@photomatt @lennysan @screen_pipe Dayflow is another one you might check out. You can switch between hosted and local models depending on your privacy comfort level
English
Traun Leyden
5.4K posts
Traun Leyden
@tleydn
Fullstack Engineer building Fluensy - Speak As Brilliant as you Think. Ex-Databricks ML infra eng, ex-Couchbase eng.
Munich, Germany Beigetreten Aralık 2009
940 Folgt827 Follower
@lennysan It should be open source and local, like @screen_pipe
English
This is a the future
"Littlebird is a desktop app that remembers everything you’ve been working on – meetings, messages, docs, browsing - and helps you stay focused, prioritize, recall, and move projects forward. It uses screen reading to understand all the text on screen, for all applications, and uses that context to build a rich understanding of your life: who matters to you, what you're working on, and what you care about this week and this year."
alexander green@alexframegreen
English
Looks super cool, can't wait to try it!
@lennysan Are you planning to add an API or MCP server?
Lenny Rachitsky@lennysan
This is a the future "Littlebird is a desktop app that remembers everything you’ve been working on – meetings, messages, docs, browsing - and helps you stay focused, prioritize, recall, and move projects forward. It uses screen reading to understand all the text on screen, for all applications, and uses that context to build a rich understanding of your life: who matters to you, what you're working on, and what you care about this week and this year."
English
Traun Leyden retweetet
I mean, what could go wrong?
Xiaoan Liu@_seanliu
now my clawdbot lives in my ray-ban meta glasses so i can just buy whatever i’m looking at
English
Sounds amazing for 7B!
Charly Wargnier@DataChaz
NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on @huggingface 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This @nvidia model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥
English
I would like to follow more B2B bootstrapping founders.
Any recommendations?
English
@_lhermann Building LinguaFriend: helping C1+ speakers reach native level by showing how they actually sound.
Records meetings, gives targeted reports and drills. (granola meets duolingo)
English
@giaccoangelo I'm living in Germany right now and it's 23 degrees fahrenheit. Tell me more
English
ChatGPT kind of has a built-in churn mechanism. They cut me off from using too much Deep Research this week, so now I'm checking out the Gemini Deep Research ..
English
Nice tips on launching on PH from @JayTheSong shadow.do/blog/how-to-la…
English
@alpic_ai looks cool! I saw you on this repo: github.com/Rodriguespn/st…
I tried to subscribe to your newsletter, it didn't seem to work?
English
@awnihannun @exolabs This is cool, but I haven't seen much in the way of cloud hosted OSX / MLX servers. Anyone know of a provider?
English
Check-out the Mac Studio cluster looking good at the Apple NeurIPS booth.
It's running a 1T parameter model using MLX distributed and @exolabs
Awni Hannun@awnihannun
I won't be at NeurIPS, but there will be some fun MLX demos at the Apple booth: - Image generation on M5 iPad - Fast, distributed text generation on multiple M3 Ultras - FastVLM real-time on an iPhone
English
I've integrated @gethuxe into my daily biking commute:
1) Queue Hacker News auto-generated podcast
2) Listen and ride, and enjoy the amazing engaging dialog
I think they use Gemini for the voices. It's very easy to listen to, and great content summary, including comments
English
@gethuxe I've been using your product daily. Any chance I can hunt it on PH? Or do you already have something in the works? DMs open
English
I still can’t believe some people have $1200/mo car payments.
Gives me anxiety just thinking about having a car payment that high
English
Another data point to my hypothesis - anything that involves copy/paste between LLMs is basically a product that needs to be created.
Andrej Karpathy@karpathy
As a fun Saturday vibe code project and following up on this tweet earlier, I hacked up an **llm-council** web app. It looks exactly like ChatGPT except each user query is 1) dispatched to multiple models on your council using OpenRouter, e.g. currently: "openai/gpt-5.1", "google/gemini-3-pro-preview", "anthropic/claude-sonnet-4.5", "x-ai/grok-4", Then 2) all models get to see each other's (anonymized) responses and they review and rank them, and then 3) a "Chairman LLM" gets all of that as context and produces the final response. It's interesting to see the results from multiple models side by side on the same query, and even more amusingly, to read through their evaluation and ranking of each other's responses. Quite often, the models are surprisingly willing to select another LLM's response as superior to their own, making this an interesting model evaluation strategy more generally. For example, reading book chapters together with my LLM Council today, the models consistently praise GPT 5.1 as the best and most insightful model, and consistently select Claude as the worst model, with the other models floating in between. But I'm not 100% convinced this aligns with my own qualitative assessment. For example, qualitatively I find GPT 5.1 a little too wordy and sprawled and Gemini 3 a bit more condensed and processed. Claude is too terse in this domain. That said, there's probably a whole design space of the data flow of your LLM council. The construction of LLM ensembles seems under-explored. I pushed the vibe coded app to github.com/karpathy/llm-c… if others would like to play. ty nano banana pro for fun header image for the repo
English
@noahsolomon @Deepfishlol Looks super cool! What is it? 😂
J/k, I think I get the high level .. but what exactly can I build with it?
Can I do basic stuff like add nice captions or other visuals to screencast demo videos?
English
Deep Fish is now Open Source! @deepfishlol
My goal was to build the web version of comfyui that had the extensibility of touch designer.
I ended short so graph execution is not recursive and remains client directed.
Go drop it a star and if anyone needs help plz dm :D
English
@Shpigford But don't you feel like it doesn't love you back when it says "Reaching Weekly Limit"?
English
