Full-time Python Engineer - Sharing daily insights on Python, ML and AI. - DM/[email protected] for collaboration - Open for opportunities
Remote
Joined July 2022
- Tweets6.7K
- Following223
- Followers104K
- Likes10.6K
Chat models generate messages.
Decision models make decisions.
Workflow models execute entire workflows in a single API call.
Meet @TypeLLM the workflow model
Chat models generate messages.
Decision models make decisions.
Workflow models execute entire workflows in a single API call.
Stop writing orchestration loops around your LLM.
TypeLLM is a workflow model. You declare the decisions, their types and what depends on what. It runs the whole graph in ONE API call.
Think SQL for AI workflows.
Support ticket example:
→ Classify category + urgency in parallel
→ Refund only runs if billing
→ Reply reads category + urgency
Four steps. One call. Typed results.
vs four serial calls:
→ 2.1x fewer input tokens
→ ~1.9x faster
Not having access to experts is no longer a bottleneck when it comes to learning new things. You can ask AI to make a 5 minute video for you to learn anything. Here’s one on how a fab makes chips.
Graphify is now live in @AskPerplexity Computer’s skills marketplace.
Every Computer user gets 5,000 free credits (through Oct 31) to turn any codebase into an interactive map like this.
Go burn them. Build the memory system your code has always needed.
The Graphify skill by @graphify is now in Computer's skills marketplace, available to all Computer users.
Turn a codebase into an interactive map of its files, functions, and dependencies.
Tasks that use /graphify are free through October 31, up to 5,000 credits per user.
Python Space retweeted
Don't waste your time, just use graphify skill to turn your codebase into an interactive map.
Now available to all @perplexity_ai
Computer users for FREE.
The Graphify skill by @graphify is now in Computer's skills marketplace, available to all Computer users.
Turn a codebase into an interactive map of its files, functions, and dependencies.
Tasks that use /graphify are free through October 31, up to 5,000 credits per user.
Don't waste your time, just use graphify skill to turn your codebase into an interactive map.
Now available to all @perplexity_ai
Computer users for FREE.
The Graphify skill by @graphify is now in Computer's skills marketplace, available to all Computer users.
Turn a codebase into an interactive map of its files, functions, and dependencies.
Tasks that use /graphify are free through October 31, up to 5,000 credits per user.
We’re hiring in Australia. Just spent a week with our team in Sydney and Melbourne (incredible!) - 22 people now, 900k users across the region, and Australian data residency for enterprise launching soon.
If you want to build voice and agents from the ground up, get in touch!
We let Runable run our own social media for 3 months
Impressions went from 0.29M to 19.7M.
AI tools have gotten absurdly good
but it's been bugging me that the actual
operations of social media still haven’t been solved
And the legacy tools (@hootsuite and the likes) practically need a course just to learn how they work
and their implementation of AI has made the whole process of social media management worse
No more
Social media on Runable is as easy as it gets
Research, analysis, creation, and posting happen in one workflow, on one platform, from a single prompt
You don’t have to believe me. Or this cool video (which, yes, was also made with Runable).
But numbers don’t lie. 0.29M → 19.7M
(This is also being posted via Runable, but we don't add the annoying "Posted by xyz" tag)
Now you can run Perplexity Computer fully local on your Mac!
No wifi needed.
works with Mac apps and 100% local.
https://xitter.cf/t.co/z4KSTY1QrM @AravSrinivas
The offline part is what gets me. Curious what you'd hand it first: sorting a messy Downloads folder, or going through PDFs you'd never upload anywhere?
Yes, this can be used to organize the computer without uploading our data.
I need to get a @perplexity_ai computer to try all these things soon.
Python Space retweeted
AI tools are everywhere, but direct access to Seedance on Dreamina for $0.29 definitely caught my attention. Register through my official partner link to get the offer:
dreamina.capcut.com/pricing/…
#DreaminaOnly29Cents #Dreamina #DreaminaPartner #Seedance
AI tools are everywhere, but direct access to Seedance on Dreamina for $0.29 definitely caught my attention. Register through my official partner link to get the offer:
dreamina.capcut.com/pricing/…
#DreaminaOnly29Cents #Dreamina #DreaminaPartner #Seedance
Perplexity Computer now runs entirely on Apple Silicon Macs, but its recommended RAM requirement is pretty steep and limits actual deployments.
appleinsider.com/articles/26…
The hybrid approach is brilliant, starting local for privacy, then tapping cloud only when needed. We actually went deeper on this here: xitter.cf/AGTPinsights/status/21…
Perplexity just made its Computer agent run fully local on Mac, no cloud needed. Here's what you need to know.
Perplexity announced on October 20, 2026 that Perplexity Computer can now run fully local on your Mac. Both the model and the agent run on your machine. You can work with native Mac apps and local files without sending sensitive data to the cloud. CEO Aravind Srinivas added that it works with no cloud-based inference, even without WiFi.
Local tasks use PPLX Pro, Perplexity's post-trained version of Qwen 3.8. They don't consume Computer credits. For more complex work, a Hybrid mode can split the task between cloud models and the local model on your Mac, keeping sensitive data private. MacStories notes this flips last month's Hybrid Computer, which started in the cloud. Now you start local and only reach cloud frontier models when needed, with the user's approval.
Who can use it: it's available now in the Perplexity Mac app for Pro, Max, and Enterprise subscribers on supported Apple silicon Macs. You download the app and set up a local model to get started.
The catch is memory. Perplexity recommends 36 GB of unified memory. Engadget and AppleInsider both flag that as steep. iThinkDifferent reports the new Mac mini with M6 can't be configured that high, and one reply says only the M5 Pro mini, from $1,699 with up to 64GB, clears the bar. Some users with 24GB Macs say they feel left out. Others are glad to skip API costs while experimenting.
Key numbers:
- 36 GB unified memory recommended
- Model: PPLX Pro, post-trained Qwen 3.8
- Local tasks use 0 Computer credits
- Plans: Pro, Max, Enterprise
- Announced October 20, 2026
The launch pairs fully offline Mac agents with a hybrid option for heavier tasks.
Hybrid AI is going to change the way we use AI.
@perplexity_ai computer makes it easy. I wish to have the computer setup soon.
Python Space retweeted
Now you can run Perplexity Computer fully local on your Mac!
No wifi needed.
works with Mac apps and 100% local.
https://xitter.cf/t.co/z4KSTY1QrM @AravSrinivas
You can now run Perplexity Computer fully local on your Mac with no cloud based inference, without WiFi too. Enjoy!
we crushed a keyboard.
its retirement party got a little out of hand.
for years, it was there for every email, every plan, every “just one more thing.” a loyal colleague. a very loud colleague.
but your ideas move faster than your fingers.
and somewhere between knowing what you want to do and typing it all out, a quick task becomes another thing taking up your afternoon.
meet SpeakON AI Agent.
start with what you need, in your own words. less time behind a blinking cursor. more room to move things forward.
the keyboard had a good run.
now, let’s give your voice a turn.
THE LAST KEYSTROKE is here. watch the film, then tell us: what’s the first task you’d hand over?
speakon.app/x
Disclaimer: The calling feature is still in beta and will be available soon. All other Agent features are available now, with ongoing improvements.
Python Space retweeted
You're deep in a content draft when you remember a client needs a follow-up.
You won't stop to open a reminders app. You'll tell yourself you'll remember. Then you don't.
That's where SpeakON makes sense to me. Say it out loud, and the agent helps set the reminder.
Voice Keyboard and Notes capture the thought. Agent helps you act on it.
The useful part isn't voice typing. It's going from saying something to getting help with the next step, without breaking focus.
For anyone juggling clients and content, that gap is where things slip.
we crushed a keyboard.
its retirement party got a little out of hand.
for years, it was there for every email, every plan, every “just one more thing.” a loyal colleague. a very loud colleague.
but your ideas move faster than your fingers.
and somewhere between knowing what you want to do and typing it all out, a quick task becomes another thing taking up your afternoon.
meet SpeakON AI Agent.
start with what you need, in your own words. less time behind a blinking cursor. more room to move things forward.
the keyboard had a good run.
now, let’s give your voice a turn.
THE LAST KEYSTROKE is here. watch the film, then tell us: what’s the first task you’d hand over?
speakon.app/x
Disclaimer: The calling feature is still in beta and will be available soon. All other Agent features are available now, with ongoing improvements.
You're deep in a content draft when you remember a client needs a follow-up.
You won't stop to open a reminders app. You'll tell yourself you'll remember. Then you don't.
That's where SpeakON makes sense to me. Say it out loud, and the agent helps set the reminder.
Voice Keyboard and Notes capture the thought. Agent helps you act on it.
The useful part isn't voice typing. It's going from saying something to getting help with the next step, without breaking focus.
For anyone juggling clients and content, that gap is where things slip.
we crushed a keyboard.
its retirement party got a little out of hand.
for years, it was there for every email, every plan, every “just one more thing.” a loyal colleague. a very loud colleague.
but your ideas move faster than your fingers.
and somewhere between knowing what you want to do and typing it all out, a quick task becomes another thing taking up your afternoon.
meet SpeakON AI Agent.
start with what you need, in your own words. less time behind a blinking cursor. more room to move things forward.
the keyboard had a good run.
now, let’s give your voice a turn.
THE LAST KEYSTROKE is here. watch the film, then tell us: what’s the first task you’d hand over?
speakon.app/x
Disclaimer: The calling feature is still in beta and will be available soon. All other Agent features are available now, with ongoing improvements.