Atomic Bot put Hermes and OpenClaw head-to-head on the... exact same task, running the same model (Qwen 3.6 35B) with the same goal: analyzing GitHub history, mapping growth spikes, and shipping a live dashboard in the browser. Key metrics to watch for 👀 > Time to complete the task > Tokens spent > Quality of the final result (dashboard in browser)show more

Hermes Agent vs OpenClaw using Qwen 35B Local Model... We asked agents to scrape GitHub star history for both tools, find what caused the growth spikes, build a live dashboard in the browser. MacBook Pro M5 Max 64Gb OpenClaw: 203k tokens, 12m 01s - wrote a bash script Hermes: 257k tokens, 33m 01s - wrote a SKILL.md OpenClaw hit GitHub API, got truncated responses, paginated through contributors, pulled star-history JSON, found a security incident in OpenClaw's history, fetched SVGs, fixed broken HTML from trimming, rewrote it clean. Hermes parallel tool calls across GitHub API, web search, and browser. Hit Google rate limit, auto-switched to DuckDuckGo. Fetched article contents, mapped viral moments, then built the dashboard. Both shipped a live dashboard with star growth charts and spike annotationsshow more

Laguna XS 2.1 performed on Qwen 3.6 35B's level... in Tetris building and ran 2x faster We tested two open models on a single RTX 3090 in the Poolside coding agent. The task was building a playable retro Tetris as one self-contained html file. Each model wrote and rewrote the game across 3 iterations Outputs: Laguna XS 2.1: 45K tokens, 158 tok/s Qwen 3.6 35B: 39K tokens, 81 tok/s The two Tetris builds are near identical. Poolside's Laguna has a couple of small visual bugs that Qwen 3.6 35B doesn't, but it built the same game twice as fast by its built-in DFlash speculative decodingshow more

Qwen 3.6 models are now 2.5x times faster on... Atomic Chat with new MTP speedups. > MTP drafts several tokens ahead and verifies them in one pass. The speedup depends on the memory moved per pass. Users can run Qwen 3.6 models locally via the open-source Atomic Chat to test them!show more

Codex Dynamic workflows are great. Try it out. 1.... Go to GitHub link below 2. Copy install instruction 3. Type /dynamic to invoke the skill Recreates the same orchestration logic as Claude Dynamic Workflows. > Generates orchestration script. > Spins up a swarm of subagents. > Enters /goal mode to complete the task. Free and open source.show more

When it's 7AM on a Monday and you're trying... to hype yourself up to live the same week for the 97th time in a rowshow more

Comet browser got a new "Act for me" option... in the sidebar, which can explicitly instruct Comet to take over your screen to execute the task. Explicit is always better than implicit 👀show more

1. Start with Google Head to Click ‘Delete’ at... the top Pick ‘All time’ and erase everything That’s where the real tracking happens. Not just in your browser.show more

This is running in my web browser on my... laptop. It's deterministic and running using webgpu Tonight; I have a /goal going where it is going to set up one of my 4090s as the authority server, and then test all the rollback code. Goal is 50k boxes simmed per user, up to 512 users. Massively multiplayer massively rigid body physics online games inside your web browser. Why the hell not, we've got the tokens to spare!show more

No. 1 picks in the building ✨ The last... time we saw Paige Bueckers and Aliyah Boston on the court at the same time was in the 2022 NCAA National Championship Game. Now, they go head-to-head for the first time professionally as the Dallas Wings host the Indiana Fever at 7:30pm/ET on ION!show more

So the Head of State, with his Head of... Government and Deputy Head of Government all in the same place on the same visit👇 King Charles was showing Keir Starmer & Angela Rayner his Nansledan new town development in Newquay - ahead of a PM announcement on new house building later this week 🏠show more

Nicki Minaj and cardi b in the same hotel…... at the same time? Oh how I can’t wait for cardi to mop the floor with her.show more

Most people see a Mac Mini as a home... computer. He saw a $300 invoice waiting to happen. A guy in Shenzhen figured out that every early-stage startup, every founder, every small business owner needs the same thing, someone to tell them what their competitors are doing and where the gaps are. Nobody wants to pay $2,000 for a research firm. Nobody wants to wait a week. He set up Hermes on a laptop. Local model. No API costs. First report took 15 minutes. He charged $300 and delivered same day. Then he bought another machine. Then another. Now there are 65 Mac Minis on metal shelves in his apartment. Each one runs its own agent. Each agent has its own skills folder that grows every time it completes a task. Month one: $3,200. Month three: $9,600. The tool: Hermes Agent. Free on GitHub. The model: Qwen 3.6 27B. Also free. Total monthly cost: $2 in electricity. The hardware paid for itself in week two. The shelves haven't changed. He just keeps adding machines.show more

Sprint training will never be the same again. You... can now use AI to analyse running your technique using a mobile phone. We have taken the best coaching eye’s in sprint and movement training and then downloaded them into the Speed Solutions Dashboard.show more

You don’t have to use one model (or one... provider!) for everything. With Workshop, you can combine frontier and local models in the same workflow. For example: Opus can be the main agent, and delegate specific tasks to Gemma 4 via subagents. Better quality where it matters. Better privacy, speed, and cost where it counts. One workflow, best model for each task.show more

Sanders up next, same situation, with the 2s. He... moved down the field with a pair of completions to Gage Larvadain and Harold Fannin. Third-and-1, Sanders finds Cade McDonald for the conversion at the 35 and spikes it in time for a last-second FG.show more

let me save you 3 hours of head scratching.... if you're running local models like Qwen3.5-35B-A3B through Claude Code via llama.cpp's Anthropic endpoint, the chain will break every 3 to 5 minutes. tool call fails. flow stops. you reprompt. it recovers. 2 minutes later it stops again. the model is fine. the harness chokes on local inference latency. switch to OpenCode. same localhost endpoint. same model. same GPU. the chain doesn't break. the tradeoff: OpenCode sometimes loops. the model forgets what it already read and repeats the same tool call. but a loop you can interrupt. a broken chain kills your momentum and you start over. watch both side by side. proprietary agent vs open source agent. same 3B model. different failure modes. pick your poison.show more

26/ Video explanation for dummies. Here's a montage of... the two videos with a timeline sequence. As I mentioned, the same people are present in the same place and at the same time.show more

PAYING PER MODEL IS THE DUMBEST THING IN TECH... RIGHT NOW i was paying 3x what i needed to for AI inference the grid lets you buy a quality spec instead of a specific model.. it routes every request in real time to the cheapest option that qualifies swap one url and your code keeps working exactly the same openai-compatible, one line to switch, 200M free tokens to startshow more

🚨INSANE: CHAINLINK ENABLES $29 TRILLION IN TRANSACTION VOLUME Per... the Chainlink metrics dashboard, $LINK's technology has facilitated a staggering $28.64 trillion worth of transactions since January 2022. This refers to volume enabled by Chainlink's famous oracle product. At the same time, its oracle secures some $61 billion in assets.show more