Building AI Agents solo can feel isolating when you hit technical roadblocks or need fresh perspectives on your approach. Join us for LangChain Hacking Hours at our office — a focused co-working session where you can make real progress on your projects while getting direct
CODE
-
Adding Image to Image Option with FLUX.1-Kontext-dev to Anycoder
By
–
working on adding a image to image option with FLUX.1-Kontext-dev to anycoder for vibe coding would this be useful?
-
GPT-5 Now Available in LangSmith Playground with Cost Tracking
By
–
🔥GPT-5 is now in LangSmith Playground w/ built-in cost tracking.
— LangChain (@LangChain) 8 août 2025
Available models:
• gpt-5
• gpt-5-mini (now default)
• gpt-5-nano
Start building with the latest models → https://t.co/fRKTx58e2V pic.twitter.com/jdFtoJvOpRGPT-5 is now in LangSmith Playground w/ built-in cost tracking.
Available models:
• gpt-5
• gpt-5-mini (now default)
• gpt-5-nano Start building with the latest models → http://
smith.langchain.com/playground -
OpenAI API Compatibility Breaking Affects Research Projects
By
–
The APIs remain but the locus of use for OpenAI has been the ChatGPT interface. I have a whole prompt library for previous models, now I don’t know which ones work. People had research projects, school assignments & training programs built around them. So weird to break them all.
-
Cursor vs VS Code: AI Code Editing Tools Comparison
By
–
I'm not the right person to answer that because I've hardly explored Cursor – I use VS Code with Copilot or Zed for most of my text editing
-
ChatGPT Interface Optimization for GPT-5 Performance
By
–
Make sure you're using the ChatGPT interface directly. Most of the agent/code harnesses are not optimized for GPT-5 yet, so performance will seem worse than it actually is.
-
Nasdaq Accelerates AI Model Deployment Through Hackathon Innovation
By
–
When demand surged, Nasdaq kept pace. AI adoption moved at record speed, with the most effective hackathon “hacks” propelling Nasdaq’s entire roadmap. Now, teams across Nasdaq work smarter—deploying and adapting AI models in minutes, not weeks.
-
LangChain Enables Citable Search Results with Claude Models
By
–
LangChain supports Claude Opus 4.1 and Sonnet 4’s citable search results — now GA on the Anthropic API and Vertex AI. With this update, you can: • Return search results with built-in titles and source links • Automatically link citations to the tool call that generated them
-
GPT-5 Enables Single-Shot Code Generation for Web Apps
By
–
GPT-5 writes code that just works in single shot (most of the times!) And @emergentlabs really makes it easy to integrate everything and deploy your app in matter of mins. Build your first web app with GPT-5 now at http://
emergent.sh.
