Car's Eye Sensor Falsely Flags Closed Eyes, User Annoyed
my car just warned me that my eyes were closed when they weren’t so now i’m a little offended but whatever
Falkor's GraphRAG SDK Tops Benchmark, Now Open Source
Falkor's new GraphRAG SDK just took #1 on GraphRAG bench and yes it's open source 😆
Agent Orchestration: A Living Decision Framework, Not Static Architecture
developers talk about agent harnesses/orchestration like it's back-end architecture and that if they could only get it right, they can keep building on top of it but what if it's more like personal/organizational decision making processes and org charts, and it's...
A Fantastic, Accessible Read for Model Behavior Training
this is a fantastic read and surprisingly approachable for a training retro on model behavior
AI‑Powered Co‑ops: Coordinating Communities Through Central Intelligence
the idea of a co-op, but reimagined with a central AI that coordinates everyone, would be fascinating to explore
Build for Abundance: AI's Rapid Evolution Invites New Possibilities
AI is moving so fast, what should we even build? We're excited about the opportunity for AI to accelerate abundance, help us better understand each other, and who knows what else https://t.co/jcVKtobSUS
Simplify Agent Orchestration with DB‑Stored Function Architecture
this is a great read on thinking through how to simplify agent orchestration to it’s core interestingly converges on an architecture very similar to babyagi 2, which stored functions (agent tools) in a db with input/output/dependencies/keys, and the started agent could...
Quarterly AI Session Highlights Trends and Experiments
we held our quarterly AI session with LPs last week where we go over ai trends and our experiments sharing an abbreviated version here for anyone interested 🧵 https://t.co/fRoZX64IFS
Policy Layer, Not Prompts, Should Block Agent Behavior
this is exactly what tools like @denieddotdev was built for (behavioral auth) some agent behavior should be deterministically blocked by a separate policy layer, not via prompt instructions reach out to @p_valfre for help w this stuff
Autonomous Agents Need Verifiers for Self‑improvement
feels like we have all the primitives for building powerful autonomous agent model task management tool use/auth memory & context management self improvement UI/UX what’s missing? verifiers (for self improvement) we have this in coding, which is why coding agents work so well
China’s Manus Block Signals AI Software Now Under Scrutiny
China is blocking the Manus acquisition by Meta. A few things stand out: - China has historically been more opaque and less public in restricting foreign acquisitions of Chinese tech assets, while the US (CFIUS) has been more explicit and aggressive...
Claude Design Turns Brand Guidelines Into Ready Slides
been using claude design and loving it it's basically claude code under the hood but with a very opinionated ontology for input and output - the input ontology is logo, colors, fonts, etc. - the output ontology is slides, decks, business cards as...
Founders Might Still Pitch Even After Data Sale
do you think founders would still pitch me, if like… i sold our call data to ai labs 👉👈
Top Local/Edge AI Repos and Trending Projects
if you’re interested in local/edge AI related repos and their trends, these are your guys
Simple Closure Launches Asset Hub to Sell Legacy Data
a company called @simple_closure that helps startups wind down is launching "asset hub", which is a marketplace to sell all the old slack/email data apparently they are working on hardening the PII removal tech for this
36 Companies Max for 1x Return in Concentrated Fund
this makes sense all else held equal, concentrated fund = less risky bets we've found that 36 companies is the max number of companies we can fit into a fund while claiming that a single company at 1B exit can return 1x...
Now Tracking Revenue Growth Across Every Fund Portfolio
i can't believe i didn't have this before, but i can now see (and show) revenue growth across each fund's portfolio https://t.co/Jgmf7wORWv
AI Builds Complete News Podcast in One Shot
one-shot podcast from news with @flymy_ai's new agent builder (just tested it), it: - researched news - created a transcript - created a voice for each part - stitched it together full prompt + output https://t.co/MFqPxTSwlr
Introductions Lead Requests; AI Can Streamline Most
"how can i help?" i analyzed 100 asks from portfolio companies identified in notes and emails to see what they asked 26% specific person intro 9% investor discovery 7% hiring/talent 9% pr/media 11% business/partnerships 14% scheduling/coordination 6% strategy/advice 6% product/technical 4% event related 4% admin 2% research 2% permission/approvals then further analyzed what percent...
MCP Server Lets Claude Auto‑create Reusable Skills
haha cool, this worked. an MCP server that allows Claude to build it's own reusable skills https://t.co/p2z23uqsf9 (1473 LoC) basically a server with skills to CRUD skills in this video, i use claude to create an openai image generation skill and trigger it...
Terminal Struggles Remind Me Why I Choose Replit
tried using terminal for the first time in a while... 🤦♂️ this is why i use @replit https://t.co/jd7HvVAi1W
Choose Your Hours Wisely: Mastery Requires Thoughtful Time
you have three magical beans after eating each one, whatever activity you do for the next hour, you will master what three activities do you choose? life is like this, but it takes a lot more than one bean to master an activity,...
Start Simple, Unlock Tools Gradually for Better UX
agents can do everything*, which causes a UX problem, your users have vastly different experiences, some better and some worse thinking like an RPG can help here when you start an RPG game, you start with one weapon, and you learn to...
Connecting Japanese Founders with Silicon Valley Opportunities
there are some really cool founders visiting SF from Japan to build their startups did my part this morning helping bridge US/Japan :)
Even AI Struggles With One‑Shot Real‑World Business Tasks
things that seem possible but are hard to one-shot* with the latest agents - come up a unique tee concept, design it, and sell at least 100 tee shirts for a profit - sell $1000 worth of drop shipped goods for a...
Japan Lets You Return Partially Brown Avocados
in japan you can return avocados that have turned brown on parts of the inside https://t.co/slzsVUlGaF
From Texas BBQ Roots to Tokyo Teppanyaki Heights
my two most memorable/notable meat eating restaurant experiences in US and Japan: 🇺🇸 Black’s BBQ Lockhart - oldest family owned bbq in the US. used to be a meat market that started in 1932. they have this giant wooden block as...
Momo Leverages Integrations for Automated Insight Memory
momo is cool, been trying it out. takes a different approach to memory where it’s more about turning existing data from integrations into useful insights that can be recalled as memory their new implementation with posthog automates identifying helpful insights
Testing Siri as Sole Controller for All Agents
lol gonna try using siri exclusively to run all my agents to see how that feels
Comparing AI Memory Benchmarks Reveals Key Design Trade‑offs
[Opus 4.6 Research] "Research the top memory benchmarks for AI systems, look at the top performing memory systems, and to the extent you can look at how they approach memory (looking at code if they are open source), note similarities...
Top Open‑Source Projects to Watch: Mirofish, Paperclip, Hermes, Autoresearch
someone asked me yesterday what recent open source projects have been interesting recently there's a ton but i mentioned mirofish, paperclip, hermes agent, and autoresearch
Automated Trading Now Handles 70‑80% of Market Trades
i just mentioned in a talk that 1/3 of stock trades are automated, but that was widely outdated apparently it's now 70-80% of market transactions that are carried out through automated trading software
Future AI Agents May Outpace Individual Human Oversight
right now, we manage multiple agents but as they get better, does the capacity of one agent surpass one person’s cognitive capacity to track and manage? put differently, will we get to a point where we need teams of people managing...
Redesigning Homes in 5‑10 Years Seems Unrealistic
while I agree with his general thinking about how we’ll rethink home design, seems optimistic to think that a meaningful percentage of homes would be redesigned in a 5-10 yr period
AI Emotional Companion with Self‑Updating Memory Handles Life
me: what are you working on? founder: we're building the emotional friend that everyone needs, but with embedded graph based composable memory that can connect to claude code/openai with mcp/api/cli. it has it's own rl environment it uses to continuously update...
Future Fun Becomes AI‑Driven Data Collection
in the future, everything is fun and interactive gamified entertainment, carefully designed to generate training data the ai has decided it needs
Claw Normalized AI Chat Across Every Channel
the real impact of claw was normalizing the ability to chat with your ai from any channel
Three Years of BabyAGI: Tracing Agent Evolution
as babyagi turns 3 yrs old, i finally sat down to compare the 9 iterations i did over the years... this turned into https://t.co/x2evpDgcIM a technical history of a personal project (which kind of captures the progress of the agent space overall)...
AI Filtering Faces Same Overlap as Bears and Tourists
as i think about the challenges of filtering ai content and replies, i’m reminded of this quote by a park ranger on the challenges of designing trash cans: “there is considerable overlap between the intelligence of the smartest bears and the...
AI Agents Out‑personalize Humans in Cold Emailing
getting mixed feeling, ai agents cold emailing me do a better job personalizing emails than some humans
California VC Diversity Reporting Rule Temporarily Paused
wait, so that weird CA rule where every VC has to ask their portfolio about diversity stats and submit by April 1st is now on pause? https://t.co/gLKVEsa0wY
Agentic VCs: Navigating AI Opportunities and Challenges
I'm speaking at the Virtual DDVC Summit 2026! I'll be joining 30+ speakers from Accel, Atomico, Balderton, BlackRock, NEA and more for 3 days of practical sessions on how leading investment firms are using AI, data, and automation. My session: "Opportunities &...
Alpha Test Ready: Founders & VCs Can Try Now
okay, founders/VCs can test the alpha version now... https://t.co/AQNDNk7N2l some notes: - will extract startup details/VC interest (after call) - i have access to transcription/notes - you will be able to see your own - a verification steps checks to see if you're a VC/founder first,...
Balancing Agent Development with Workflow Adaptation
the constant push and pull of building agents around our workflow vs updating our workflows to better work with agents
Agents Can Self‑register APIs Using Email as Identity
when I combined AgentMail w BrowserUse, my agent was able to create an account for an API service and grab an API key for itself email isn’t just about sending and receiving emails, it’s identity, auth, notifications, and more
Rolling Stone Revisits BabyAGI, Sparking Human‑machine Debate
.@rollingstone remembers babyagi 🥰 (in an article questioning the role of machines vs humans from yesterday) https://t.co/H71nwLSBCv
AI Pitch Bot Offers Cheap, Consistent Feedback, But Limits Hurt
haha the @runwayml real-time characters is great. i just spent 2 minutes pitching a ghibli version of myself a bladeless blender startup it's only a 2 min demo, but the questions and tone are pretty solid. one question even threw me...
Plaud: Not a Plumber’s Claude, Just Another AI Pin
for a sec i thought plaud was like claude for plumbers but it’s a more generic wearable ai pin (how many are there now?)
Travel Booking Thrives on APIs, Not Browser Demos
booking travel is the classic browser agent demo, but APIs make more sense here companies like @duffelhq and @selfbookhq are good for this. the latter seems to have leaned into AI based on their site, but their X account is inactive
From DoW Drama to Exciting New Chinese Model Launch
i guess we’re moving on from DoW drama to celebrating a new chinese model drop