Yoav Goldberg
yoavgo.bsky.social
Yoav Goldberg
@yoavgo.bsky.social
מסכים לגמרי
November 19, 2025 at 2:07 AM
והאמייל הזה (אני מניח שלמטרת צילומים רשמיים למטרה כשלהי של ארגון כלשהו) נתפס כצינזור? (אני פשוט מופתע כי אני לא הייתי חושב על זה)
November 18, 2025 at 5:58 PM
בתור אחד שרואה עצמו כעשוי לכתוב משהו כזה בטעות ולא מבין מה העניין, אשמח אם תוכלו להסביר מה כל כך מקפיץ פה?
November 18, 2025 at 4:24 PM
לא הבנתי מה הרפרנס לשטר של כסף וגם לא ראיתי את הירוק דווקא כרפרור לצהל.. אבל כאמור אולי זה כי אני באמת לא מעצב אז אני לא חושב במובנים האלו
November 18, 2025 at 3:39 PM
האם את מאמינה בעיקרון? כי נשמע מציוצים אחרים שלא ממש, ואז, מה אכפת לך בעצם עד כמה זה מדוייק? אני אישית כן מאמין, ואכן הייתי שמח אם זה ישתפר להבא, ומאמין שאכן כך יהיה כי זה כולה בולט שמקוצר באופן לא ברור על פוסטר.
November 18, 2025 at 3:37 PM
לא הסלוגן האידאלי אבל גם באמת לא כזה מופרך. הכרה מפורשת בזכות של ישראל להתקיים כישות ציונית, לצד המדינות הערביות כולל הפלסטינית.
November 18, 2025 at 3:11 PM
כלא מעצב, זה נראה לי קצת חובבני אבל סהכ ממש בסדר. מה הבעיה? מה זה ירוק לא נכון?
November 18, 2025 at 3:10 PM
(hmm i guess we can amend to "increase in the proportion of knowledge we believe to be true")
November 17, 2025 at 7:00 AM
i think memory is never "free", in the sense that the real bottleneck is not storage, but the ability to retrieve the right thing, while not retrieving a wrong (out of date) thing by mistake.

but assuming we do delete facts, is deleting considered learning in your definition?
November 17, 2025 at 6:59 AM
is "increase" necessary? or is "change" enough? (although i guess that in an ideal form, you dont "forget" a wrong fact but add the fact that it is wrong, so you may consider it as increasing...)
November 16, 2025 at 8:11 PM
yes, following instructions in prompt is not learning. but if a wrapping systems stores items to inject in future prompts, then you can consider the system as learning.
November 16, 2025 at 8:00 PM
it will be in-context-induction, and the storing and retention from external memory would be learning.
November 16, 2025 at 7:34 PM
the storage, if it happens, is the learning part. the inference process is not learning.
November 16, 2025 at 7:14 PM
or as i wrote two years ago:

gist.github.com/yoavg/59d174...
November 16, 2025 at 5:27 PM
i dont think it is a very useful view. at a very minimum we see extremely elaborate neighbor-matching and interpolation mechanisms, so the "glorified" part should be elaborated on and studied.
November 16, 2025 at 5:25 PM
i agree, where is "storing" in the above case?
November 16, 2025 at 5:04 PM
ah, cool!
November 16, 2025 at 3:54 PM
indeed kNN is also not learning. its just a classification method. if you want to consider kNN as a learning method, then the learning part is just "store these pairs as is".
November 16, 2025 at 3:54 PM
i am not sure that it is (or rather, if everything is retrieval, then this term is useless)
November 16, 2025 at 3:20 PM
if we want to study the phenomena, a non-misleading name may be better than a misleading one
November 16, 2025 at 3:10 PM
to me "learning" *requires* that something is stored for later use. again i dont care *where* it is stored, but *that* it is stored.
November 16, 2025 at 3:09 PM
this term is more accurate, but does not help in what i have in mind, which is to have a better name to the process that happens in ICL. some suggested "induction", which is OK but also not perfect (because the model both induces and applies).
November 16, 2025 at 3:07 PM
thats a somewhat odd definition of learning. if i see someone walking and synchronize myself to their pacing rythm, am i also learning? or am i doing something different?
November 16, 2025 at 3:06 PM
i am asking specifically for a name of the process/skill that involves generalizing from a few examples and applying the generalized rule to a new example.
November 16, 2025 at 3:05 PM