Australia has 59,700 kilometres of coastline and every centimetre has been protected by Pat Beach. 🧱🌟
The 22-year-old keeper makes EIGHT saves as the Socceroos open their World Cup with a 2-0 win over Türkiye. GET IN 🇦🇺
As a kid, my dad let me use his timesharing computer account and I unwittingly racked up hundreds of dollars of CPU charges. He wasn't angry, but I knew I'd made an expensive mistake. I avoided programming until I got an Apple ][. Then every CPU cycle was mine.
Today I'm not money-limited, but apparently still scarred. Because my willingness to screw around with AI coding went way up when I got a GPU box to run one locally.
Maybe you're the same? If you're AI-hesitant, splurge for a B200 card and run qwen/ollama or something. Then you're wasting money when you DON'T use it. You might think of something clever to do with it.
I read the RLM paper and it’s like, this is the simplest way to do solve a general problem, seriously it’s just this simple.
Love this kind of vibe. Last one like this for me was the ReAct paper from 4 years ago, and that one defined agent we use today.
I made a visualization to help understand how RLM works.
1990: Full specs, slow shipping.
2010: Minimal specs, "move fast."
2026: Full specs, instant shipping.
The era of the coder is being replaced by the era of the specifier. If you can't write the documentation, you'll be left behind.
An engineer at Anthropic wrote a spec, pointed Claude at an Asana board, and went home. Claude broke the spec into tickets, spawned agents for each one, and they started building independently.
When the agent is confused it runs git-blame and messages the right engineers in Slack. By Monday the agents finished the plugin feature.
That's one example of how the best engineers are shipping software right now.
Developers will soon orchestrate 50 AI agents in parallel and the difference between a good engineer & a great one would come down to specs.
You can't write a spec that holds up at that scale without genuinely understanding what you're building at a deeper level.
The next-gen developer who understands the fundamentals, can architect well and orchestrate agent is going to be a 1000x developer!
MCP servers in @code can now return a UI in chat thanks to the MCP Apps spec.
So I added a UI to the LIFX MCP server - get a control panel for the light if the AI can't figure out what you want from your lazy prompt.
@bansalg_ Looks great, will try, thanks. Shameless plug: I created an MCP Server to simulate a set of smart home and lifestyle devices, includes banking and groceries. Agent can check the fridge, compare it to last grocery order and restock, as an example. https://t.co/jz5Ip7z4W0
The Semantic Kernel and @pyautogen team have worked hard over the last few months to bring together the best of both frameworks for a much stronger developer experience (and to simplify the choice!). Today we are excited to release Agent Framework in public preview and get feedback.
Agent Framework brings the production ready focus of Semantic Kernel with full C#/Python support, as well as the nimble intuitive interface of AutoGen for rapid experimentation.
Some of the things that I think we have done really well:
- Middleware support - write hooks to control agent behaviour great for RAI, security, context engineering etc
- Support for Agents backed by various services - Azure Foundry Agent, OpenAI Responses, Google A2A agents, ofcourse with full MCP support
- Bring your own model, integrate with any agent
- Workflow API that lets you express business or application logic as a computation graph (this is something that was a weak spot for AutoGen)
Ofcourse, frameworks are only there to simplify aspects of your work - what matters is what you build!
To illustrate this, I’d try to do a “demo a day” over the next week to showcase capabilities of the framework. The video below shows an sample app (DevUI) that ships with Agent Framework for running and debugging your Agent Framework tools.
If you are starting a new AI Agent project - try it out!
British NIMBYism is truly a sight to behold.
“We are rejecting this solar farm, because one time I saw an electric vehicle on fire, which reminded me that decades ago a coal mining disaster killed lots of children”.
Congrats to the Class of 2025 for their superb A level results! Our students achieved 70.1% A* grades at A Level and 92.2% A*-A grades. 39% of students secured places at Oxford or Cambridge. On average students performed two-thirds of a grade better than expected in each subject.