Tootfinder

cool " Russia’s economy has entered the death zone.
Alexandra Prokopenko wonders how much longer it can go on metabolising its own muscle tissue" https://www.economist.com/by-inv…

NIVEL weekrapportage week 11.
De griepepidemie is voorbij. We kunnen de balans opmaken en zien dat we, ondanks de opkomst van H3N2, toch een minder heftige epidemie hebben gehad dan een jaar geleden.
Volgens NIVEL is er ook sprake van een kortere epidemie, maar dat is m.i. een beetje appels en peren vergelijken, omdat ze de epidemie nu over verklaren o.b.v. een andere indicator dan vorig jaar. Aan onderstaand plaatje kun je dat i.i.g. niet zien.

RE: https://mastodon.social/@heidilifeldman/116596292735099594
There will surely be — must already be! — many other such efforts sneaking under the radar, exploiting the marginalized, or cake-walking past the indifferent.
The thing about having trillions of investment dollars behind your industry is that you don’t really even need a marketing •strategy• per se; you just need to flood the zone, flood the containers of society and see where the leaks are. Efforts like the one in the linked @… article only need to succeed 1 time in 100 to pay off, because once you’ve got the data you can milk it forever.

Tipp: Die Stiftung Naturschutz Berlin bietet am 23.4.26 von 16-18 Uhr einen kostenlosen Online-Vortrag zum Thema Libellen an 🧚‍♂️
Hier anmelden:
https://www.umweltkalender-berlin.de/angebote/details/89412?dat=2026-04-23?dat=2026-04-23…

Libellen 23.04.2026 | 16:00 - 18:00 Uhr
Bei näherer Betrachtung sind Libellen, wie viele andere Insekten auch, faszinierende Tiere. Sie jagen andere Insekten, unter anderem auch Mücken, die wir als Plagegeister empfinden. D...

"Daarna sprak je een zin uit die me diep raakte: “Alles waar ik in geloofde, is mislukt.”
Je vertelde over de antikernwapendemonstraties begin jaren tachtig, je lidmaatschap van vredesorganisaties in Israël/Palestina, je werk als oprichter van de sectie Vrouwenstudies aan de UvA en al je waarschuwingen voor racisme en fascisme als journalist."

So to follow up on this, I've caught it in action. Models, when quantized a bit, just do a bit more poorly with short contexts. Even going from f32 (as trained) to bf16 (as usually run) to q8 tends to do okay for "normal" context windows. And q4 you start feeling like "this model is a little stupid and gets stuck sometimes” (it is! It's just that it's still mostly careening about in the space of "plausible" most of the time. Not good guesswork, but still in the zone). With long contexts, the probability of parameters collapsing to zero are higher, so the more context the more likelihood you are to see brokenness.
And then at Q2 (2 bits per parameter) or Q1, the model falls apart completely. Parameters collapse to zero easily. You start seeing "all work and no play makes jack a dull boy” sorts of behavior, with intense and unscrutinized repetition, followed by a hard stop when it just stops working.
And quantization is a parameter that a model vendor can turn relatively easily. (they have to regenerate the model from the base with more quantization, but it's a data transformation on the order of running a terabyte through a straightforward and fast process, not like training).
If you have 1000 customers and enough equipment to handle the requests of 700, going from bf16 to q8 is a no-brainer. Suddenly you can handle the load and have a little spare capacity. They get worse results, probably pay the same per token (or they're on a subscription that hides the cost anyway so you are even freer to make trade-offs. There's a reason that subscription products are kinda poorly described.)
It's also possible for them to vary this across a day: use models during quieter periods? Maybe you get an instance running a bf16 quantization. If you use it during a high use period? You get a Q4 model.
Or intelligent routing is possible. No idea if anyone is doing this, but if they monitor what you send a bit, and you generally shoot for an expensive model for simple requests? They could totally substitute a highly quantized version of the model to answer the question.
There are •so many tricks• that can be pulled here. Some of them very reasonable to make, some of them treading into outright misleading or fraudulent, and it's weirdly hard to draw the line between them.

Alibaba and China Telecom launch a data center in southern China that is powered by 10,000 of Alibaba's Zhenwu chips designed for AI training and inferencing (Arjun Kharpal/CNBC)
https://www.cnbc.com/2026/04/08/china-alibaba-data-center-ai-chips-zhenwu.html…

Alibaba launches data center with 10,000 of its own chips as China ramps up AI push
Alibaba and China Telecom launched a data center in China designed for AI training and inferencing.

W Turynie było nadzwyczaj pusto - pogoda taka se, ale dobra, żeby zostawić Freje i pojechać na kawę Bicerin w kawiarni Bicerin - gorącą czekoladę z kawą z śmietaną. Bardzo dobra, ale lepiej by weszła zimą.

Pojechaliśmy jescze zobaczyć muzeum Lavazza - opowiadającą historie od sklepu kolonialnego z końcówki XIX wieku, aż po dzisiejsze imperium kawowe. Ogólnie fajnie - wiadomo, że kilka kwestii przemilczeli, ale można było zobaczyć rodzinne eksponaty, proces technologiczny i ciekawe projek…