正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Building a harness to run scans with an agent. It is absolutely garbage. Completely useless. There’s literally 0 benefit to using it over plain Claude Code. Everything it can do, you can just do via Skills etc. Many were preaching the benefits of a harness, but I’m not sure.

solst/ICE of Astarte

32,110 subscribers

56,130 次观看 • 4 个月前 •via X (Twitter)

喜剧教育科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

DeepSeek Harness is an agent harness where every component is a plugin, built on Cordis for spatiotemporal composability. Run it via `npx deepseek-ai/dsh web` to get a local Web UI at port 3080. Explore it here:

DeepSeek Harness is an agent harness where every component is a plugin, built on Cordis for spatiotemporal composability. Run it via `npx deepseek-ai/dsh web` to get a local Web UI at port 3080. Explore it here:

GitHub Projects Community

19,201 次观看 • 22 天前

Claude Code can now go find the right skill itself, instead of you searching for one. it's called find-skills. a small package that plugs into Claude Code, and instead of you hunting for rest, you just describe the task and it searches the whole open skills ecosystem, finds the ones that fit, and installs them for you. > tell it what you're trying to do, in plain english > it scans the skills registry and maps your task to real skills > it pulls the right ones in and sets them up half the time you don't even know a skill exists for what you're doing. now you don't have to.

Claude Code can now go find the right skill itself, instead of you searching for one. it's called find-skills. a small package that plugs into Claude Code, and instead of you hunting for rest, you just describe the task and it searches the whole open skills ecosystem, finds the ones that fit, and installs them for you. > tell it what you're trying to do, in plain english > it scans the skills registry and maps your task to real skills > it pulls the right ones in and sets them up half the time you don't even know a skill exists for what you're doing. now you don't have to.

Alvaro Cintas

38,829 次观看 • 24 天前

The easiest way to find out which models you can run on your computer: Just run: - 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 - 𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲 𝘀𝗲𝘁𝘂𝗽 It profiles your machine and ranks the models across: - Speed - Accuracy - Intelligence - Memory required Finally, you can choose your favorite harness (Pi, OpenCode, Claude Code, Codex, etc.) to run with it. Get started here: (don't forget to star 🌟) I also wrote a detailed article on running your favorite harnesses with local models. The article is quoted below.

The easiest way to find out which models you can run on your computer: Just run: - 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 - 𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲 𝘀𝗲𝘁𝘂𝗽 It profiles your machine and ranks the models across: - Speed - Accuracy - Intelligence - Memory required Finally, you can choose your favorite harness (Pi, OpenCode, Claude Code, Codex, etc.) to run with it. Get started here: (don't forget to star 🌟) I also wrote a detailed article on running your favorite harnesses with local models. The article is quoted below.

Akshay 🚀

349,874 次观看 • 4 天前

Claude Code feels completely different once you install this. Anthropic quietly released an official plugin called claude-code-setup and it basically turns Claude Code from “pretty good” into an actual AI dev environment. It scans your project and recommends: → hooks → skills → MCP servers → subagents → automations Then sets everything up step-by-step for you. Most people are using Claude Code completely vanilla… which is why their experience feels messy. The real power comes from the ecosystem around it. Install: /plugin install claude-code-setup@claude-plugins-official Bookmark this before you forget it.

Claude Code feels completely different once you install this. Anthropic quietly released an official plugin called claude-code-setup and it basically turns Claude Code from “pretty good” into an actual AI dev environment. It scans your project and recommends: → hooks → skills → MCP servers → subagents → automations Then sets everything up step-by-step for you. Most people are using Claude Code completely vanilla… which is why their experience feels messy. The real power comes from the ecosystem around it. Install: /plugin install claude-code-setup@claude-plugins-official Bookmark this before you forget it.

Suryansh Tiwari

1,549,943 次观看 • 3 个月前

Ever watch an agent solve a problem with 100% confidence and get it completely wrong? You can fix it… if you catch it. But then you need to watch every… single… run. New paper: We show that a meta-agent can do this for you, so your agents get ~2x more done on their own. 🧵

Ever watch an agent solve a problem with 100% confidence and get it completely wrong? You can fix it… if you catch it. But then you need to watch every… single… run. New paper: We show that a meta-agent can do this for you, so your agents get ~2x more done on their own. 🧵

Weiyan Shi

63,558 次观看 • 2 个月前

pro tip: you can ask claude code to use ascii art to prototype layouts for you 👀 here is me using it to find a good layout to display the caloric deficit/surplus to users had it prototype in ascii before actually building it

pro tip: you can ask claude code to use ascii art to prototype layouts for you 👀 here is me using it to find a good layout to display the caloric deficit/surplus to users had it prototype in ascii before actually building it

Chris Raroque

67,048 次观看 • 8 个月前

Claude Tag is an amazing org-level harness. Ignore the haters. Do this right now: 1. Create a private channel 'you-claude-tag' 2. Start asking it questions about your work This is the best way to get started.

Claude Tag is an amazing org-level harness. Ignore the haters. Do this right now: 1. Create a private channel 'you-claude-tag' 2. Start asking it questions about your work This is the best way to get started.

Dan McAteer

32,853 次观看 • 2 个月前

Here is another big E-MOTO meetup by teenagers in Denver Colorado. They meetup all at the same time. Taking over everything. Not much you can do to stop this. It seems like many parents and adults are cool with it. Not sure what the police will do to stop this.

Here is another big E-MOTO meetup by teenagers in Denver Colorado. They meetup all at the same time. Taking over everything. Not much you can do to stop this. It seems like many parents and adults are cool with it. Not sure what the police will do to stop this.

Colorado 411

13,925 次观看 • 1 个月前

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 次观看 • 20 天前

WIRED magazine just gave a 10/10 rating to a piece of hardware for the first time in a decade. It is a robot vacuum. Meet Matic. You do not use an app to control it. You literally treat it like a pet. You can point at a coffee spill and say "Hey Matic, clean this." You can even tell it to "follow me" and it walks behind you. It spent 9 years in development to solve the biggest smart home problem: privacy. It has 5 cameras, but it processes everything locally on an Nvidia chip. Your data is deleted in real-time. Hardware is finally getting fun again.

WIRED magazine just gave a 10/10 rating to a piece of hardware for the first time in a decade. It is a robot vacuum. Meet Matic. You do not use an app to control it. You literally treat it like a pet. You can point at a coffee spill and say "Hey Matic, clean this." You can even tell it to "follow me" and it walks behind you. It spent 9 years in development to solve the biggest smart home problem: privacy. It has 5 cameras, but it processes everything locally on an Nvidia chip. Your data is deleted in real-time. Hardware is finally getting fun again.

shirish

2,010,021 次观看 • 26 天前

this is insane… they just connected Claude to Blender you can do 3D modeling by chatting with it

this is insane… they just connected Claude to Blender you can do 3D modeling by chatting with it

el.cine

74,702 次观看 • 5 个月前

We released physics-intern: a simple harness for science problems! It gets models like Gemini 3.1 Pro to go from 17.7 -> 31.4, thus beating GPT 5.5 Pro. The physics-intern harness can wrap any model and via dedicated subagent boost the performance of the vanilla reasoning models. While I think more and more of these harness capability gains will be absorbed into the models (like prompting tricks disappeared over time) there is a lot to be gained right now by building good scaffolds for those models and integrating tools well. Interestingly, the exception we found that GPT 5.5 Pro actually didn't benefit from the physics-intern harness! Read more about it here: PS: I think the Harness[Model] notation is kind of nice.

We released physics-intern: a simple harness for science problems! It gets models like Gemini 3.1 Pro to go from 17.7 -> 31.4, thus beating GPT 5.5 Pro. The physics-intern harness can wrap any model and via dedicated subagent boost the performance of the vanilla reasoning models. While I think more and more of these harness capability gains will be absorbed into the models (like prompting tricks disappeared over time) there is a lot to be gained right now by building good scaffolds for those models and integrating tools well. Interestingly, the exception we found that GPT 5.5 Pro actually didn't benefit from the physics-intern harness! Read more about it here: PS: I think the Harness[Model] notation is kind of nice.

Leandro von Werra

97,432 次观看 • 3 个月前

I’m going to keep using John Doyle’s likeness to sell ED medication for thousands of dollars and there’s nothing you can do about it

I’m going to keep using John Doyle’s likeness to sell ED medication for thousands of dollars and there’s nothing you can do about it

Will Sexton

70,401 次观看 • 2 个月前

I've been messing with connecting Claude and Framer over the last week and yeah... this is absolutely crazy. You can get Claude to optimise your site, create/edit styles, write content and a lot more. Here's how you can set it up in literally 2 minutes:

I've been messing with connecting Claude and Framer over the last week and yeah... this is absolutely crazy. You can get Claude to optimise your site, create/edit styles, write content and a lot more. Here's how you can set it up in literally 2 minutes:

Hamza Ehsan

66,936 次观看 • 6 个月前

I ABANDONED LOVABLE AFTER SEEING WHAT CLAUDE CODE CAN ACTUALLY DO basic generators are great for quick ideas but trying to build a premium site with Lovable feels like playing in a sandbox I gave Claude Code a few custom design skills instead 4 minutes later it built a premium design they would have quoted me $7,500 for the difference between generic templates and a skilled local agent is literally worth thousands grab the full guide below 👇

I ABANDONED LOVABLE AFTER SEEING WHAT CLAUDE CODE CAN ACTUALLY DO basic generators are great for quick ideas but trying to build a premium site with Lovable feels like playing in a sandbox I gave Claude Code a few custom design skills instead 4 minutes later it built a premium design they would have quoted me $7,500 for the difference between generic templates and a skilled local agent is literally worth thousands grab the full guide below 👇

Mr. Buzzoni

176,242 次观看 • 2 个月前

In St. Petersburg, here in Russia, a janitor who was cleaning snow from the roof of a five-story building (without a safety harness) fell but managed to grab an electrical cable. It literally saved his life. He survived with a very stiff arm.

In St. Petersburg, here in Russia, a janitor who was cleaning snow from the roof of a five-story building (without a safety harness) fell but managed to grab an electrical cable. It literally saved his life. He survived with a very stiff arm.

Chay Bowes

29,753 次观看 • 6 个月前

I still don't understand why everyone is not using this yet. Thanks to it, a year ago I increased my income to 17,000 dollars a month Andrey Karpathy, co-founder of OpenAI, published a simple idea that got 16 million views: stop using AI to write code, use it to build a second brain You point Claude Code to a folder, drop any source in there (an article, transcript, PDF) and Claude reads it, links it, and saves it into a living wiki of everything you know. It compounds like interest: the more you feed it, the smarter it gets Here is the gist: Install Obsidian, create a vault, open it in Claude Code Paste the file with Karpathy's wiki idea and tell Claude to build it Claude creates three folders: raw for sources, wiki for its pages, CLAUDE which runs everything Drop any source into raw and say "ingest this" Ask questions across everything, forever Five minutes to set up, and you never start with an empty chat again The full step-by-step guide is in the article. Save to bookmarks

I still don't understand why everyone is not using this yet. Thanks to it, a year ago I increased my income to 17,000 dollars a month Andrey Karpathy, co-founder of OpenAI, published a simple idea that got 16 million views: stop using AI to write code, use it to build a second brain You point Claude Code to a folder, drop any source in there (an article, transcript, PDF) and Claude reads it, links it, and saves it into a living wiki of everything you know. It compounds like interest: the more you feed it, the smarter it gets Here is the gist: Install Obsidian, create a vault, open it in Claude Code Paste the file with Karpathy's wiki idea and tell Claude to build it Claude creates three folders: raw for sources, wiki for its pages, CLAUDE which runs everything Drop any source into raw and say "ingest this" Ask questions across everything, forever Five minutes to set up, and you never start with an empty chat again The full step-by-step guide is in the article. Save to bookmarks

Bober_smart

2,819,781 次观看 • 18 天前

“Alan Jackson is coming. Alright. You can delay it, you can deny it, you can do everything you can. You can try to apologize. You can try to get out in front of it. You can go on your own media tour… but it’s coming.”

“Alan Jackson is coming. Alright. You can delay it, you can deny it, you can do everything you can. You can try to apologize. You can try to get out in front of it. You can go on your own media tour… but it’s coming.”

Unfiltered Thoughts (Justice For John O’Keefe)

21,952 次观看 • 2 个月前