I've tried all (24) AI coding agents & IDEs 😵‍💫 [Cursor, Softgen, Windsurf, Wrapifai, Copilot, Lovable, Bolt, v0, Replit, MarsX, Claude, AmazonQ, Pear, Devin, Github Spark, IDX, Webdraw, Tempo, Cline, Continue, Databutton, Base44, Qodo, Aider] The Vibe Coding giga-thread:

7/ Appreciating How Far AI Code Editors Have Come Whatever tool you choose, we have to appreciate how much AI code editors have improved the developer experience. These tools have made complex tasks faster, streamlined workflows, and eliminated tedious manual work. It’s

Ever tried fixing a system only to have it push back? That’s the SDLC. Optimise one part, and new constraints pop up elsewhere. With AI coding assistants speeding up dev, we’re seeing new challenges emerge. Where are you feeling the pushback? Read more: annievella.com/posts/the-sdlc…

Excited to share our new tosem paper “The Future of AI-Driven Software Engineering,” Co-authored with Annie Vella Partha Roop Kelly Blincoe We envision how AI will transform Software Engineering doi.org/10.1145/3715003 #AI #SoftwareEngineering #AcademicTwitter #Research

Last week I saw the future of how we'll all work with AI. Logan (Google's AI Studio lead) was showing me Gemini's new“real time streaming” feature. He had his code editor open, and casually said via voice 'hey, should I change this function?' The clip below is wild - you have

digital-strategy.ec.europa.eu/en/news/second… Good to see the EU lean into AI innovation with these six AI Factories.

Many of us became software engineers because we found our identity in building things. Not managing things. Not overseeing things. Building things. With our own hands, our own minds, our own code. But that identity is being challenged by AI. annievella.com/posts/the-soft…

We're excited to announce our #YOWTLS25 keynote Annie Vella! She'll explore AI-assisted development's long-term impact, why keeping systems & orgs simple still matters, & how short-term gains turn into long-term costs in 'The Duality of AI in Software Engineering'

Cursor is now free for students. Enjoy!

Eleven v3 Alpha is a ChatGPT moment for text-to-speech. This AI model turns plain text into studio-quality voice acting in 70 + languages expressively. 10 wild examples:

Palantir CEO Alex Karp: “Those of us in tech cannot have a tin year to what is this going to mean for the average person” Dario Amodei is now joined by the Palantir CEO, who warns of major upheavals: “We have to will it to be, because otherwise we’re going to have deep

Dario Amodei never tires of outlining the serious impact on AI. Many now see him as an AI doomer, but he is simply trying to warn us about what is coming. Why is this so important? Let me explain:

A greater theory of system design: what’s wrong with modernity and post-modernity, how to survive the coming avalanche, and how to fix the major problems we are facing. Part one: Systems are Models. But what’s a Model?

Do you miss that spark you felt the first time code you wrote leapt off the screen and did something cool? I do. So I traced it back to its roots and wrote about why our craft still matters, even as AI types for us. annievella.com/posts/the-hear…

My next Universals paper [0] is out today! Unleashing the Power of End-User Programmable AI As a demonstration of what can be accomplished with contemporary LLMs, this paper outlines the high-level design of an AI-first, program-synthesis framework built around a new

RIP fine-tuning ☠️ This new Stanford paper just killed it. It’s called 'Agentic Context Engineering (ACE)' and it proves you can make models smarter without touching a single weight. Instead of retraining, ACE evolves the context itself. The model writes, reflects, and edits

New paper from Google is a major memory breakthrough for AI agents. ReasoningBank helps an AI agent improve during use by learning from its wins and mistakes. To succeed in real-world settings, LLM agents must stop making the same mistakes. ReasoningBank memory framework

Hearing from a lot of good founders that AI tools are writing most of their code now. Software engineers orchestrate the AI. They are also finding it extremely hard to hire because most experienced engineers have their heads in the sand and refuse to learn the latest tools.

We’re in a window right now where there’s a huge advantage if you’re a startup or a team that takes an AI agent-centric approach to workflows. Just in coding, we see an incredible spread between in productivity gains between two seemingly only slightly different types of

I stole this idea and now use it with every single employee. It’s the best illustration I’ve seen of teaching someone to be high agency. It says there are 5 levels of work: Level 1: “There is a problem.” Level 2: “There is a problem, and I’ve found some causes.” Level 3: