@netanelgilad Yeah, that takes you out of the flow. Admittedly, I think some of it made me feel better more than it made me more productive compared to using agents. The main problem is that constantly exercising judgment is exhausting. https://t.co/mALevvHWxn
It’s wild to think how much our role as software engineers is changing, and how that shift makes the core skills that always mattered even more important.
Highly recommend watching this talk by @tom_enden.
If AI can write the code, where do engineers create ✨ value?
That's the question @tom_enden tackles in this thought-provoking talk.
He explores how the role is evolving, which skills are becoming more important, and what may separate the engineers who thrive in the AI era from those who struggle to adapt.
Along the way, Tom connects ideas from influential voices such as @unclebobmartin, @karpathy, @paulg, @abeanstalker, and others to explore what engineering may look like in a world where AI writes the code.
If you're trying to understand where software engineering is headed - this talk is worth watching:
the Codex app now has themes
choose from some classics like Catppucin, Monokai, and Solarized. or try themes built with some partners from Linear, Notion, and OpenClaw among others. or make your own and share it
this was a bit of a personal side quest that i’ve been thinking about for a long time. we’re doing themes a bit differently! a few notes:
This is a huge problem that doesn’t get discussed enough. Building great products requires knowing what features not to build.
Today features are easy to add, but core maintainers are left with the hard job of evaluating and rejecting them.
sent this to the team today
everything great comes from being able to delay gratification for as long as possible
and it feels like we're collectively losing our ability to do that
📣 Open call to agent builders: Let's read agent skills from `.agents/skills`, so people don't have to manage separate folders per agent.
Today we pulled the trigger for Codex to read `.agents/skills`. Goal is to deprecate `.codex/skills`.
Pls like/tag/RT for momentum.
@Dean_La@nir_benz ההבדל זה שrule זה פורמט שונה בין כל coding agent, בזמן שסקילס הם פורמט שרוב הcoding agents הסכימו עליו, זה לא רק קובץ md זו תיקיה שכוללת קובץ md אבל גם קבצים נוספים כמו סקריפטים שנמצאים באותה התיקיה
You should commit the plan as part of the PR
Review the plan first. If the approach isn’t right, there’s no point reading the generated code. Iterate on the plan until it’s aligned, then I can call a remote agent to implement it.
PR should stand for 𝐏𝐥𝐚𝐧 𝐑𝐞𝐪𝐮𝐞𝐬𝐭
How do you make AI coding assistants truly useful?
It all comes down to context.
In this talk, @ranyitz dives into how @cursor_ai's rules let developers carry instructions across coding sessions - and how teams can take it further with aicm, a tool for sharing and managing rules across repositories.
👉 Watch the full talk on YouTube (Hebrew):
https://t.co/5DecsZm6JH
The https://t.co/uop4XiFxan microsite is live!
Think of it as a README for agents: a simple, open format for guiding coding agents.
It’s been awesome to work alongside peers from @AmpCode, @cursor_ai, @julesagent, @FactoryAI, and @roocode to bring this to life!