Mike Bird

what did you ship?

If we can fork it, you can't control it

@gnukeith Should use @bitwa

Just so I understand what is going on, this would be giving the agents access to passwords? Is that not a security concern..? Like every integration thingy becomes an attack vendor, no? Am I overthinking this?

@sadasant @Teknium @thekitze @Teknium you should read some of Daniel's writing. I've never met him but think he might be right

@Teknium @thekitze Hire me. I’ll make people like it.

in theory this sounds great but i highly doubt that any agent works properly at this point ... my money is still on the lobster getting better

@0xSero open source will win.

Open source must win.

Fundraising is hard... so we packed the best investors in the world into one room in Waterloo. Pitch investors from @GarageCapital, @pearvc, @firstround, @inovia, @AforeVC, and more at the Akatos Symposium Showcase on March 20. If you're building something big and ambitious, apply below ↴

This is the question you should ask everyone who hypes an AI tool Separates the grifters from the operators

@kubla can we mute emojis? Blocking '🚨' would be very effective too

I muted the word "BREAKING:" (with the colon) and my experience of X instantly improved

We can disrupt everything

@nlw has this energy

But like....what is the goal of this? What does "holding them accountable" even mean? Are you going to mandate that companies can't use AI? Or that they can't fire people? I'm sympathetic to the issues and think we need more engagement around what's going to be a very disruptive middle period between two paradigms, but this doesn't say anything and doesn't aim for anything.

@Teknium Would love to make one with someone from the @NousResearch team. Let's get it on @ToolUsePodcast

Will give some nous portal credits to the first few good video tutorials that go up on youtube! Tag me (and this person!) Cover installation, setting up gateway messengers, tips and tricks, etc!

@julianeagu @databricks @freddiev4 @QuotientAI Amazing! Congrats to the team!

Quotient is joining @databricks! @freddiev4 and myself started @QuotientAI in 2023 with a dream and a hunch that the next era of AI will be unlocked by systems that can measure, evaluate, and improve AI in the real world. Over the past couple of years, we partnered with companies ranging from AI-first startups to Fortune 500 enterprises. They used Quotient to monitor AI systems in production, ensure their agents met strict enterprise policies, and reinforcement fine-tune agents to consistently achieve double-digit performance gains. We built it all at the bleeding edge, with a small team that started in Boston, Massachusetts. Joining Databricks gives us the scale and resources to take this much, much further. Very grateful to our team, investors, customers, and everyone who supported us along the way. We couldn’t be more excited for what’s next. Onwards!

No we absolutely do not. This would just be torching money. There is zero percent chance that the Canadian government could develop anything of value in AI.

No we absolutely do not. This would just be torching money. There is zero percent chance that the Canadian government could develop anything of value in AI.

Canada Needs Nationalized, Public AI schneier.com/blog/archives/…

@LottoLabs Great! Following along to see how it works for you. I'm eager to find the combo of OSS models to maximize performance of general tasks via HA

I haven’t pushed it too hard yet, but anything I’ve had done w/ Hermes has worked. I’ve made some simple monitoring and reporting skills that run w/ cron, had a simple database built out with automated data labeling and summarizing. When I have more time I’m going to see if it can do a full training run from scratch on a simple architecture that’s mainly my use case.

Using Hermes agent and qwen 3.5 27b locally makes me fully realize how much personal data we are feeding the big labs

Build smarter, not harder. You don't need to spin up new vector indexes for every user. If you're building a multi-tenant RAG app, you need to master namespaces. Senior Developer Advocate Arjun Patel explains why you should partition your index to scale: 🔹 Isolation: User A queries User A's data. Period. 🔹 Efficiency: No more "server sprawl." One index, thousands of tenants. 🔹 Performance: Pinecone scales writes/queries independently so latency stays low. Check out the full conversation with @MikeBirdTech on @ToolUsePodcast that covers sparse/dense embeddings, reranking, Pinecone’s Claude Code plugin, and more: youtube.com/watch?v=36FDCi…

@eoghan Wonder what happens if a dev at WebMD uses AI coding tools?

How dare poor people get free medical advice

@altryne @Teknium @Gavriel_Cohen Is the comparison incorrect, incomplete, or accurate?

@Teknium @MikeBirdTech Is the only way to promote your agent now is to shit on Openclaw? Cc @Gavriel_Cohen

Quick comparison of Hermes Agent's memory system compared to OpenClaw

Acting conscious is not consciousness