{"slug": "cael-0-4-1-a-chat-assistant-with-no-neural-network-and-no-transformer", "title": "CAEL 0.4.1: a chat assistant with no neural network and no transformer", "summary": "A hobbyist developer released CAEL 0.4.1, a chat assistant built in plain Python with no neural network, transformer or LLM weights, now published on Hugging Face. On five Open SLM Leaderboard tests run locally, CAEL scored a 49.97% mean versus SmolLM2-360M's 58.86%, ahead on ArithMark-3 (69.5% vs 59.6%) but far behind on HellaSwag and PIQA, and in blind chat rounds against Qwen3.5-0.8B (set to 1000 Elo) CAEL scored about 796. The system combines symbolic, count-based and cellular-automaton engines with an index of about 285,000 human-written answers from Stack Exchange, OpenAssistant and databricks-dolly-15k, and is source-available for non-commercial use; the developer notes it is weak on open advice, how-to questions and creative writing.", "body_md": "Hi all. I’d like to share CAEL, a hobby project: a chat assistant built without any neural network. No transformer, no neural weights, no LLM behind the replies. It runs on a CPU in plain Python.\n\n**How it works**\n\n- Symbolic, count-based and cellular-automaton engines for reasoning and state.\n- Exact skills for conversation: quantities, rates, clock times, syllogisms, schedules and changed values.\n- Chat memory: it answers from what you said earlier in the conversation.\n- Checked web answers: when it doesn’t know, it searches and answers only if a second independent source agrees.\n- An index of about 285,000 human-written answers (Stack Exchange, OpenAssistant, databricks-dolly-15k) for open questions.\n\n**Honest results**\n\n- On the five Open SLM Leaderboard tests, run locally: 49.97% mean against SmolLM2-360M’s 58.86%. It is ahead on ArithMark-3 (69.5% vs 59.6%) and far behind on HellaSwag and PIQA. This is a local comparison and not a leaderboard entry, since CAEL uses offline Wikipedia and the ARC Corpus while answering.\n- In blind chat rounds against Qwen3.5-0.8B (set to 1000 Elo), CAEL scores about 796. It does not match a small LLM at general chat. I judged these rounds myself, so treat them as a rough guide.\n\n**Where it is weak:** open advice, how-to questions and creative writing. It often declines to answer where an LLM would say something plausible.\n\n**Links**\n\nIt is source-available for non-commercial use, and it was built with AI assistance. I’d welcome feedback, especially ideas for non-neural approaches to open-ended chat.\n\n*Edit: 0.4.1 is now published on Hugging Face; the link above replaces the earlier 0.4.0 model card link.*", "url": "https://wpnews.pro/news/cael-0-4-1-a-chat-assistant-with-no-neural-network-and-no-transformer", "canonical_source": "https://discuss.huggingface.co/t/cael-0-4-1-a-chat-assistant-with-no-neural-network-and-no-transformer/191825#post_1", "published_at": "2026-11-14 00:22:35+00:00", "updated_at": "2026-11-14 00:50:58.714180+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-tools"], "entities": ["CAEL", "Hugging Face", "SmolLM2-360M", "Qwen3.5-0.8B", "Open SLM Leaderboard", "Stack Exchange", "OpenAssistant", "databricks-dolly-15k"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/cael-0-4-1-a-chat-assistant-with-no-neural-network-and-no-transformer", "markdown": "https://wpnews.pro/news/cael-0-4-1-a-chat-assistant-with-no-neural-network-and-no-transformer.md", "text": "https://wpnews.pro/news/cael-0-4-1-a-chat-assistant-with-no-neural-network-and-no-transformer.txt", "jsonld": "https://wpnews.pro/news/cael-0-4-1-a-chat-assistant-with-no-neural-network-and-no-transformer.jsonld"}}