John Berry retweeted
Most of what people hate about data centers is factually incorrect or aimed at the wrong target.
The remaining concerns trace back to policy failures: unnecessary subsidies, sluggish permitting, antiquated power rules. Fix those, and the problems dissipate, says @scottlincicome.
ow.ly/poy050ZxMIK
John Berry retweeted
You gotta give Opus 4.5 a run in @code. It is that good.
John Berry retweeted
Introducing Gemini 3 Flash, our frontier intelligence model, available at scale for everyone. It excels at coding, tool calling, and is stronger than 2.5 Pro across most metrics!! ⚡️
Available in the API at $0.50 in / 1M tokens and $3.00 out / 1M tokens across.
John Berry retweeted
GPT-5.1, GPT-5.1-Codex, and GPT-5.1-Codex-Mini, the full suite of OpenAI’s latest 5.1-series models, are now rolling out in public preview in GitHub Copilot.
Try it out in @code.
github.blog/changelog/2025-1…
John Berry retweeted
Introducing Claude Sonnet 4.5—the best coding model in the world.
It's the strongest model for building complex agents. It's the best model at using computers. And it shows substantial gains on tests of reasoning and math.
John Berry retweeted
New in Visual Studio: GitHub Copilot Diagnostics for .NET 🧑💻
✅ Smarter breakpoints
✅ LINQ query help
✅ Exception summaries
✅ Deadlock insights
A smoother debugging experience, right in your IDE.
#GitHubCopilot (cont) msft.it/l/6015swg1R
What makes Claude Code so damn good
minusx.ai/blog/decoding-clau…
How to build a coding agent ghuntley.com/agent/
John Berry retweeted
Becoming a better writer also makes you better with AI.
I'm seeing this with devs using agents. Some are having a great time, others not so much. The difference is usually how well they write (e.g. give context).
Try documenting how you build software in AGENTS.md. It's hard!
Every token matters, so being concise is important. But you also have to find the right balance of determinism vs. style and preference.
You can still use type checking, linters, formatters, and other tools. Your job is steering the agent in the right direction and making clear which tools it has available (e.g. commands to run tests or linting).
But you likely have additional context about how you (or your team) prefer to build software that isn’t captured by those tools. For example, more on the system design and architecture.
A classic React example is: do you prefer a single component per file, or multiple components in the same file?
What level of abstraction do you want? You might tell the agent to only move things to a `lib/` folder if they have been used 3 times, otherwise just copy/paste.
Anyone doing this well? I'm on the hunt for AGENTS/CLAUDE/Cursor rules for inspiration. They should be concise, personalized, and very intentionally written.
John Berry retweeted
It's a few days early, but there's just so much good stuff out already. steipete.me/posts/2025/essen…
Vibe coding tips for experienced engineers - stochasticlifestyle.com/a-gu…
John Berry retweeted
GM!
Grok-4 coding is rumored to be pretty good!
Deepseek v3.1 is just a marginal improvement
Nano-banana is showing an astonishing capability to follow instructions well
John Berry retweeted
✨ Asynchronous agents are a game-changer for AI-assisted software development.
Read more and see real examples 👉 elite-ai-assisted-coding.dev…
John Berry retweeted
The @code team is hard at work improving the agent prompts - always.
If you've got Insiders you can try the new agent system prompt for GPT-5 today.
Let us know how it works!
I've been waiting for this one. Finally!
We’re introducing an all-new voice assistant that will provide the next-gen of help at home 🥁 🥁 🥁 Gemini for Home—enabling hands-free help for the entire household.
And that’s not all, @GeminiApp is also coming to your TV this fall!¹ goo.gle/3UBpTYL #MadeByGoogle
John Berry retweeted
Opus+Sonnet to build features, GPT-5 to verify and debug them (via codex-cli) is my corrent dream team.
Codex/GPT isn't an agent of many words but seems to dig deeper and finds the actual issue vs Claude's fake "I see the issue now" and randomly changing shit,.
John Berry retweeted
Our new @OpenAI open models
Our open models are here.
Both of them.
openai.com/open-models
Specs > Code. Great way to think about software engineering in an LLM world. youtu.be/8rABwKRsec4?si=sIyy…
John Berry retweeted
30 days, 15 AI Coding Agents, one prompt — and the results will surprise you!
Will Schenk, TheFocusAI, specially for Turing Post tested which coding tool could best build a Dockerized idea app with voting, notes, and file attachments.
You would not believe what he discovered about Cursor, v0, Copilot, and 12 others 🧵



























