Software engineering

Excited to announce Claude for Open Source ❤️ We're giving 6 months of free Claude Max 20x to open source maintainers and core contributors. If you maintain a popular project or contribute across open source, please apply! https://claude.com/contact-sales/claude-…

We’re launching Nano Banana 2, built on the latest Gemini Flash model. 🍌 It’s state-of-the-art for creating and editing images, combining Pro-level capabilities with lightning-fast speed. 🧵

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow. Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes. As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now. It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

I have AIDHD. The models are so good that I’m working on 5 different projects a day. At first it felt like distraction, but I’ve shipped more features and apps in the last 3 months than ever before. AI made building fun again. It’s a better programmer than me, so I can focus on creativity instead. I’m grateful to be alive at this moment. Decades from now, people will look back at this era as the best time to be a maker. Huge respect to the people building the models so idiots like me can just make stuff.

we’re still pricing ai tokens like software subscriptions but most companies will soon price them like labor $200/month feels expensive because we compare it to saas $50k/month will feel cheap when we compare it to headcount

We've rolled out a new auto-memory feature. Claude now remembers what it learns across sessions — your project context, debugging patterns, preferred approaches — and recalls it later without you having to write anything down.

Frame․io is falling apart. I wanted something better. Something simple, fast and reliable. I'm excited to introduce lawn․video, an open source video review platform. It flies. This video is not sped up at all. 100 gigs of storage, unlimited seats, $5/month.

Today's chapter of Agentic Engineering Patterns is some good general career advice which happens to also help when working with coding agents: Hoard things you know how to do https://simonwillison.net/guides/agentic…

Sometimes when a startup wants to escape from a bad organization that has some claim on their IP, it's worth rewriting their software from scratch in a "clean room." AI-assisted programming will make this much easier.

What Claude Code actually chooses if you ask it to build with no tool names anywhere in the input.

We've identified, responsibly disclosed, and confirmed 2 critical, 2 high, 2 medium, 1 low security vulnerabilities in Cloudflare's vibe-coded framework Vinext. We believe the security of the internet is the highest priority, especially in the age of AI. Vibe coding is a useful tool, especially when used responsibly. Our security research and framework teams are extending their help and expertise to Cloudflare in the interest of the public internet's security.

We're a few months away from a $500/month plan. maybe weeks.

New @openclaw beta's up! Again your fav: security, various fixes, I restricted hartbeat in DMs, you screamed, now it's a setting. Slack threads work better. Subagents as well. Telegram webhook is more reliable. https://github.com/openclaw/openclaw/rel…

Victor has joined Lovable as our first Forward Deployed Engineer. He spent 3+ years at Google working directly with enterprise customers - first as a Customer Engineer, then building AI solutions as a Generative AI Field Solutions Architect. He'll work with our enterprise customers to solve complex integration problems, build custom solutions, and feed what he learns back into the core product. When thousands of companies are trying to transform how they build software, you need people who've done this before at scale. We're looking for more wold-class Forward Deployed Engineers in SF, NYC, Boston, London, Stockholm. Apply on our website you're interested!

Omarchy 3.4 is out! Massive release with 61 contributors, three new themes, tailored Tmux, new screenshot flow, new agent features (claude by default + tmux swarm!), keyboard RGB theme syncing, and a million other things. https://github.com/basecamp/omarchy/rele…

Say hello to Nano Banana 2, our best image generation and editing model! 🍌 You can access Nano Banana 2 through AI Studio and the Gemini API under the name Gemini 3.1 Flash Image. We are also introducing new resolutions (lower cost) and tools like Image Search!

I'm Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code -- everyones' setup is different. You should experiment to see what works for you!

A few small updates today - we've added Moodboards and Personalization to Niji V7. We've released a much better web interface for Personalization. And we are sunsetting web rooms as we work on next-gen collab tools (which should make the whole site feel noticeably faster). Enjoy!

ShortKit lets every app roll their own TikTok-quality feed. Built by a former YT infra engineer, ShortKit's managed SDKs and video infra lets teams roll best-in-class short form video experiences, without needing their in-house video eng teams. Congrats on the launch, @neilbhammar and @michaelmahersel! https://ycombinator.com/launches/PXQ-sho…

New in Claude Code: Remote Control. Kick off a task in your terminal and pick it up from your phone while you take a walk or join a meeting. Claude keeps running on your machine, and you can control the session from the Claude app or http://claude.ai/code