Ranee

VP of Growth @Notta.ai

[SpeakON @SpeakON_Global]

Human: "What do you want?"
Cat via SpeakON: "Food."

Human: "Anything else?"

Cat: "More food."

😼😼🎙️ #SpeakON

#SpeakON #CatTok #PetTech #AI #CatLife #FunnyCats #VoiceAI

[SpeakON @SpeakON_Global]

a small team with a magnetic button just beat ChatGPT Image2 for #1 on Product Hunt.
no billion-dollar backing. no hype machine.
just a device that turns your voice into perfect text.
SpeakON > ChatGPT today. let that sink in.
thank you to everyone who made this happen 🙏

curious? join us 👉 https://t.co/t0CcdzWMy0

#SpeakON #TypeOff #ProductHunt

[Ranee @Raneeq]

@code_codeforge https://t.co/hdGK8TU5Xe

[Ranee @Raneeq]

@aryanlabde https://t.co/hdGK8TU5Xe

[Ranee @Raneeq]

Typing on iPhone is broken.
By the time you unlock, type, delete, and rewrite, the thought is already weaker.

So we built SpeakON.
Press the device button once. Speak naturally.

Text goes where you’re already working.
No app switching.
No always-on mic.
No extra battery drain.

If your best ideas happen on the move, this is for you.
We launched on Product Hunt today — would love your support:
https://t.co/jHXKS7UwUL

[Ranee @Raneeq]

here's the new benchmark

[MATT GRAY @matt_gray_]

I automated 97% of my company.

The 3% that's left is taste.

[Lenny Rachitsky @lennysan]

.@rabois: "I've noticed that in some of the best organizations, the number one consumer of tokens is the CMO."

[Ranee @Raneeq]

@DoctorYev type off

[Ranee @Raneeq]

enjoy the infographic

[Notta｜AI meeting notes & audio transcription @NottaOfficial]

Your SEO agency gets you to page one.

Then 60-80% of the leads who find you there go unanswered.

Here's why agencies are leaving 40% of revenue on the table, and the flywheel that closes it 👇

[Ranee @Raneeq]

btw, I am still working on it to check if I can finish them today. I am using @grok to write the PRD and brainstorming.

[Ranee @Raneeq]

@lennysan I turned your open podcast + newsletter archive into a driving companion.

Just say “Hi Lenny” in the car → get a playlist of the best original audio clips on Product, Growth, AI, and Productivity, hand-picked like a personal exec assistant.

https://t.co/UabI29biam

[Ranee @Raneeq]

@lennysan I turned your open podcast + newsletter archive into a driving companion.

Just say “Hi Lenny” in the car → get a playlist of the best original audio clips on Product, Growth, AI, and Productivity, hand-picked like a personal exec assistant.

https://t.co/UabI29biam

[Ranee @Raneeq]

i am doing some last-minute Lenny's contest vibe coding now. Lol Hope I can catch the ddl.

[Zara Zhang @zarazhangrui]

The most efficient way for humans to collaborate: do not collaborate

One person should own something end-to-end and work with agents

[Notta｜AI meeting notes & audio transcription @NottaOfficial]

Ask an AI which brand to use for your problem.
It names three companies. Yours might not be one of them.

Here's what the ones that show up are doing differently 👇

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[Dickie Bush 🚢 @dickiebush]

https://t.co/81G7aapcJd

[m0h @exploraX_]

here’s a video guide showing how to easily add any agentic skill to Claude.

the article includes a list of 20 powerful agentic skills you can use with claude.

save this post for later.

[Ranee @Raneeq]

totally agree

[Jil Theo @theo_jil]

Writing is selling without pressure. Every tweet, every post is a chance to invite someone to your world. Don’t sell hard. Sell real.

[Ranee @Raneeq]

i'm a heavy user and beta tester for my next product. i think the most important thing is to have full confidence and use it everyday.

[Ranee @Raneeq]

Awesome list.

[Zara Zhang @zarazhangrui]

Introducing the "Follow builders" skill: the best way to stay on top of the insane happenings in AI

I carefully curated 25 X accounts & podcasts that share the highest-quality, first-hand insights on AI (by builders from OpenAI, Anthropic, Google, OpenClaw, Replit, Vercel, Cursor...)

Your OpenClaw/agent can remix my central feed & send you a personalized daily newsletter in whatever channel you like

Already widely used with 2k+ stars on GitHub; link below