@CodingWorkflow profile picture
Coding Workflow @CodingWorkflow

Automation next level.

Joined September 2025
  • Tweets 248
  • Following 65
  • Followers 17
Photos and videos
Still seeing in end of 2025 people assesing model capabilities in chat and one shots. If you don't get how agentic workflow work, adding the right tools. Then likely you will miss 2025 core revolution in AI. And it's now more multi models. #AI #2025 #Agentic
34
Coding Workflow retweeted
Sean Strong
@sean_t_strong
22 Nov 2025
What if your MCP servers could provide interfaces, not just tools & data? We're designing MCP Apps with OpenAI and MCP UI, an official MCP standard for how MCP servers can provide interactive interfaces: blog.modelcontextprotocol.io…
36
49
567
66,587
Deepwiki now faces a challenger: Google wiki. But I got addicted to Deepwiki MCP as feeds directly the agent. codewiki.google/ Announcement: developers.googleblog.com/en… Also they plan to integrate it into Gemini CLI, so expect an API. #AI #Deepseek #Google

Code Wiki

Code Wiki provides automatically generated, up-to-date documentation for your code. Stop wasting time on manual docs and explore codebase insights, API references, and architecture overviews instan...

codewiki.google
108
Coding Workflow retweeted
David Soria Parra
@dsp_
15 Nov 2025
MCP Specification 2025-11-25 Release Candidate: We have frozen the spec for the upcoming release of MCP. Upcoming additions are Tasks, enabling long running operations, and Client ID Metadata replacing Dynamic Client Registration as well as a lot of small ergonomics. Take a look and give us feedback in our discord and issues. We are happy to make changes based on feedback. We want to get this version right. modelcontextprotocol.io/spec…

Key Changes - Model Context Protocol

modelcontextprotocol.io
8
57
287
35,272
Use Colab directly in vscode, amazing from Google. github.com/googlecolab/colab… marketplace.visualstudio.com… #AI #Google #Colab

GitHub - googlecolab/colab-vscode: A Visual Studio Code extension for Colab.

A Visual Studio Code extension for Colab. Contribute to googlecolab/colab-vscode development by creating an account on GitHub.

github.com
71
Claude Code 2.0.37 killed CPU 100% in Devcontainer after using --teleport.
34
Owasp Released AIVSS a new method to assess risk for AI instead of CVSS scoring. Scores seem lower, which seem more logic in threat modeling. The topic is still a bit fuzzy and suffering from a lot of hype. aivss.owasp.org/ aivss.parthsohaney.online/ca… #AI #Security

OWASP AI Vulnerability Scoring System (AIVSS) | OWASP Foundation

OWASP AI Vulnerability Scoring System (AIVSS) on the main website for The OWASP Foundation. OWASP is a nonprofit foundation that works to improve the security of software.

aivss.owasp.org
1
27
Sonnet 4.5 have major flaws, when following plans. It manage always to create havoc, despite solid specs, SDK, docs all prepared and laid out. The least it do, is telling you all done while it's 40% completion. Bad for complex long tasks.
26
Helm 4.0 is out github.com/helm/helm/release… #Kubernetes #K8s #Helm

Release Helm v4.0.0 · helm/helm

The Helm Team is proud to announce the first stable release of Helm 4. New Features Helm 4 has numerous new features, but a few deserve highlighting here: Redesigned plugin system that supports We...

github.com
2
35
More than sure Claude Code Web have a "loop" detection. To detect when the model is unable to complete a task and start redoing/undoing stuck in sort of loop, unable to really finish the task.
42
Claude Code cloud died trying to fix some tests. It was no more responding until Codex provided it with clear direction. It was quite stalling, refusing to do anything! And the genius Sonnet 4.5 marked them skipped and said all done 5 times.
46
#Codex since few days starting using like crazy inline python scripts with very bad results. This is strange. Never noticed this before. Any one noticed this?
27
How to see that Kimi K2 is built on top of Deepseek: huggingface.co/moonshotai/Ki… @Yuchenj_UW

config.json · moonshotai/Kimi-K2-Thinking at main

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co
1
19
Nvidia latest GB300 is kicking! A full cluster system can get up to 1M t/s with Llama 3 70B which is not a small dense model or MoE. That's 62k t/s per node!! techcommunity.microsoft.com/… #AI #NVIDIA #INFERENCE

Breaking the Million-Token Barrier

Azure ND GB300 v6 Virtual Machines with NVIDIA GB300 NVL72 rack-scale systems achieve unprecedented performance of 1,100,000 tokens/s on Llama2 70B...

techcommunity.microsoft.com
1
53
DeepWiki is one of my favorite tools to explore and understand code on Github. But I found they had an MCP open and free! That's a real steal. Thanks #Cognition docs.devin.ai/work-with-devi… #AI #MCP

DeepWiki MCP - Devin Docs

How to use the official DeepWiki MCP server

docs.devin.ai
1
92
MCP/Tools can't be mapped to API 1:1. May sound easy shortcut for some API lovers, but AI models can use more efficiently API's thru wrappers. Doesnt' mean CURL is the solution! You need to help the model and steer it a bit. #AI #MCP
28
No one looking at #llama.ccp output? Or updating it? The Web UI had been there since a while! #AI
31
Great rex from Hugging face over Smol llm training: huggingface.co/spaces/Huggin… Thanks for sharing @huggingface #AI

The Smol Training Playbook - a Hugging Face Space by HuggingFaceTB

The secrets to building world-class LLMs

huggingface.co
32
Surprised to see AMD so close in the high end vs B200. TCO is close too for AMD. MI355is close. (inference here as training is another story). inferencemax.semianalysis.co… #AI #Inference

Open Source AI Inference Benchmark | InferenceX

Compare AI inference performance across GPUs and frameworks. Real benchmarks on NVIDIA GB200, B200, AMD MI355X, and more. Free, open-source, continuously updated.

inferencex.semianalysis.com
30
VLLM support sleep mode to allow faster models switching, which is practical in constrained GPU env while testing or to save on GPU when deploying multiple models. blog.vllm.ai/2025/10/26/slee… #AI #VLLM

Zero-Reload Model Switching with vLLM Sleep Mode

The multi-model serving problem: You have two LLMs that each fit on your GPU, but not both at once. Traditional solutions force a bad tradeoff:

vllm.ai
30
Load more