For my Mac friends here that don't want to use cloud solutions for Dictation and Meeting Transcriptions:
I was too annoyed with other options, so I built dettivo.com. One-time purchase, on-device, agent first, fine-tuned and fully optimised (59ms voice to insert).
Intelligence should be open, accessible, and ready to build with, empowering every developer, everywhere.
GLM-5.2 is now available to all GLM Coding Plan users, including Lite, Pro, Max, and Team plans.
docs.z.ai/devpack/latest-mod…
As our new flagship model, GLM-5.2 delivers powerful coding capabilities, usable 1M-context support, and continued strengths in long-horizon tasks.
API and Chatbot services will launch next week. The model will also be officially open-sourced next week under the MIT License.
The future of AI is open, and it belongs to the people.
‘What happens if/when the US shuts off our access to the best models?’ - 80% of the boardroom discussions across our portfolio I’ve been in this past year. These discussions are going to be fun now
Off to the 🏖️ in Italy for a week tomorrow, remoting to codex set up of course.
Got some OSS work done before leaving, flow-next.dev now also works in @cursor_ai and @grok build (in addition to the claude code and cursor)
It's been a fun journey with this thing that started off as a little plugin for my own usage and which has now grown into something that a ton of companies across Europe use as their only way to develop, both in terms of tooling and methodology.
For my Mac friends here that don't want to use cloud solutions for Dictation and Meeting Transcriptions:
I was too annoyed with other options, so I built dettivo.com. One-time purchase, on-device, agent first, fine-tuned and fully optimised (59ms voice to insert).
Experimenting with @openclaw's clawpatch in flow-next.dev for creating a semantic feature map that flow-next can then use during the its planning and capture phases -> sharper R-ID anchoring, less scope drift. Fully opt-in for now and provider-free by default. Try it out in v1.3.0
Yesterday was my first day at @OpenAI working under the amazing @romainhuet.
I've spent the better part of two years pushing the frontier of having models write code for you, shipping updates week after week for @RepoPrompt.
Transitioning from being a founder is never easy, especially when you have a community of amazing developers who invested so much in your tool.
Thankfully Romain worked hard to ensure that all those users would be taken care in the process, and if you're one such user, you should have an email waiting in your inbox with the details!
I'm very excited to be joining this talented team and work alongside everyone at OpenAI contributing to codex.
I had a chat about context agentic engineering with Eric the founder of Repoprompt and a member of the rate limited podcast.
I've learned a lot from Eric over the last 6 months, he has a great understanding of how to best utilise AI agents.
Enjoy
My book, Building Agentic Applications with CrewAI and MCP, is currently off 50% for the Memorial Day weekend!
Great timing, as chapter 5 was just released on Manning's Early Access Platform.
Helped a company achieve 50% efficiency gains after a one hour call just by restating the importance of agentic harnesses being able to verify their own work.