Europurr

@SoskaKyle I never understood these kind of trades. Just to take risk and pay shitload of fees for nothing.

Sell your BTC at 70200 and rebuy at 68900 for no reason

@JohnnyNel_ That's what I've been hearing, so going to give it a try. It even detects openclaw install and imports everything. love it

@vrloom most AI tools fall apart when you need consistency... Hermes actually handles task sequencing way better in my experience

I had had enough of OpenClaw. It's just not working, no matter what I do. Keeps failing every single task, doesn't check for progress, doesn't do what I told it to do, etc. Switching to Hermes.

@nikitabier It's too late for protests, trump isn't leaving

If gas goes up another ten cents, I’m going to a No Kings Protest.

@Teknium This is using Claude code, not actually powering Hermes with claude max subscription?

Did you know you can get your claude through hermes without any fancy tricks? Just type /claude-code In a new session. Hermes Agent can pilot a claude code session for you like it’s nothing. Give it a try It also doesn’t break all the self improvement loop and features of your hermes agent like openclaw’s approach does

@Teknium @AustenMakers Mine ended yesterday. Wtf

@AustenMakers Yes, it ends Tuesday

@mjtechguy @NousResearch Considering switching, I had enough of OpenClaw. Also the guy blocked me for some reason, eventhough I never interacted with him. Just followed. Weird guy.

Hermes agent by @NousResearch is elite. Setup was a breeze, integrations were super easy and it just seems to work. Way easier than openclaw was. Great work. Also, GLM-5-Turbo is cooking.

I accepted, by the way

Google literally left 2 of the access requests blank One will be your soul, and the other is what?

@SkyeSharkie Every generation there's always something that "will fry your brain brah"

@SkyeSharkie Reminds me of the same "brain fry" narrative, but from the early 90s when first cell phones appeared. They even sold fry protection, that you would attach on your phone to protect your brain. True story.

new "LLM psychosis" is apparently "you built too many things! how dare you!"

Claude MAX plan cannot be used for OpenClaw anymore? This is a HUGE mistake. There's no point in buying Max Plan anymore. I'd rather use Gemini API instead of Anthropic API.

@keithtyser Nemotron Super around 120 t/s Minimax m2.5 around 90t/s That's what I tested so far

@vrloom Just been doing some basic tests so far but gonna try with real agent workloads soon. Jealous of your setup. What kind of tok/s you getting for these models with the unquantized versions on your rig?

Been testing local LLMs on my M3 Ultra Mac Studio (96GB) w/ llama.cpp gemma-4-26B-A4B (MoE, Q8_0): 73 tok/s Qwopus3.5-27B (Q4_K_M): 27 tok/s gemma-4-31B (Q4_K_M): 25 tok/s gemma-4-31B (Q8_0): 18 tok/s The 3x speedup for a small decrease in quality makes the MoE a no-brainer choice IMO.

Finished building my beast at last: - WRX90 with Threadripper Pro 7985WX 64c/128t - 512GB ECC RAM - 4x RTX 6000 (384GB VRAM) - 2x RAID 5 with 4TB Samsung 9100 Pro (8x NVMe drives total) Able to run unqunatized Minimax M2.5 at 100 tokens/s

Arabs and Persians fighting each other in 2026 was not on my bingo card.

@bitcoinpanda69 fuck

Every man, at one point in his life, found a clothing style that worked for him somehow And from that point on, his style freezes, and he never dresses differently again He will wear that style forever, even decades after it has ceased to be fashionable

@bitcoinpanda69 Always wondered where are these pics coming from? Are they real?

Anyone know how to get the "date" part of their watch unstuck?

@bitcoinpanda69 I still think how in 1969 they were able to fly all the way to the moon, land there, take off, reconnect with the rocket and fly all the way back to earth without accidents and a single failure on the first try. But today they can barely circle around the moon, while we have AI.

How come the 1972 picture looks so much clearer and better

@notsofast Pretty sure this is a stolen tweet. Read this back in 2017 bull market.