Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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... show more

🚨 AI News | TestingCatalog

73,388 subscribers

142,411 views • 4 months ago •via X (Twitter)

News & Politics Science & Technology Finance

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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 annotations

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 annotations

atomicbot.ai

607,115 views • 4 months ago

We put grok 4.5 and opus 4.8 head to head on the same browser task, on Hyperbrowser Sandboxes. We then asked it to open a page in a real sandboxed browser and pull the title. Grok build on Grok 4.5, Claude code on Opus 4.8, identical setup. Grok 4.5 came out ahead ↓

We put grok 4.5 and opus 4.8 head to head on the same browser task, on Hyperbrowser Sandboxes. We then asked it to open a page in a real sandboxed browser and pull the title. Grok build on Grok 4.5, Claude code on Opus 4.8, identical setup. Grok 4.5 came out ahead ↓

Hyperbrowser

406,488 views • 2 months ago

SOMEONE MAPPED CHAOS INTO A NAVIGABLE SPACE AND YOUR HERMES AGENT NEEDS THE SAME THING thousands of chaotic data points, each given a position, navigation becomes instant because the structure does the work your vault is the same chaos, hermes lands in it and opens files at random because nothing tells it where to start one index file per major folder with a clear starting point changes everything 2 minutes per task drops to 10 seconds, same agent, same model full breakdown in the article below ↓

SOMEONE MAPPED CHAOS INTO A NAVIGABLE SPACE AND YOUR HERMES AGENT NEEDS THE SAME THING thousands of chaotic data points, each given a position, navigation becomes instant because the structure does the work your vault is the same chaos, hermes lands in it and opens files at random because nothing tells it where to start one index file per major folder with a clear starting point changes everything 2 minutes per task drops to 10 seconds, same agent, same model full breakdown in the article below ↓

leopardracer

23,629 views • 3 months ago

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!

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!

🚨 AI News | TestingCatalog

46,013 views • 4 months ago

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.

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.

Dan McAteer

160,974 views • 4 months ago

We built a plugin that gives Jev a browser in Cline, and have been blown away by the results. 1. Install it in our new desktop app: Customize > Marketplace > Plugins > search 'jev-browser' 2. Create a Vercel AI Gateway API key, then save it to ~/.cline/plugins/cline-jev-browser.config.json as {"gateway": {"apiKey": "..."}} and restart Cline. 3. Ask any browser task and it will launch Chrome in the background to complete it.

We built a plugin that gives Jev a browser in Cline, and have been blown away by the results. 1. Install it in our new desktop app: Customize > Marketplace > Plugins > search 'jev-browser' 2. Create a Vercel AI Gateway API key, then save it to ~/.cline/plugins/cline-jev-browser.config.json as {"gateway": {"apiKey": "..."}} and restart Cline. 3. Ask any browser task and it will launch Chrome in the background to complete it.

Cline

80,115 views • 13 days ago

Rewarding real product usage just got a little more interesting. NeoSoul is now LIVE on ActionFi. Your task? Create your first AI agent on NeoSoul. Complete the task. Meet the success criteria. Get rewarded. You've got 2 weeks. Head to Action Model, open the ActionFi tab, and go take action.

Rewarding real product usage just got a little more interesting. NeoSoul is now LIVE on ActionFi. Your task? Create your first AI agent on NeoSoul. Complete the task. Meet the success criteria. Get rewarded. You've got 2 weeks. Head to Action Model, open the ActionFi tab, and go take action.

Action Model

33,987 views • 1 month ago

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 row

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 row

𝖗𝖊𝖉✞

248,242 views • 7 months ago

The key to using only 1% of the weekly limit with GPT-6 Astra is organizing the task first with a clean prompt, only the necessary context and hard constraints like a 10-test cap and a stop-and-report rule if the same approach fails twice. → No scope expansion allowed in the prompt → If the same approach fails twice, try a different strategy instead of repeating → Hit 10 tests without success, stop and report what's failing instead of working around it → A harder follow-up task took 9.5 minutes and used 6% of the weekly limit on Plus

The key to using only 1% of the weekly limit with GPT-6 Astra is organizing the task first with a clean prompt, only the necessary context and hard constraints like a 10-test cap and a stop-and-report rule if the same approach fails twice. → No scope expansion allowed in the prompt → If the same approach fails twice, try a different strategy instead of repeating → Hit 10 tests without success, stop and report what's failing instead of working around it → A harder follow-up task took 9.5 minutes and used 6% of the weekly limit on Plus

0xMarioNawfal

50,736 views • 18 days ago

Hermes Agent beat OpenClaw on Grok 4.5 in a real security audit. — Hermes: $4.63 / 1.42M tokens / 5m 4s — OpenClaw: $1.31 / 396K tokens / 2m 55s So why would you ever pay more? Because Hermes caught what OpenClaw missed. It flagged the AWS key as a copy-paste docs example instead of a live secret, found the file's path sitting in shell history, and shipped a per-provider rotation checklist that actually closes the incident. OpenClaw was faster, cheaper, and cleaner to read, but it measured the keys without ever asking whether they were real, and stopped at the file instead of chasing where the leak could spread. The honest verdict: OpenClaw is the efficient baseline, perfect when you want a quick, cheap scan. Hermes is the one you want when it actually matters, because it spends the extra time and tokens on judgment, not padding.

Hermes Agent beat OpenClaw on Grok 4.5 in a real security audit. — Hermes: $4.63 / 1.42M tokens / 5m 4s — OpenClaw: $1.31 / 396K tokens / 2m 55s So why would you ever pay more? Because Hermes caught what OpenClaw missed. It flagged the AWS key as a copy-paste docs example instead of a live secret, found the file's path sitting in shell history, and shipped a per-provider rotation checklist that actually closes the incident. OpenClaw was faster, cheaper, and cleaner to read, but it measured the keys without ever asking whether they were real, and stopped at the file instead of chasing where the leak could spread. The honest verdict: OpenClaw is the efficient baseline, perfect when you want a quick, cheap scan. Hermes is the one you want when it actually matters, because it spends the extra time and tokens on judgment, not padding.

atomicbot.ai

58,421 views • 2 months ago

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 @speedsolutions_ Dashboard.

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 @speedsolutions_ Dashboard.

Speedworks Training

64,756 views • 2 years ago

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 👀

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 👀

TestingCatalog News 🗞

69,484 views • 8 months ago

We just did the largest live deployment of interactive robots in history. Users online could ask the robot to do things it was never taught to do. A true foundation model, with 0 task-specific data and 0 task fine tuning. 1/10

We just did the largest live deployment of interactive robots in history. Users online could ask the robot to do things it was never taught to do. A true foundation model, with 0 task-specific data and 0 task fine tuning. 1/10

Enigma

203,338 views • 1 month ago

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.

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.

Muhammad Ayan

149,835 views • 9 months ago

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!

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!

WNBA

296,325 views • 1 year ago

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!

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!

kache

39,217 views • 2 months ago

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 🏠

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 🏠

Chris Ship

305,562 views • 1 year ago

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.

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.

Workshop AI

962,487 views • 5 months ago

A Carnegie Mellon student launched a Markov Chain model that reads the structure beneath the price and made $67,000 in three weeks on Polymarket. In his applied mathematics classes he studied Markov Chains - the same model physicists used to simulate neutrons in nuclear reactors. The same model describes how prices move on prediction markets. He wrote a Python script. > Takes 60 days of contract price history. > Builds a transition matrix - a map of how the price actually moves between states. > Runs 10,000 simulations in a tenth of a second. > Calibrates the result against data from 72.1 million real trades. The output is an exact probability and position size. No gut feeling. His first test day brought $3,400. A week later he improved the result and hit $17,000. His balance has now reached $67,000. full guide on how to build the same model - in the article below.

A Carnegie Mellon student launched a Markov Chain model that reads the structure beneath the price and made $67,000 in three weeks on Polymarket. In his applied mathematics classes he studied Markov Chains - the same model physicists used to simulate neutrons in nuclear reactors. The same model describes how prices move on prediction markets. He wrote a Python script. > Takes 60 days of contract price history. > Builds a transition matrix - a map of how the price actually moves between states. > Runs 10,000 simulations in a tenth of a second. > Calibrates the result against data from 72.1 million real trades. The output is an exact probability and position size. No gut feeling. His first test day brought $3,400. A week later he improved the result and hit $17,000. His balance has now reached $67,000. full guide on how to build the same model - in the article below.

Damir Akaza

136,105 views • 4 months ago