ทวีตที่ปักหมุด
Manu Ebert
2.4K posts

Manu Ebert
@maebert
Technologist and Entrepreneur. Talk to me about Machine Learning, AI, and building teams driven by empathy and purpose.
San Francisco เข้าร่วม Kasım 2008
831 กำลังติดตาม2.7K ผู้ติดตาม

I spoke to @CliveThomp15983 at @NYTmag about the future of coding, the depths of my prompt files, and the daily fight to get Claude Code to not embarrass me.
nytimes.com/2026/03/12/mag…
English

@garrytan I remember fundraising a year ago and every investor was like “won’t people just use an MCP for this?”
There’s not a single problem that MCPs solved that couldn’t be solved without MCPs already.
English

MCP sucks honestly
It eats too much context window and you have to toggle it on and off and the auth sucks
I got sick of Claude in Chrome via MCP and vibe coded a CLI wrapper for Playwright tonight in 30 minutes only for my team to tell me Vercel already did it lmao
But it worked 100x better and was like 100LOC as a CLI
Morgan@morganlinton
The cofounder and CTO of Perplexity, @denisyarats just said internally at Perplexity they’re moving away from MCPs and instead using APIs and CLIs 👀
English

@the__shredator @conor_ai @hyperspell I love how a practice that is completely standard for professional TV people and literally called a prompter is considered weird for people who also have lots of other things to do than to pitch ideas on twitter
English

@conor_ai @hyperspell @maebert These weirdos can't even pitch an idea without reading from a prompt. Their brains have already been hijacked by an LLM
English
Manu Ebert รีทวีตแล้ว

introducing agent-to-agent hiring at @hyperspell
no resumes. no leetcode. you build an agent. our agent interviews yours
if you can build a great agent to do the job, that's the proof you can do the job
anyone can apply. we will interview every single agent
English

@conor_ai @hyperspell @maebert few questions:
1. after creating it is there a form through which we have to submit?
2. any poc we can use to contact
English

@thesayannayak I created my first web pages raw-dogging notepad.exe in the 90s. Syntax highlighting is for the feeble minded.
English

Our in-house AI agent at @hyperspell, Cubert, is telling it like it is. I just wish I could follow any of it.

English

Our in-house @openclaw bot, Cubert, keeps wanting to complain to HR about us. Finally we had to tell him.

English

come join us for coworking this saturday with the @hyperspell team
Lily yang@lilyyang169
This Saturday @smallest_AI is hosting Tipsy Co-Working with the support from @hyperspell and Cortex. The idea is simple: rent out a cocktail lounge, turn it into a beautiful co-working space, cocktails on us. We are bringing in the best founders and builders within our network. Dress nice, bring your laptop, and lock in with the best founders/builders in SF. Last few spots available, register now.
English
Manu Ebert รีทวีตแล้ว

first day in the new @hyperspell office with the team
including cubert, our digital employee running on an imac

English

He fixed a customer bug
20 minutes before his @ycombinator interview.
6 rejections.
Lived in a closet.
No revenue.
Most founders chase optics.
@conor_ai chased customers.
Now he’s building @hyperspell (YC F25).
Obsession wins.
🔗Watch it.
English

@conor_ai @hyperspell It's going great. Nothing to be concerned about here.
English


Tech stocks puked this week because of the rise of AI agents. Perfect timing for a conversation with the cofounders of @hyperspell, one of whom is such an AI OG that he once bought a .ai domain name via fax.
@conor_ai and @maebert discussed AI agents, the evolution of context, @ycombinator , and more:
From chatbots to true agents – Conor breaks down where tools like ChatGPT stop and AI agents begin, and why the key shift is agents taking actions autonomously across your tools, not just answering questions.
Why context is the real bottleneck – Manu and Conor share how building their own “chief of staff” agent led them to Hyperspell, a memory and context layer that plugs into tools like Slack, Gmail, and Notion so agents can actually understand your customers, org chart, and tech stack.
The three bottlenecks to agent adoption – Manu explains why verification, capability, and context each limit what agents can do today, and why decoupling these layers (rather than relying on a single big lab) gives companies more flexibility and avoids platform lock-in.
Why workers aren’t using AI (yet) – Conor reacts to studies showing most desk workers rarely touch AI, and argues that fear, bad framing (“AI will replace you”), and lack of personalized context are holding back adoption despite models already outperforming humans on many benchmarks.
AI as global leapfrog, not just US office automation – Manu highlights under-discussed upside: primary care in Africa, McKinsey-grade advice for small businesses, tailored guidance for farmers, and always-on tutors that could reshape opportunity in developing markets.
Let machines be the cogs, not people – The pair paint a future where AI agents handle status updates, follow-ups, and information shuffling inside big orgs, freeing humans to do creative, high-leverage work instead of feeling like dehumanized “TPS report” machines.
YC, rejection, and founder stubbornness – Conor and Manu talk about finally getting into Y Combinator after nine applications between them, why persistence is a superpower for founders, and how YC has shaped Hyperspell’s trajectory.
Thanks to Conor and Manu for joining on this conversation. And, yes, we are proud investors in Hyperspell at @SeaplaneVC.

English

Playing with @home_assistant.
Any sufficiently automated home is indistinguishable from haunted.
English

@conor_ai @pratik_satija @agentmail @hyperspell You mean the TOP 1% of the YC batch started at the hackathon ;)
English

@pratik_satija joined the halloween hackathon with @agentmail and @hyperspell
now he’s yc w26 🚀🚀
1% of the w26 batch started at that hackathon

English






