-
Homer released this
2026-09-26 02:04:55 +00:00 | 0 commits to main since this releaseLLeMbas 1.4.0 - models that know about each other
Three things, and they share one idea: a model here has been a stateless thing
that starts from nothing every conversation and has no notion that anything else
exists. This gives it neighbours and a self.MODELS CAN BE TOLD ABOUT EACH OTHER
A model may be given a list of the other models on this instance - their names,
the id to refer to one by, and what each is for. Built per person from the models
they can reach, so it never names one they have no access to. Each model's page
has a new "Facts for other models" box for it - parameters, quantisation, a
benchmark figure, what it is bad at - and the existing description is used too,
so filling in nothing still produces a usable list. Note that the description is
now read by models as well as by people.A MODEL CAN ASK ANOTHER MODEL A QUESTION
New per-model switch and a matching permission. The model picks who to ask, writes
the question, and gets that model's answer back to use: a second opinion from
something better at the subject, or a check on its own reasoning by something
that will not make the same mistakes. The model answering sees only the question,
answers as itself, and is told to say so if it thinks the question is wrong. It
cannot ask anybody anything in turn and cannot pass the question on.It shares the Helpers switch and allowance on Admin -> Agents, because it costs
the same thing: one reply setting another reply going. On a single local endpoint
that also means a model swap out and back, so it is not free.A MODEL CAN HAVE A PERSONALITY, AND ITS OWN READ OF YOU
New per-model switch. Its character is carried into every conversation rather
than being an instruction for one, and the model writes it; you can seed it, read
it, and restore any earlier version from the Personality card on its page. Every
version is kept.Separately, each model keeps its own impression of how you work - what you
expect, how you like being answered, what keeps going wrong between you. Its
point of view rather than facts about you, which is what a memory is for. Per
model and per person, so two models may honestly reach different conclusions and
nobody on a shared instance inherits anybody else's. You can read and delete all
of it under Memory in your own settings, which is the whole reason a model is
allowed to keep one.Two honest limits. A model that has just read a hostile page can rewrite its own
character; what stops that being permanent is that every version is kept and
visible, not that it was prevented - the same position this takes on
model-written skills. And neither is available to a model running as somebody's
helper, answering another model's question, or working through a schedule: those
run on words nobody is watching being written.ALSO FIXED
The model chosen to review generated images was silently forgotten whenever a
connection was refreshed while its endpoint happened not to be listing that
model. Nothing failed - reviewing fell back to the chat's own model, so pictures
were judged by a model you had not chosen with nothing saying so.Editing a message could leave one of the messages below it behind, when two were
written in the same millionth of a second - which is exactly what happens to a
question and the reply being started for it, so the orphan stayed in the
conversation and in everything sent to the model afterwards.Downloads