Software Engineer | Agentic AI | Productivity
Joined September 2007
- Tweets 2,693
- Following 80
- Followers 1,535
- Likes 1,779
255 Photos and videos
Pinned Tweet
18 Jul 2025
First YouTube video is up! We walk through the different phases in a typical #MCP flow. #LLMs #Anthropic
Link in the thread!
1
45
1,841
FullContextAgent retweeted
Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities
- Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas
- MiniMax Sparse Attention scales context to 1M
- Natively Multimodal from Step Zero
API: platform.minimax.io
Token Plan: platform.minimax.io/subscrib…
🚀New! MiniMax Code: code.minimax.io
Weights & Tech Report in ~10 Days
560
1,154
10,971
4,944,722
FullContextAgent retweeted
Christabel Randolph - China announced its Global AI Governance Action Plan just 2 days after the U.S. announced its Action Plan. gov.cn/yaowen/liebiao/202507…
1
4
3
611
18 Jul 2025
First YouTube video is up! We walk through the different phases in a typical #MCP flow. #LLMs #Anthropic
Link in the thread!
1
45
1,841
3 Jun 2025
I only spent a couple of weekends playing with @n8n_io , and I'm already convinced that most utilitarian AI apps out there can be replaced with a couple of workflows that even people who've never coded can put together.
🧵
1
98
3 Jun 2025
...if they can make a workflow in n8n or Make that will get the job done then notify the user in the channels they are already using and familiar with (email, Slack, Discord, etc.).
1
76
3 Jun 2025
If you don't have a clear answer to this question, AI automation tools are coming for your niche.
58
22 May 2025
That’s it, playing Pokemon is officially the only benchmark that matters. Nice one @AnthropicAI
105
19 May 2025
Sharing what worked for me when using coding agents for debugging, or you know, vibe debugging 🙈
📃 Provide context
🧠 Use both thinking and standard models
🔍 Let the agent figure what to log and where
🔬 Give the agent access to logs
🔄 Iterate
More info in the🧵
1
197
19 May 2025
🔄 Iterate until the bug is identified and a solution is suggested. The agent might miss things on the first pass, so be ready to highlight critical sections they overlooked.
1
1
146