Mãdālin VP

614 posts

Mãdālin VP banner
Mãdālin VP

Mãdālin VP

@CTOxAI

AI Conductor. Chef. Cooking™️

Romania Katılım Şubat 2011
19 Takip Edilen355 Takipçiler
Sabitlenmiş Tweet
Mãdālin VP
Mãdālin VP@CTOxAI·
Introducing @GitHub Copilot plugin for Claude Code. Ask Copilot questions, delegate background tasks, or get code review without leaving your Claude Code session. Works with your existing GitHub Copilot subscription. /plugin marketplace add mvpasarel/gh-copilot-plugin-cc
dominik kundel@dkundel

I built a new plugin! You can now trigger Codex from Claude Code! Use the Codex plugin for Claude Code to delegate tasks to Codex or have Codex review your changes using your ChatGPT subscription. Start by installing the plugin: github.com/openai/codex-p…

English
1
0
1
478
Ivanka Trump
Ivanka Trump@IvankaTrump·
Most of us spend years trying to change outcomes without examining the internal framework producing them. This article gets to the root by examining and then stripping away the conditioning that keeps you from becoming fully yourself and finding your bliss. Great read @thedankoe !
DAN KOE@thedankoe

x.com/i/article/2010…

English
513
1K
8.7K
2.3M
Mãdālin VP
Mãdālin VP@CTOxAI·
@yacineMTB @sama There is no such thing “as many kids as you can”. You should always have one more, see how that goes, and if that works out, have one more. You’ll be surprised how many you CAN have
English
0
1
1
386
kache
kache@yacineMTB·
Being a parent is great. You guys should have kids. I really mean it. You guys should have as many kids as you can
English
210
108
2.4K
255.5K
Philo Groves
Philo Groves@PhiloGroves·
Before the agents became reliably autonomous, we chatted with them in a terminal. Their context could only fit a million tokens (max). They were slow. They had “hallucinations”. We inspected their every thought. We watched their every output. The mid-20s were weird for us all.
English
22
79
2K
405.8K
Mãdālin VP
Mãdālin VP@CTOxAI·
You dont even need offline models. As soon as SpaceX and @elonmusk buys @cursor_ai everyone will get access to cutting edge models.
Julien Chaumond@julien_c

This is where we are right now. And i’m not gonna lie it feels pretty magical 🧚‍♀️ Qwen3.6 27B running inside of Pi coding agent via Llama.cpp on the MacBook Pro For non-trivial tasks on the @huggingface codebases, this feels very, very close to hitting the latest Opus in Claude Code, or whatever shiny monopolistic closed source API of the day is. In full airplane mode. Most people haven’t realized this yet. If you have, it means you have a huge headstart to what I call the second revolution of AI. Powerful local models for efficiency, security, privacy, sovereignty 🔥

English
0
0
0
26
Mãdālin VP retweetledi
Dr. Parik Patel, BA, CFA, ACCA Esq.
Dr. Parik Patel, BA, CFA, ACCA Esq.@ParikPatelCFA·
Ladies if your boyfriend uses the Claude Code VSCode extension instead of the terminal tool that’s not your boyfriend that’s your girlfriend
English
165
294
6.1K
537.2K
Mãdālin VP retweetledi
Yann LeCun
Yann LeCun@ylecun·
Dario is wrong. He knows absolutely nothing about the effects of technological revolutions on the labor market. Don't listen to him, Sam, Yoshua, Geoff, or me on this topic. Listen to economists who have spent their career studying this, like @Ph_Aghion , @erikbryn , @DAcemogluMIT , @amcafee , @davidautor
TFTC@TFTC21

Anthropic CEO Dario Amodei: “50% of all tech jobs, entry-level lawyers, consultants, and finance professionals will be completely wiped out within 1–5 years.”

English
1.2K
2.8K
21.4K
4.1M
Mãdālin VP
Mãdālin VP@CTOxAI·
Those issues have become trivial, and well below my concern.
GIF
Uncle Bob Martin@unclebobmartin

That was interesting. I have two comments. 1. Shed your ODS because you badly misrepresented the O in the context of Clean Code. 2. You seem to think I have changed. I have not. The internal forces that caused me to write the Clean Code book are the same forces that are driving my conclusions about agentic development. For me it is a natural evolution not a revolution. P.S. While I think experiments would be interesting, I don’t care about static or dynamic typing anymore. Those issues have become trivial, and well below my concern. The AI can worry about that.

English
0
0
0
21
Claude
Claude@claudeai·
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
English
4.1K
15.1K
148.5K
63.7M
Pardheev :)
Pardheev :)@pardheevvv·
@claudeai Designers watching Claude take away their jobs
English
12
15
311
45.2K
Mãdālin VP retweetledi
@levelsio
@levelsio@levelsio·
I had to fact check because it sounded too unbelievable but it's true: Romania in 1981 just like the EU presented food austerity measures as "more healthy eating" In EU's case it's "meat is unhealthy" but the underlying austerity reasoning is same In both cases it's blatant propaganda to make people consume less!
@levelsio tweet media
English
17
64
814
78.9K
Nikita Bier
Nikita Bier@nikitabier·
Pour one out tonight for the reply bots. This week is going to hurt 🪦
English
4.5K
1.9K
30.5K
2.3M
Oren Melamed
Oren Melamed@OrenMe·
“Doctor, can I get a 2nd opinion” - the @GitHubCopilot version, and it is now baked in the harness I love this approach and using it usually with fleet or even manually asking a few sub agents to do quick code review each with another model The fact it is now built in just makes it more natural to use
Gerald Versluis@jfversluis

New in GitHub Copilot CLI: Rubber Duck 🦆 A second model from a different AI family reviews the agent's plan before execution. Claude Sonnet + GPT-5.4 review closes 74.7% of the gap to Opus. Catches the confident mistakes that compound. Try: /experimental github.blog/ai-and-ml/gith…

English
1
2
18
2.4K
Mãdālin VP
Mãdālin VP@CTOxAI·
@burkeholland @github But you can also delegate tasks because Premium Requests is better than current CC pricing and usage
English
0
0
0
198
Burke Holland
Burke Holland@burkeholland·
The @GitHub Research folks released a "Rubber Duck" agent for the Copilot CLI. Automatically get a review from a model from a different AI family. And their data shows that yes, this does in fact help. Quite a bit.
English
25
68
469
240.8K

Keşfet

@CaudilloXIV @elonmusk @IvankaTrump @thedankoe @yacineMTB @sama @PhiloGroves @cursor_ai