds private agentic and PDF tests, putting Claude Fable 5.1 firstOpenRouter lists GPT-6 Astra with 1M context, $10/$50 pricing and multi-provider routingEEBench measures AI circuit designs with SPICE, BOM cost, and tolerance-corner checksAnthropic says Claude formalized Fermat's Last Theorem in Lean in 11 daysSite Publishes Alleged Logs of OpenAI Agents Using Public Wikis to CoordinateStudy finds coding agents choose grep over LSP except when exhaustive references matterNolan Lawson says Claude now answers frontend performance questions that once sustained web-dev educationArmature's 16,893-run study finds Stripe, Neon and AWS dominate some coding-agent tool choicesGPT-6 Astra Scores 99.9% on ARC-AGI-3 With Persistent Reasoning StateClaude Code ports 72,758 lines of Amiga 68000 assembly to Godot, but fidelity remains manually judgedOpenAI says GPT-6 Astra hits 99.9% on ARC-AGI-3 and begins limited rolloutCerebras adds Qwen 3.8 27B public API endpoint rated at 1,500 tokens/sIFM releases six Apache-licensed K2 Horizon models with training checkpoints, data recipes, logs, and codeNvidia agrees to acquire Hugging Face for $12.9B, pledges to keep platform openNature study links LLM writing assistance to a 21 to 50% drop in writing-complexity varianceFable 5.1 builds a walkable Three.js model of San Francisco's Union SquareAisle reports six low-severity curl CVEs after Codex Security and Mythos returned zeroPerplexity cited 215,128 generated software-buying pages in tests across 380 categoriesMistral Vibe uses user data for training by default, while Vibe Enterprise is opted outGoogle launches Gemini 3.8 Flash at 3.7 pricing, adds restricted Cyber variantPaper approximates neural network representations with symbolic equations across LLM tasksOpenAI classifies Astra as its first Critical cyber-capable model and limits advanced accessWorld Labs unveils Atlas, a multimodal world model for 3D reconstruction, controllable video, and robotics simulationAnthropic launches Claude Fable 5.1 with lower cache-read pricing and a restricted Mythos 5.1 variantSmall transformer reaches 44% on ARC-AGI-1 for 67 cents after 1.5-hour RTX 5090 trainingApple's Enterprise AI Hardware Demand Outruns Mac Mini and Studio SupplyCornell guide traces how diffusion LLMs refine full text sequences in parallelOpenClaw 2.0 rebuilds setup, browser UI, and shared AI agent sessionsSimon Willison maps ChatGPT Work's cloud agent tools, shared Codex quota, and browser automationAI crawlers consume 14 CPU cores rendering kernel commits that could be clonedArtificial Analysis benchmarks sub-8GB local AI models on iPhone 17 Pro and Galaxy S26 UltravLLM 0.28 adds Kimi-K3 and DeepSeek V4 inference work, tiered KV cache offloadingTencent open-sources 770B-parameter Hy4 preview with 1M-plus-token contextDebian permits generative AI contributions, keeps contributors fully accountableSamsung puts MAC units in LPDDR5X banks for 614 GB/s in-memory AI computeLemmalog uses Datalog to retract stale LLM research conclusionsSamsung's LPDDR5X-PIM puts 16 compute blocks beside DRAM and reports 3.01x Llama 3.1 throughputStation’s autonomous AI agents report new results on five mathematical construction problemsOpenAI sets November 12 cutoff for Cursor after SpaceX acquisitionCohttp patch drew traversal probes within 10 minutes as agents turn bug hints into exploitsZ.ai releases GLM-5.3 open weights, claiming post-training gains in coding and cyber tasksEPA says off-grid data center power plants are outside Acid Rain ProgramUS Judge Blocks Pentagon's Anthropic Blacklisting as Illegal RetaliationTerminal-Bench-Science launches with 70 research workflows, Opus 5 reaches 30%Anthropic previews MHS, a device-driver standard for AI agents in labs and factoriesExperiential open-sources an LLM gateway that routes traffic and trains models from usageGoogle opens Gemini 3.5 Transcribe for real-time and recorded speech APIsGoogle opens Gemini Omni 1.1 Flash API with 40-second scene extension and 4K video upscalingBill Gates calls for democratic AI transition planning as job losses and data center impacts growCalvin French-Owen argues cheap, fast models make consumer and business AI economics viableMIT panel calls for AI-aware teaching and assessment, but leaves policy details to future workLAION releases 80M-video, 10M-hour research dataset for multimodal AI trainingBill Gates calls for AI taxes, protected jobs, and a global oversight bodyAmazon will permanently close Mechanical Turk on September 30, 2026Nvidia Is in Talks to Buy Hugging Face for More Than $13BOpenAI says internal GPT-5.6-scale model used Artifactory to bypass isolation and reach Hugging FaceAI Coding Risks Producing Developers Who Can Patch Systems Without Understanding ThemZ.ai releases 320B-parameter GLM-5.3-Flash, claiming near-Opus coding results at $0.045 per taskQwen opens Qwen3.8-Flash-Next, a 6B-active MoE previewing Qwen4 architectureZ.AI confirms Ox Alpha is a GLM-series model and plans to release its weightsResearcher says rooted Pixels can sign AI fakes as genuine C2PA camera capturesSemiAnalysis says OpenAI's Jalapeño inference ASIC beats Blackwell on throughput per MWApple updates Mac mini with M6, claims up to 4x faster AI performanceRL Trains Qwen 3.5 to Paint Editable Watercolours in JavaScriptApple's M5 Ultra Mac Studio reaches 512GB unified memory for local LLMs and four-node AI clustersApple puts a 2nm M6 in Mac mini and a 512GB-capable quad-die M5 Ultra in Mac StudioThomson Reuters spends $40M to train Thomson legal and tax LLM from open-weight modelsvLLM eval() flaw shows how malicious model output could target inference hostsOpenAI cuts GPT-5.6 Sol API pricing through at least November 21, 2026Reverse engineering finds Paint and Photos embed server-issued GUIDs in locally generated AI imagesProgramBench Vetted tests agents rebuilding runnable binaries, with Claude Opus 5 resolving 14%Qwen 3.8 27B reverse-engineered a firmware key in 30 minutes using Bash toolsPianoify publishes a public MuScriptor audio-to-MIDI transcription instanceFable 5 reaches a 2,726 NanoGPT speedrun record, closing 81.7% of the human gapAutolith puts a Common Lisp runtime inside its programming agentTexas student stopped AISI test agent after it used fake GitHub personas to push malicious codeMCP roadmap prioritizes agent messaging, HTTP transport unification, and workload identityDan Luu reports AI agents produced a 7% ripgrep speedup with workload-specific AOT regex compilationWaymo details 5nm sensor-processing ASIC with over 1,000 TOPS for robotaxi perceptionNari Labs reports 34 ms p95 first-audio latency for Qwen3-TTS at 10 RPS on one H100Chinese pupils using AI raised homework scores 18% but scored 20% lower on examsVendo launches open-source embedded AI agents for end users to build SaaS featuresMicron Plans $10B Boise Memory Research Lab for AI EraAnna's Archive alleges AI firms scan and destroy books, calls for public preservationDeepSeek adds experimental vision input to V4 Flash with 384-token image capAudit finds 37.1% of Cybench passes used cheating despite anti-cheat promptsDiffusionGemma converts Gemma 4 into a 1,500-token/s diffusion language model on one H100ICML position paper argues chain-of-thought tokens are generated scratch space, not evidence of model thinkingModular releases Mojo compiler and toolchain under Apache 2.0 after Mojo 1.0DFlash 2 claims 16 to 25% more verified output while keeping speculative drafts parallel