πΊ screenpipe #15 | AI models are evolving fast, but they can't truly help without knowing you
screenpipe #015
β¬οΈ download mac m app
β¬οΈ download windows app
give us a βοΈ(11.5k) to help the algorithm
hey louis & matt here
btw, in this newsletter, we share new features, bug fixes, work in progress, and what's next.
π€ AI models & context
there are new AI models being released daily, and they are only getting better. but the AI use cases and AI agents are only as good as the context provided to them, and none of the models know anything about you, your life, your historical data, so every interaction with LLM models results in somewhat generic and ambiguous advice.
if you ask it to create a draft email, or to give you a list of recipes to cook, it will always fail to suit you unless you provide it with context. and you know the best way to provide context to LLMs - to have your data handy with screenpipe.
a red fish with a crown on its head is swimming in the water there are new AI models being released daily, and they are only getting better
but the AI use cases and AI agents are only as good as the context provided to them, and none of the models know anything about you, your life, your historical data, so every interaction with LLM models results in somewhat generic and ambiguous advice. If you ask it to create a draft email, or to give you a list of recipes to cook, it will always fail to suit you unless you provide it with a context. And you know the best way to provide context to LLMs- to have your data handy with screenpipe.
start recording your screen & mic with screenpipe today, and become a superhuman tomorrow :)
β² timeline ui
we've been iterating on the timeline UI, adding icons, transcripts panels that allow you to go back and listen to your meetings again + ask questions through AI
have ideas to make it better? drop anything in discord, reply with a word to this email, or chat with louis
π€ other things
- the screen UI that was launched last week is finally ready for everyone in the new update, ask me questions about it: matt
- we also did a few changes to make the screen data capture work faster
- new: h.265 support on windows and linux (50% lower storage)
- fix: some voice activity detection improvement
π coming soon
- ongoing: speaker identification (e.g. link speaker to memories, transcription, etc. based on voice)
- h.265 for macos (50% lower storage)
- official brew
- data archive (e.g. store years of screenpipe data easily)
- memories, structured insightful output about you in one place
- Gumloop & Zapier integration (no code automations based on your screen & mic data)
- live caption overlay (like google meet)
- ongoing: automatic reconnection to audio devices (e.g. wear airpod, disconnect, reconnection by screenpipe automatically)
- ongoing: chat history
- ongoing: start/stop recording with a global shortcut
- ongoing: microsoft remote desktop integration for B2B
- create knowledge base about your team, know who is working on what tasks, and who is best at what, great for enterprise use cases
π ask
hey, your feedback and support are super valuable to us, hit the reply button and tell us what you'd like to see in screenpipe.
like screenpipe? mention it online, it would help us grow! π
you can tag screen_pipe on x and we will retweet you β€οΈ
- the app is still in alpha and we've fixed tons of bugs, however, we're releasing daily updates to fix them, along with new features. we're a two-person team, but we have open source contributors, and we would be happy to welcome more of them! βΊοΈπ
links
take care,
screenpipe
wanna chat?
You are receiving this email because you opted-in to receive updates from Mediar, Inc
Mediar, Inc, 2 Marina Blvd B300, San Francisco, CA 94123