Caithrin Rintoul

@llm_wizard Cast this in bronze and put it in front of the building

And they call me…. Joe Nemotron.

@cjpedregal Yesss nice work!

There are some tweets out there saying that Granola is trying to lock down access to your data. Tldr; we are actually trying to become more open, not closed. We’re launching a public API next week to complement our MCP. Read on for context. A couple months ago, we noticed that some folks had reversed engineered our local cache so they could access their meeting data. Our cache was not built for this (it can change at any point), so we launched our MCP to serve this need. The MCP gives full access to your notes and transcripts (all time for paid users, time restricted for free users). MCP usage has exploded since launch, so we felt good about it. A week ago, we updated how we store data in our cache and broke the workarounds. This is on us. Stupidly, we thought we had solved these use cases well enough with our MCP. We’ve now learned that while MCPs are great for connecting to tools like Claude or chatGPT, they don’t meet your needs for agents running locally or for data export / pipeline work. So we’re going to fix this for you ASAP. First, we’ll launch a public API next week to make it easier for you to pull your data. Second, we’ll figure out how to make Granola work better for agents running locally. Whether that’s expanding our MCP, launching a CLI, a local API, etc. The industry is moving quickly here, so we’d appreciate your suggestions. We want Granola data to be accessible and useful wherever you need it. Stay tuned.

@JordanNanos congrats!

let’s go

@samt_granola @appenz @meetgranola Ahhh ok Drop me a DM I have some feedback on this!

@caithrin @appenz @meetgranola Claude pls 🥲 Mostly yes, we do some offline caching to make the app snappy but these are regularly pruned (also to keep the app snappy!)

Sorry to see Granola @meetgranola going closed. They encrypted their local db, no local and no cloud API. In a world where notes are managed by agents, the app now has zero value. Any recommendations for good alternatives? What are you switching to?

@samt_granola @appenz @meetgranola Claude tells me differently! Are they now stored server-side only?

@caithrin @appenz @meetgranola Transcripts are available in the MCP on Granola Business/Enterprise!

@samt_granola @appenz @meetgranola no transcripts now in the MCP, correct?

@appenz @meetgranola hey Guido! Have you tried our MCP? granola.ai/blog/granola-m… The changes to the local cache were 100% performance related - it's a change we've needed to make for a while and became unavoidable, but we wanted to make sure we released the MCP before doing it.

@benoror I should show you my pitch deck maker on top of this exact stack. It’s pretty good stuff.

Been experimenting this weekend with agentic workflows on top of Obsidian vaults... it's addictive AI agents that handle meetings, transcripts, follow-ups, recaps, and commits -- all via slash commands, right inside your vault. Works with Cursor, Claude Code, OpenCode, etc...

@johnowhitaker @austinc3301 👏🏼👏🏼👏🏼

Who called it "Effective Altruism" and not "Crazy Rich Bayesians"?

@LydNot I’m doing something related to this at a conference in May, so keep me up to speed with your favorites please.

yep! ran a reading group on this for some time. and then rachel instigated ilya list for ai safety. i think we need more ilya lists for diff fields curation by a 'high-taste' individual is important feature of the ilya list. ofc we need better systems for filtering/sorting the vast amount of research increasingly generated perhaps spending a bit of time filtering/sorting historical research may be instructive

hi! does anyone have...curated lists of significant papers they like? e.g. '30 papers to understand x'. compiling a list of lists. the papers need to be information-dense.

@oh_that_hat The best part is 30% of those people still hope that we’ll go back there

Old enough to remember when "AGI" was a taboo word, and the idea that scaling transformers could get us there were downright offensive to many in academia

@binarybits @jasminewsun Ant Ling is a thing in China, too. Sucks to have two Ant frontier labs

@jasminewsun That's surprising to me. I feel like I only started seeing it a few weeks ago.

People have started abbreviating Anthropic as "Ant" and I don't like it. The th is a single phoneme. You shouldn't split it up like that.

@bryancsk We call that the perma-muda triangle

Sometimes I wonder if we will ever be able to bring internet connectivity to phones in the Mission District, San Francisco. But maybe we can't. We don't have the technology

@phones111111 Dont sleep on SF jazz either. It’s damn good.

the ballet/operahouse is the actual third space in sf. few

@Ryan_Gasoline @irl_danB @mylordcod We should stamp people’s O1 visas with this tweet

@irl_danB @mylordcod Don't call it San Fran, don't leave your backpack in the car, and don't accept a fancy title in lieu of actual compensation

I will be in San Fran for the first time in my adult life April-June will not have a ton of free time; what are the do’s and don’ts?

@kevinsxu This is a great piece Kevin!

We are LIVE on Substack with @natolambert and @rasbt and our newest SAIL writer: @swyx ! Follow this link to join the conversation substack.com/live-stream/12…

Codex in a code base written mainly by Claude

@conncarroll @binarybits @Aella_Girl I don't believe for a second those jobs still exist in the age of decent OS models who can write. But if I am right and this is all AI convos, OF would be a top 5 AI company by revenue, right?

@caithrin @binarybits Right. There is no way the porn actresses are texting everyone. @Aella_Girl had a long story awhile back that reported it was all actually people getting paid to do the messaging.

I mean, considering the revenue involved I guess this has to be true but part of me still doesn't believe it. There is a literal infinite amount of porn available for free. Is being able to pretend you are texting with the pornstar really that much of a value add on?