M

curious

[M @adhocanim]

@CliftonSellers you should not take advice from someone who thinks that tweet reflects well on sam.

[M @adhocanim]

@SpartacusNole56 @SlumRNA_Dog @thatguy3357 @kinzer_coleman do all boomers just bitch online about bitching online all day? your entire account is just pitching insults like a teenager who just learned to swear. lead poisoning has turned you into something indistinguishable from a foreign agitator bot. you betray your soul for nothing

[M @adhocanim]

@xiong_hui_chen @with_gene2626 have you guys abandoned the coder-next models?

[M @adhocanim]

@NVIDIAAI any ts numbers for dgx spark specifically?

[M @adhocanim]

@_sholtodouglas @1thousandfaces_ idk if anyone has mentioned but aside from the code stuff, the language ticks and slop is unbearable, the overuse of the :, “it’s not x it’s y”, the x is y: {answer}, it mentally fatiguing to parse through and clean.

[tippity @tippity]

timeline on bullshit today

[Pope Leo XIV @Pontifex]

Those who pray are aware of their own limitations; they do not kill or threaten with death. Instead, death enslaves those who have turned their backs on the living God, turning themselves and their own power into a mute, blind and deaf idol (Ps 115:4–8), to which they sacrifice every value, demanding that the whole world bend its knee. Enough of the idolatry of self and money! Enough of the display of power! Enough of war! True strength is shown in serving life. #Peace

[Khem Birch Society @NBABabySecret]

A “me and who?” so loud that it shatters it blows all the windows out of a skyscraper

[M @adhocanim]

@sudoingX is there a website or something where you are tracking these benchmarks for different hardware? also, have you seen the apex quants

[M @adhocanim]

@viemccoy yes

[M @adhocanim]

@cnakazawa i have been thinking the same thing chatgpt is the worst, actually unbearable to speak to. each one of these sends me into actual rage, i had to stop using gpt for my sanity.

[M @adhocanim]

@andrewchen wow i had an idea for something similar using my watch with the built in mic. will post if i get around to making it

[M @adhocanim]

@mudler_it @no_stp_on_snek @LocalAI_API you should quantize the Trinity model that just came out today, I would like to run it on my DGX spark.

[M @adhocanim]

@lompocus @arcee_ai why??

[M @adhocanim]

@snowiecone tim horton?

[M @adhocanim]

this whole industry is going to be a ping pong from the frontier labs seeing if they can out waste their rival until they realize they can’t and start clamping back and forth until the open source models catch up and devour these guys

[Tibo @thsottiaux]

Our Codex dashboards are showing increased rate of users hitting rate limits and since we don't fully understand why I have made the cautious decision of resetting the usage limits for all plans. Enjoy.

I also wanted to celebrate us finding a pocket of fraudulent accounts that we banned and have helped us regain some compute. The fight against abuse never stops, but it's important to mark the moment and make it a little shared victory.

[M @adhocanim]

@elliotarledge @0xSero the software side is super rough rn, but the community is sorting it out and some nvidia updates have fixed a lot. a lot of the issues come from the new hardware combination, but i don’t anticipate it being this rough for long.

[M @adhocanim]

@elliotarledge @0xSero lol me neither, the spark was painful to buy. but compared to the alternatives, this plus a mac will likely be cheaper than an an a6000 for the amount of ram, energy use and future proofing.

[M @adhocanim]

@elliotarledge @0xSero you can stream KV cache and get the best of both worlds, this lab did with the spark and a mac: https://t.co/cI6W3ZiWGj i’m hoping to do something similar when i can get my hands on a mac. or hopefully a chip specialized for inference comes out.

[愛国心の足りないなまけ者 にきめっ！ @tacowasa2nd]

最近ありがた迷惑なことにフォローもしてないアメリカ人のtweetが勝手に翻訳されて表示されるんだけど、その中で【MAGA】って赤い帽子被ってる人らがいて、みんなとてつもなく頭悪そうな人ばっかなんだよな。
あれなんなんだろ?

頭の悪い人につけるラベルかしら?