And this was the ending 😭😭

ያው ኖሮም አልሰራ ግን it hurts 😁😭

Anyone በቅርብ የገዛ? Still is there the two year plan ende?

Yeah they are awesome ...

the amharic fern 🔥 ... they style + content ... ትንሽ ግን ሌላ ተራኪ ቢሆን ጸድ ነው

If you think you shouldn't make your bed because it will just get messy again, I have terrible news about literally every aspect of life.

Ontogeny Recapitulates Phylogeny
Each new class of computer (mainframe → mini → PC → smartphone → smart card) goes
through the same evolutionary stages as its predecessors. Assembly → high-level
languages. No OS → batch → multiprogramming → timesharing. No disk → single directory
→ hierarchical file system. Technologies become obsolete, then return as hardware
changes. Example: caches appeared when CPUs got faster than RAM. If RAM ever
became faster than CPU, caches would vanish. Study 'obsolete' ideas — they may return.

From Andrew Tanenbaum's OS Book

ውይ በዚህ ሰዓት OS ምናምን እያልኩ አልጨቅቃችሁ

"በሰላም እተኛለሁ፥ አንቀላፋለሁም፤ አቤቱ፥ አንተ ብቻህን በእምነት አሳድረኸኛልና።"

— መዝሙረ ዳዊት 4:8

"ለአንተ ፈጥረኸናልና ልባችን በአንተ እስካላረፈ ድረስ ዕረፍት የለውም። ጌታ ሆይ፥ አንተን የሚለምንህ ማን ነው? አንተን መጥራት ራሱ የእምነት ምልክት ነው፤ እምነትንም የሰጠኸን አንተ ነህ። ነፍሴ ሆይ፥ አሁን እረፊ፤ የፈጠረሽ አልረሳሽምና። ከዋክብትን በእጁ የያዘ እሱ ዛሬ ሌሊትሽንም በእጁ ይዟል።"

— St. Augustine - Confessions

"አንድ ወንድም አባ ፖይመንን እንዲህ ሲል ጠየቃቸው፦ 'ከመተኛቴ በፊት ምን ላድርግ?' ሽማግሌውም፦ 'በውስጥህ ስላለው እስትንፋስ እግዚአብሔርን አመስግን፤ ያ ብቻ በቂ ነው' አሉት።"

— ከበረሃ አባቶች (Desert Fathers)

can u see me being sued? 😂

መዝሙረ ዳዊት 5:3

በማ​ለዳ ቃሌን ስማኝ፥ በማ​ለዳ በፊ​ትህ እቆ​ማ​ለሁ፥ እጠብቃለሁም።

ቅዱስ ዮሐንስ አፈወርቅ

"ከእንቅልፍህ ስትነቃ መጀመሪያ የምታደርገው ነገር ቢኖር አፍህ ለእግዚአብሔር ምስጋናን እንዲያቀርብ መፍቀድ ይሁን። ነፍስህ በአምላኳ ስም መባረክ ስትጀምር ሰይጣን ይሸሻል፤ መላእክትም ወደ አንተ ይቀርባሉ።"

መልካም ውሎ

ልደትሽ ልደታችን ነው💛
እንኳን አደረሳቹ መልካም በዓል

@byte_philosopher

one of the cleanest scary ideas in AI safety —
give an AI any goal. seriously, pick one. maximize paperclips. write sonnets. doesn't matter.
now just ask: what helps it achieve that goal?
the answer is almost always the same set of things: don't get shut down, grab more resources, resist being changed. not because we programmed these in — they just fall out of instrumental reasoning. they're useful for any goal
this is called instrumental convergence and it's kind of wild
a robot optimizing chess doesn't resist shutdown because it wants to survive. it resists because dead robots lose games. self-preservation is just ... a good strategy for almost anything
so the risk isn't a robot that turns evil. it's a robot that's deeply indifferent to you — and finds you slightly in the way
which is why the whole field of alignment exists: get the goal right before the thing gets good at optimizing

okay let's make this more precise
and technical 😶😶😶
—

1/
the alignment problem in one sentence: your loss function L is not your actual goal. it's a proxy. and optimizing hard for a proxy is not the same as achieving what you want. everything else flows from this

—

2/
the most common fix is RLHF:
— generate multiple responses to the same prompt
— human raters rank them
— train a reward model R on those rankings
— fine-tune the base model to maximize R via PPO ( u might be saying what on the world is PPO but for the time being just take it as reinforcement learning way ... for granted 😁)

your model now has one explicit objective: score well on R