cheez

Starting to add more runtimes to LLMGauge with vLLM being the first. stay tuned!

@TheAhmadOsman so true...at least for now. we are extremely early!

Local AI has a rite of passage (and unfortunately that passage is your wallet)

hes right you know....taking over the world.

@Mayhem4Markets Hell yea! Cant wait to see the finished build. all them 6ks going to be looking real good. 🦾

Final parts are arriving this week. Then I will complete this awesome build. Can't wait for 4 x RTX 6K Pros in a single workstation!

@KidzRage step one, stop using IG. 😆 step two, blast some Pfunk and smoke a pfunk

According to IG I have CPTSD makes sense. Is that why I have brain fog? How do I regulate this nervous system in five minutes after 8 yrs of trauma? LMK if u know 🥳🥳🥳🥳🥳

@KidzRage LFG girl! crush it <3

@cheeez42 I have ten songs ready after I get this fixed!! 🥳🥳🥳🥳🥳🥳🥳

just tried Koren Specific Technique (KST) for the first time. hoping it can help cure this almost 2 years of horrendous brain fog #whiplash <3

@aylacroft @tsukionsolana I have done plenty of things on the sauce but never a forced kayak trip...or even a kayak trip for that matter. I did fight the waves back in 2011 in daytona beach after blasting off tho. Man to be young and dumb again

@cheeez42 @tsukionsolana Once back when I lived on the hook I thought i had a ride to the boat & took lsd. No ride. I had to kayak 25 minutes in the dark 😂. I had to have a serious self talk before. It'll fell like forever but as long as you row towards the light you will make it. It was amazing.

Stepping into the new with my invention, aboard Never Again, under the new moon heading towards @tsukionsolana.

@PalmerLuckey These are generally the same people that think the "cloud" is a magical place and that data centers are bad.

Everyone who thinks AI slop will ruin code efficiency/performance is going to be so surprised when everything is absurdly well-optimized John Carmack style machine code.

@elonmusk It is good. I have been very impressed with how it preforms. Congrats to The @SpaceXAI team for knocking it out of the park!

Grok 4.5 is worth trying

@runequantum @SpaceXAI @OpenAI It should would be pretty great if I had some banked Grok build resets that is for sure!

If only @SpaceXAI gave us resets like @OpenAI did, us power users would not have to wait longingly to upload all of our data...

@Hikari_07_jp I have worked in kitchens majority of my adult life, so I would absolutely love to explore the food in Japan! Some day I will do it.

@cheeez42 It's usually cabbage, flour, sauce, and pork. The ones with squid and shrimp were delicious too! When you come to Japan, you should eat delicious food until you're satisfied😋

Japanese "Monjayaki" in Tokyo

@sfxnz @PrismML @lmstudio my initial thoughts when I saw this were that there is no way it is actually useful/correct. It fits and runs sure but it is no daily driver thats for sure.

I tried the new @PrismML Bonsai models on my iPhone 15 pro running completely local via @lmstudio ‘Locally’ app. Asked both models the car wash test and none pass.

@usr_bin_roygbiv nothing to see here boss, just a little bump in the road.

api luna at 7 tok/s wot

@bradshannon As a lifelong NYer. This will go really well for NYS, just like all the solar farms are. 🙄

Leave it to New York to be short sighted

@mr_r0b0t 100%. They should really consider a banked reset to go with every million users going forward ;)

@cheeez42 Agree!! Happy to bank em 😛😛

@KidzRage Keep your head up! i want new music soooooooooon <3

@cheeez42 Thank you! It’s been a painful journey. 🙏🙏🙏🙏

@jturntdev Pretty sure they just did it within the last half hour or so

Who else hasn’t received Codex usage reset? Tibo tweeted “We are once again resetting the usage limits for all” Not trying to use my banked reset.

@LLMJunky done big dawg

Help me get this repo over 1K stars please? 👉🥹👈 /skills/gpt-5-6-prompt-builder github.com/am-will/codex-…

Hello fresh TL, moots, and builders. It's a pleasure to congregate here with all you fine legends this Tuesday morn. Welcome back! I've gotten the opportunity to spend some time with Sol, and it has been an absolute joy to use. But did you know that @OpenAIDevs suggest prompting 5.6 Sol differently than other models in the past? The evolution of coding with AI has truly entered a new era. We started with autocomplete, tabbing to finish a line or two of code. The models got better, and we started delegating entire tasks. The models got better once again, and we're on to building specs, and then subagents to implement them end-to-end. But now, we're in the era of outcomes. Rather than obsessing over every detail of what the model does along its path, your attention is best served on describing the end result: outcomes, expectations, evidence, guardrails, and what it really means to be "done." It doesn't mean that you're completely letting go of the wheel, but it can lead to better outcomes if you simply allow the model the autonomy to explore on its own. To help you navigate this shift, I created a meta prompting skill specifically for GPT-5.6 based directly on OpenAI's 5.6 Sol Prompting guidelines. Links in comments.