Keerthan

[Sahil Bloom @SahilBloom]

Everyone should read this...

The High Shoulders Theory

(a visual thread)

[Google Cloud Tech @GoogleCloudTech]

An LLM without tools is just a chatbot.

On this week’s livestream, learn how to feed an OpenAPI spec directly into the Agent Development Kit (ADK), instantly teaching your agent how to use your backend APIs → https://t.co/ZWKEPs7fZt

[Tom Osman 🐦‍⬛ @tomosman]

This "loop" automation is nuts inside of Codex.

"/goal go over every single feature in this app create a user story with expected behaviour based on the code keep a single canonical spreadsheet tracking the features status
- when done switch loop to testing every user story and documenting all errors
- when done fix every logistical error or ux error
- test every user behaviour again post fix"

Shoutout to @MatthewBerman for the heads up.

Hundreds of user stories being worked through like it's nothing.

[Dharmvir @dharmvir_]

CS content you can watch instead of doom-scrolling:

[Rahul @sairahul1]

This is the best site on the internet to learn how LLMs actually work.

Free. Completely.

https://t.co/YOGF6PsmBN

Bookmark this site.

Then read this setup ↓

[David Ondrej @DavidOndrej1]

once Fable becomes available again, I'm not gonna sleep

instead, I will create roadmaps and long-term plans for:

> all areas of my life
> all startup ideas I have
> all potential features for all of my softwares
> long-term forecasts for geopolitical events
> personalized SWE courses
> deep summaries of all books I wanna read
> in-depth analysis of my business data

and any other ideas I'll get.

this is the only way to escape the permanent underclass.

[Paul Graham @paulg]

How to Earn a Billion Dollars: https://t.co/WeWBUkKym6

[Shann³ @shannholmberg]

what is agent looping

for the last two years we prompted agents one task at a time. that is starting to change

instead of asking an agent to build the landing page and then driving every step yourself, you set up a loop that handles discovery, planning, the work, checking, and iterating until the goal is met

looping is a setup you build. almost any agent harness can run it, it just depends on how you wire it up

at its simplest, looping is one agent working on itself:

> researches
> drafts
> checks the draft against a goal
> fixes what is weak
> runs that cycle again until the work clears the requirements

you are not prompting each step anymore. the agent repeats the cycle for you

the bigger version is a fleet looping. you give an orchestrator agent a goal, it breaks the goal into pieces, hands each piece to a specialist agent, and those specialists hand smaller jobs to their own subagents

the whole tree keeps looping through discovery, planning, execution, and verification until the goal is met

one agent looping is like a person redoing their own draft. a fleet looping is a whole team running a project end-to-end

you create a goal, and the system runs the loop until it finishes within the reqs you set

open and closed looping:

OPEN LOOPING is exploratory. it still has conditions and a goal, but you give the agent or the fleet a wide space to move in. it can try different paths, discover things, build something you did not fully spec out

this is the exciting end, it is what Peter and others are doing, and tbh it is where I want to spend more time

the catch is cost, an open loop with real room to explore burns an insane amount of tokens. for the 90 percent of people without an unlimited budget it is not runnable yet, and pointed at projects with a loose standard it turns into a slop machine

CLOSED LOOPING is bounded. a human designs the end-to-end path first:

> clear goal
> defined steps
> an eval at each step
> a point where it stops or hands back to you (and feeds back performance data)

the agents still loop, but inside framework you built. it gets better every run because each pass feeds the next, and it runs on a normal budget because the path is tight.

for most marketing work, closed is the one that pays off today.

> the orchestrator owns the goal
> the specialists own the steps
> the subagents do the narrow work
> an eval gate make sure its not slop

[Google Health @googlehealth]

We’ve loved seeing how people are styling, modifying, and accessorizing Google #FitbitAir already.

Now, we’re officially releasing the hardware specs to help creators, makers, and accessory brands keep cooking: https://t.co/OKtHbHls1a

[Mustafa @oprydai]

daily dose of premium content

[Berry @Berry_cooool]

Claude can now sell for you 🤯

Meet Autosales

An AI Employee that sells your Product FOR You 24/7

Just Paste your website URL and watch it sell.

Trained on Brain data of a $1.2M/year Sales Guy

Comment "Auto" for Exclusive Invite.

[Farea @FareaNFts]

adobe stock pays up to $64 per download for AI generated videos and most creators still don't know this is allowed 😭

no camera. no studio. just text prompts and adobe firefly

one creator already hit $8,652 from 386 downloads uploading 5 clips a day

here's the full playbook:

what you need before starting:
- a free adobe ID (https://t.co/IPi6liOepw)
- adobe firefly access (https://t.co/84FpsRWX1z, free with adobe ID)
- paypal, payoneer or skrill for payouts
- a computer and internet
- tax form filled (or adobe withholds 30%)

how to create your account:

> go to https://t.co/VVyEeyIYFo
> click join now
> create a free adobe ID
> verify your email and phone number
> complete your contributor profile
> add your payout method
> submit your tax form
> done, you can start uploading immediately

how to create AI motion footage:

> go to https://t.co/84FpsRWX1z
> click generate → video
> write a detailed prompt with style, camera motion, duration
> example: "cinematic close-up of glowing financial charts on a modern dashboard, smooth camera pan, 10 seconds, 4K"
> generate, preview, refine
> export as MP4 (1920x1080 minimum, 5-60 seconds, 24/30/60fps)

video requirements to avoid rejection:
- minimum 1080p resolution
- 5 to 60 seconds long
- MP4, MOV or MPG format
- no artifacts, distortion or noise
- no logos, brands or real people without releases

how to upload:

> log into https://t.co/VVyEeyIYFo
> drag and drop your MP4 file
> select videos as asset type
> check "created using generative AI tools"
> check "people and property are fictional" if applicable
> add a descriptive title, 10-50 keywords, category
> submit for review

how earnings work:
- royalty rate: 35% per sale
- standard download: $0.99+
- extended/on-demand license: up to $20-$80+ per download
- minimum payout: $25
- paid via paypal/payoneer/skrill in 7-10 business days

niches that sell best:
- finance and business charts
- technology and data visualization
- abstract motion graphics
- corporate and environmental footage

one good clip can sell hundreds of times over years

this is real passive income from prompts you write once

save this and start today 👇

[Varun Mayya @waitin4agi_]

Come over to our office this weekend!(and play!)

https://t.co/0UxrPMtl4K

[Tibo @thsottiaux]

You can just codex ... a farm
https://t.co/pwmS7IvqbH

[Isra @israfill]

Perplexity Pro is $20/month and there are multiple ways to get it FREE right now

what you get with pro:
- GPT-5.2, claude sonnet 4.6 , gemini 3.1 pro access
- unlimited file and PDF uploads
- image and video generation
- perplexity research mode
- 10x more citations per answer

here are the ones that actually work:

1. student/edu email (easiest globally)
> go to https://t.co/AynQPUbzpt
> verify with your .edu email via sheerid
> get perplexity pro free + referral bonuses
> every verified referral = 1 extra free month (stacks up to 24 months)

2. paypal or venmo (US users)
> if you have a paypal or venmo account
> check your paypal app for the perplexity offer
> claim 12 months of pro free ($200 value)

3. samsung device (check your phone)
> if you have a samsung galaxy
> check samsung members app for perplexity pro offer
> some models get 12 months free

4. xfinity internet (US only)
> xfinity rewards members get 1 full year of perplexity pro free
> check https://t.co/dLAXeXIiiL

5. referral program (anyone can do this)
> share your perplexity referral link
> every person who signs up = free months for you
> keeps stacking

most people are paying $20/month for this when they don't have to

comment if you got pro ↓

[Jonata Santos @_jonatasantos]

how to build anything rn:

- get a hetzner, do, or hostinger vps
- host hermes on it
- add gbrain or implement your own memory vault using qmd + sql
- set up hermes with codex auth -> gpt-5.5 / no reasoning / fast mode
- install orca on your macbook and phone with tailscale to have a nice ide to work on both
- before starting any work, ask hermes to conduct deep research on the subject and save it to gbrain as source material for the project
- use the `/grill-me` skill or a similar prompt to uncover as many unknowns as possible. save results to memory too
- define/write clear evals for every project to determine whether a run was successful
- have hermes iterate over the project until all evals pass, saving all learnings to the vault along the way
- whenever it gets stuck, use memory + a new research or `/grill-me` session to unblock it

rinse and repeat until the work is done. pay attention to the process. develop a feeling for how long tasks should take and do not be afraid to stop a model mid session to ask for status and why it's taking so long.

[Google Gemini @GeminiApp]

Gemini Spark is now available to all Google AI Ultra subscribers in the U.S.

It can handle the heavy lifting and connect the dots across your digital ecosystem to take action where it matters most. Whether you watch it work or let it run in the background, Gemini Spark is always under your direction.

Give it a try at https://t.co/gTWOnOwQDE or in the app and let us know what you think.

[ollama @ollama]

OpenJarvis: a local-first personal AI is now available to run with Ollama

Built by Stanford’s @HazyResearch and Scaling Intelligence labs, as part of their “Intelligence Per Watt” research into efficient local AI. @Stanford

Learn more in the blog post 👇👇👇

[Peter Steinberger 🦞 @steipete]

autoreview is the most impactful skill I've added to my stack (next to https://t.co/SEj2XRpaD1). It automatically reviews your code before landing a PR.

Finds so many edge cases.
Sometimes it runs for hours.

https://t.co/zbUjIS2e1i

[Khushi Agarwal @Aicoder786]

ANDREJ KARPATHY COULD HAVE CHARGED $2,000 FOR THIS COURSE.

He put it on YouTube.

The full training stack. Tokenization. Neural network internals. Hallucinations. Tool use. Reinforcement learning. RLHF. DeepSeek. AlphaGo.

3 hours of the most comprehensive LLM education that exists anywhere at any price.

Not how to use the tools.

How the entire system was built from the ground up and why it behaves the way it does.

The engineers who understand this build things the ones who only use the tools cannot even conceive of.

The gap between those two groups is not 3 hours.

It is everything those 3 hours quietly unlock for the rest of your career.