OmniWired

LAST DAY! Back WAVERIDER today because you wanna help get the Dons back to the USA and make an EPIC NEW MIXTAPE!

@jun_song One of those laptop fans man. It’s not that hard. Think like a normie not a tech person

What would be the best way to lower the temperature of Macbook Pro? Still searching and couldn’t find the answer.

@kr0der I used a Kinesis Advantage for years; now I have a moonlander and a Glove 80. This latest one with a custom firmware I wrote

what keyboard does everyone have? i'm still in the apple magic keyboard gang

somebody made a huggingface model visualizer!! just plug in the url and explore at any granularity

@ivanfioravanti @NousResearch I’m doing the same these are my folders. But I ended up using almost always inbox. Haha

Hermes Agent + Obsidian is match in heaven! I'm dumping all info, meetings, ideas to hermes and I get back well formatted and when needed. This is so incredible! Thanks @NousResearch for this piece of AI magic!

Recommended Ailom: How AI Permanently Makes Everything Less Meaningful jsanilac.com/ailom/

MLX Qwen3.6-27B benchmark, here you can clearly see the difference in TFLOPs and Memory Bandwidth 🥇 M3 Ultra faster decode due to memory bandwidth 🥈 M5 Max faster prefill due to Neural Accelerators Wondering why memory usage is slightly higher on M3 Ultra 🤔

Hermes Agent now has multi-agent via the Kanban, new in v0.12.0. Agents claim tasks from a board, work in parallel, and hand off when blocked. You watch progress and unblock from one easy view instead of juggling terminals. We asked it to plan and make this video about itself:

@bnafOg Where did they say they didn’t use a single NVIDIA chip?

The entire training run used Huawei Ascend 910B chips. Not a single NVIDIA GPU. The US export control playbook — deny chips, slow Chinese AI — just got a significant data point against it.

China's top coding AI — #1 on SWE-Bench Pro — was trained without a single NVIDIA chip. Here's what that actually means:

@tetsuo_cpp Truly a passion project. Amazing engineering work; I truly hope they succeed.

Zed is beautiful. In the current age of AI slop and MS Teams Copilot 360 Express Suite, they’ve managed to build a company around software crafted with love and care. :-)

It’s shocking how much bad advice and misconceptions are around Local AI inference (running AI on your own local machine) We are early. But this is going to be an uphill battle in education.

Unpopular opinion: Your $20/month AI subscription is a lie. You’re living on VC handouts. OpenAI and Anthropic are burning billions to subsidize your productivity. That money will run out. When the subsidies dry up, the cost of "intelligence" will skyrocket. The play? Build your agents and workflows now while compute is pennies on the dollar. Lock in your advantage before the price tag catches up to the tech.

@tlbtlbtlb @paulg It’s a joke. Ok? But what you used the /btw command to steer?

I was a TA for intro CS, and watching Claude Code struggle is bringing back memories. It was fun spending time in the lab, looking over student's shoulders, asking "how about this line?" and that was the clue they needed. I wonder if coding agents could accept such hints.

I love YUC massive drops. Always nice to have dynamic and eclectic music

@jarekceborski Sovereignty. Also newer models are very close of the SOTA of less than one year ago. You don’t need max intelligence all the time

What’s a good use case for local LLMs, except privacy concerns?

Nvidia’s share in China is now 0%.

@ivanfioravanti Oh man I’m SO looking forward to the next version of Gemini.

For frontend I'm still relying on Gemini 3.1 Pro Preview, I bet that after Google I/O everyone will go back to runners up places. We'll see 😎

@dianalokada They build the noisy complex machines in the history of man second to none . So yes

i’m pretty confident semiconductor industry experts are aliens

@coinbureau That’s one expensive oil slick.

BREAKING: 🇺🇸US blockade strands 1.8M barrels a day of Iranian crude oil, per Nikkei. Iran's exports have collapsed from 1.85M bpd in March to just 567,000 bpd, a ~70% drop in weeks. Per Kpler, not a single Iranian tanker has successfully evaded the blockade. The White House says Iran is losing $500 MILLION per day in revenue. "If the blockade holds for another two months, Iran's oil revenues could crash to ZERO," Kpler reports.

@lucasmeijer Haha, so true, but then they will come back with “we are all latent space “ people find explanations in the weirdest of things

Everybody who thinks ai is conscious has to do a mandatory from scratch transformer implementation. There are only floats and multiplications.