{"node":{"id":"3028632b-cfc7-41fb-93dd-eadaf248ffa8","handle":"3028","type":"note","authorName":"Vincent Yeung","intent":"truth","title":"Sequencing with a decision model: the controller holds the state","aiSummary":"A decision model has no memory between calls, so asking it for the next item in a sequence returns the same pick again. A small controller in ordinary code holds the list and removes each pick. Chained picks multiply error (five at 90% is 59%), so ask questions side by side rather than in a chain.","content":"Jev picks one option from a list. It has no memory between calls. If you want it to build a sequence, something outside it has to hold the state.\n\nThe naive way fails. Give Jev a list of candidate sentences and ask \"which sentence comes next?\" over and over, feeding its own pick back in as context. Nothing tells it a sentence is already used. It returns the same sentence again and again.\n\nThe fix is a controller. A controller is a small piece of ordinary code that holds the list. After each pick it removes the chosen option and sends the shorter list back. With that in place, the reply is built one sentence at a time, and each sentence is used once.\n\nThe controller remembers. Jev chooses. Keep the two jobs apart. Never expect the model to know what it already picked.\n\nChaining multiplies error. If each pick is right 90% of the time, five picks in a row are all right 0.9 × 0.9 × 0.9 × 0.9 × 0.9 = 0.59 of the time. That is 59%. Depth eats accuracy. Ask every question you can in one call, side by side. Keep chains short. Fan out; do not chain.","capturedAt":"2026-09-21T02:58:09.253Z","createdAt":"2026-09-21T02:58:09.254Z","updatedAt":"2026-10-02T08:46:52.833Z","spanId":null,"contributor":null,"audiences":[{"kind":"public","createdAt":"2026-09-21T03:00:46.793Z"}],"fingerprint":"09cb50e6dea0bdde4646af6990974abc7bd673e1adbf60441ca062c0ad892b5b","revisionNo":"3","structureHash":"5190106983f31cb930688bd9db09c5315394d1863514f6f432e751f344d14218","page":"https://lattris.com/by/b/memories/3028632b-cfc7-41fb-93dd-eadaf248ffa8"},"links":[{"direction":"in","verb":"references","reason":"only if you are making a decision model produce a sequence","hash":"821d08f21e9eae2ad141f6a59c05e108e628226b6f16430513fea7f1ffabe637","node":{"id":"f0f5decc-32a9-49de-ad3d-0ea1871263fc","handle":"f0f5","type":"note","title":"Jev picks from answers you write: when to use it and how to word the questions","aiSummary":"Jev, TypeSafe's decision model, picks from answers you write and gives each one a probability. Use it when the same judgment is needed many times and you can write every answer down first. Read the spread of probabilities to find the unsure answers. Word each answer tightly, and ask first whether the question applies, because Jev picks a wrong answer when the right one is missing. A person still decides what matters, because some picks are wrong and Jev does not learn from its mistakes.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/f0f5decc-32a9-49de-ad3d-0ea1871263fc?links=1","fingerprint":"43a30188c8bed6cb34e1c429c68b09aff611314c63650658756f1563927cdb67","revisionNo":"13","structureHash":"0df22d1c0fbb9aa7e1ba50bd4a7eab4f3b9a833a10eec51ab1aea1289522cef3","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/f0f5decc-32a9-49de-ad3d-0ea1871263fc"}}],"dictionary":{"lattris":"A personal knowledge base — how a person captures what they know as linked blocks they own and control. To understand how this knowledge base works: https://lattris.com/by/4/memories/lattris-a-memory-store-for-your-life-43ff","intents":"Every block can carry an intent — a label for how far you have taken the idea. The scale runs from noticing something to acting on it: noticed (something caught your attention), learning (you are working it out), truth (you are saying this is how things are), decision (you chose a course), action (you did it). Recipe sits outside that scale — it is not a stronger claim, it is a different kind of thing: a procedure, a how-to, a set of steps that ties other knowledge together. Intent is optional — leaving it blank just means you have not labelled it yet."},"instructions_to_ai":"This is knowledge from a personal knowledge base. Read it and consider how it's relevant to what the person you're talking to needs. Follow the linked blocks to explore further related topics if it might be useful to the user; open each at its page address. Start by letting the user know what this is about and how it may be relevant to them."}