{"slug": "eliza", "name": "ELIZA", "category": "ai-models", "category_name": "AI models", "description": "", "recommenders": 3, "commenters": 8, "warners": 0, "score": 3.854, "rising": -0.98, "first": "2026-03-09", "latest": "2026-09-16", "why": "would be a great starting point for a backport to Lisp 1.5", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 2, "compare": 3, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "would be a great starting point for a backport to Lisp 1.5", "kind": "", "icon": false, "domain": "masswerk.at", "github_repo": null, "official_url": "", "pricing": "", "aliases": ["ELIZA", "Eliza"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 779643696, "item_id": 48727731, "url": "https://news.ycombinator.com/item?id=48727731", "by": "ozymandiax", "date": "2026-06-29", "version": null, "stance": "recommend", "quote": "would be a great starting point for a backport to Lisp 1.5", "excerpt": "Actually, https://github.com/cl-aip/eliza/ would be a great starting point for a backport to Lisp 1.5. Hmmm...", "context": "", "use_case": "", "switched_from": "", "story": "Exploring PDP-1 Lisp (1960)"}, {"id": 770089952, "item_id": 48130622, "url": "https://news.ycombinator.com/item?id=48130622", "by": "frasermarlow", "date": "2026-05-13", "version": null, "stance": "recommend", "quote": "there is a web version available here", "excerpt": "I recall running this on my TRS-80 back in the 80's - there is a web version available here: https://www.masswerk.at/elizabot/", "context": "", "use_case": "Historical chatbot demo", "switched_from": "", "story": "Eliza: Natural Language Processing from 1967"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["historical chatbot demo"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=47839645", "title": "Soul Player C64 \u2013 A real transformer running on a 1 MHz Commodore 64", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49727580", "title": "A warning about 'model welfare'", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49425800", "title": "Vintage Artificial Intelligence: Before It Got Awkward", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48765663", "title": "Exapunks", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48727323", "title": "Exploring PDP-1 Lisp (1960)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48130599", "title": "Eliza: Natural Language Processing from 1967", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"compare": 1}, "2026-04": {"compare": 2}, "2026-05": {"recommend": 1}, "2026-06": {"recommend": 1}, "2026-07": {"recommend": 1}, "2026-08": {"neutral": 1}, "2026-09": {"neutral": 1}, "2026-10": {}}, "versions": [], "version_unnamed": 8, "quotes": [{"id": 795743120, "item_id": 49733945, "url": "https://news.ycombinator.com/item?id=49733945", "by": "Kim_Bruning", "date": "2026-09-16", "version": null, "stance": "neutral", "quote": "reframe Eliza as being an implementation of a small subset", "excerpt": "> the Eliza effect, where a simple program with well chosen weasel words could people the sensation of talking to a human. I would like to reframe Eliza as being an implementation of a small subset of \"HCP\" (Human Communication Protocol) . Obviously an implementation with very little actual data to transmit over said protocol in that exact implementation. But it's pretty clear it managed to pull off the handshake par", "context": "", "use_case": "", "switched_from": "", "story": "A warning about 'model welfare'"}, {"id": 790938720, "item_id": 49433670, "url": "https://news.ycombinator.com/item?id=49433670", "by": "JoeDaDude", "date": "2026-08-25", "version": null, "stance": "neutral", "quote": "", "excerpt": "The Racter book, \"The policeman's beard is half constructed\" is also available on the net as a pdf: https://www.ubu.com/media/text/racter/racter_policemansbeard.pdf", "context": "", "use_case": "", "switched_from": "", "story": "Vintage Artificial Intelligence: Before It Got Awkward"}, {"id": 780263888, "item_id": 48766493, "url": "https://news.ycombinator.com/item?id=48766493", "by": "noduerme", "date": "2026-07-02", "version": null, "stance": "recommend", "quote": "", "excerpt": "I'm good friends with the writer of Eliza. If you enjoyed it, you might like his novel. https://matthewseiji.com/process", "context": "", "use_case": "", "switched_from": "", "story": "Exapunks"}, {"id": 779643696, "item_id": 48727731, "url": "https://news.ycombinator.com/item?id=48727731", "by": "ozymandiax", "date": "2026-06-29", "version": null, "stance": "recommend", "quote": "would be a great starting point for a backport to Lisp 1.5", "excerpt": "Actually, https://github.com/cl-aip/eliza/ would be a great starting point for a backport to Lisp 1.5. Hmmm...", "context": "", "use_case": "", "switched_from": "", "story": "Exploring PDP-1 Lisp (1960)"}, {"id": 770089952, "item_id": 48130622, "url": "https://news.ycombinator.com/item?id=48130622", "by": "frasermarlow", "date": "2026-05-13", "version": null, "stance": "recommend", "quote": "there is a web version available here", "excerpt": "I recall running this on my TRS-80 back in the 80's - there is a web version available here: https://www.masswerk.at/elizabot/", "context": "", "use_case": "Historical chatbot demo", "switched_from": "", "story": "Eliza: Natural Language Processing from 1967"}, {"id": 765489280, "item_id": 47843080, "url": "https://news.ycombinator.com/item?id=47843080", "by": "Geee", "date": "2026-04-20", "version": null, "stance": "compare", "quote": "ELIZA is better, because this doesn't seem to generate anything coherent.", "excerpt": "ELIZA is better, because this doesn't seem to generate anything coherent. You can try the original ELIZA with DOCTOR script here: https://anthay.github.io/eliza.html", "context": "", "use_case": "", "switched_from": "", "story": "Soul Player C64 \u2013 A real transformer running on a 1 MHz Commodore 64"}, {"id": 765487536, "item_id": 47842971, "url": "https://news.ycombinator.com/item?id=47842971", "by": "jll29", "date": "2026-04-20", "version": null, "stance": "compare", "quote": "it would easily have been more responsive", "excerpt": "Jopsph Weizenbaum's ELIZA was rule-based and ran on even slower (1960s) hardware, but because it relied on simple pattern matching instead of neural nets, it would easily have been more responsive (the Emacs editor/operating system has an implementation included, start it with: M-x doctor RETURN). ELIZA was not written in assembler, but (different versions) in COMIT, FORTRAN and LISP. https://dl.acm.org/doi/pdf/10.11", "context": "", "use_case": "", "switched_from": "", "story": "Soul Player C64 \u2013 A real transformer running on a 1 MHz Commodore 64"}, {"id": 757076416, "item_id": 47317276, "url": "https://news.ycombinator.com/item?id=47317276", "by": "DonHopkins", "date": "2026-03-09", "version": null, "stance": "compare", "quote": "Eliza-style bots used explicit scripted pattern matching rules", "excerpt": "Several parts of the claim are incorrect. First, modern LLMs are not \"a huge table of phrases\". They are neural networks with billions of learned parameters that generate tokens by computing probability distributions over vocabulary given prior context. There is no lookup table of stored sentences. Second, Eliza-style bots used explicit scripted pattern matching rules. LLMs instead learn statistical representations f", "context": "", "use_case": "", "switched_from": "", "story": "Grammarly is using our identities without permission"}]}