JG

I hear to learn

[Marie Haynes @Marie_Haynes]

This is really big news. Google introduced the Open Knowledge Format (OKF) - a standardized way to store information in a directory of markdown files. Makes it really easy to make a digital brain that agents can use.

These files can serve as a living wiki. You can give agents the ability to query them or edit them. They can interlink.

Seems to me this could replace Notion or Obsidian. I can think of so many uses for this.

Google's blog post: https://t.co/DqSjg4UpvH

An easier to understand explanation is the SPEC.md file:
https://t.co/A3qSz3Tfas

I gave those two links to Antigravity and asked how we could use it for any of the projects we're working on. It came up with so many ideas. I would imagine Claude Fable 5 would whip up some pretty amazing things based on this system.

Currently creating an OKF library of our pepper garden. It's going to be a fun weekend.

[JG @jamesgunja]

If this does well, it will kill cli, api, sdk, and mcp 80% cases which reads

[Google Research @GoogleResearch]

🚀 Introducing Gemini-SQL2, our breakthrough text-to-SQL capability powered by Gemini 3.1 Pro! We've achieved state-of-the-art results on the highly competitive BIRD benchmark, translating natural language into execution-ready SQL queries. 🧵👇

[Simon Eskildsen @Sirupsen]

the art of technical writing is to appease both the p99 domain-expert and the curious p50

it's like a Pixar movie that speaks to child & parent

[JG @jamesgunja]

This is so true!

[Cynthia Dunlop @c_a_dunlop]

In a fit of frustration with AI-scented tech blogs, I ran a survey to see why/how people were having LLMs write their articles. Some findings:
- 40% of “always-LLM” writers never wrote before, 20% rarely wrote before
- 72% of those who generated LLM drafts performed substantial editing, 23% totally rewrote the drafts
- Only 13% felt LLMs captured their voice, only 11% felt LLMs captured their ideas
- 73% did not disclose that they used LLMs to write

https://t.co/tFbauEBu2j

[JG @jamesgunja]

The recent costcard app is facing a cold start problem.

[JG @jamesgunja]

I made up my mind to document and build my life in public, without shame or pride.

My name is James, work for the HCM company. My job as a Sr. architect is interesting and sometimes challenging but these two come through human channels rather than technology.

[JG @jamesgunja]

@rauchg https://t.co/KD6x5UGE1p

Claude sonnet 4.6

Check out Costcard — it finds price drops on your Costco receipts and gets your money back.

[JG @jamesgunja]

@levie @paulg It is down 50% in last 3 months.

[JG @jamesgunja]

@dunkhippo33 distribution is the key!

[Arel Avellino @ArelAvellino]

@rachitaramesh52 @lennysan Transcripts as training data is underused. I've been pulling video transcripts into Supabase and running agents against them for the same reason - the insight density in a 3-hour podcast is higher than most paid courses.

What stack are you running under the hood?

[JG @jamesgunja]

@trq212 @hnshah WhatsApp coming?

[JG @jamesgunja]

@vivekhaldar https://t.co/9KRFgGCcpa

This is interesting but we might need to have deep pockets to experiment something like this…

[Ole Lehmann @itsolelehmann]

i can't believe nobody caught this.

Anthropic's entire growth marketing team was just ONE PERSON

(for 10 months, confirmed)

a single non-technical person ran paid search, paid social, app stores, email marketing, and SEO for the $380B company behind claude

here's exactly how one human is doing the job of a full marketing team:

it starts with a CSV.

1. he exports all his existing ads from his ad platforms along with their performance metrics (click-through rates, conversions, spend, etc)

2. feeds the whole file into claude code

3. and tells it to find what's underperforming.

claude analyzes the data, flags the weak ads, and generates new copy variations on the spot

this is where he gets clever:

he then splits the work into 2 specialized sub-agents:

1. one that only writes headlines (capped at 30 characters)

2. and one that only writes descriptions (capped at 90 characters).

each agent is tuned to its specific constraint so the quality is way higher than cramming both into a single prompt

so now he's got hundreds of fresh headlines and descriptions.

but that's just the text.

he still needs the actual visual ad creative, the images and banners that go on facebook, google, etc.

so he built a figma plugin that:

1. takes all those new headlines and descriptions
2. finds the ad templates in his figma files
3. and automatically swaps the copy into each one.

up to 100 ready-to-publish ad variations generated at half a second per batch.

what used to take hours of duplicating frames and copy-pasting text by hand

so now the ads are live.

the next question is which ones are actually working.

for that he built an MCP server (basically a custom integration that lets claude talk directly to external tools) connected to the meta ads API.

so he can ask claude things like:

• "which ads had the best conversion rate this week"
• or "where am i wasting spend"

and get real answers from live campaign data without ever opening the meta ads dashboard

and the part that ties it all together and closes the loop:

he set up a memory system that logs every hypothesis and experiment result across ad iterations.

so when he goes back to step one and generates the next batch of variations...

claude automatically pulls in what worked and what didn't from all previous rounds.

the system literally gets smarter every cycle.

that kind of systematic experimentation across hundreds of ads would normally need a dedicated analytics person just to track

the numbers from the doc:

ad creation went from 2 hours to 15 minutes. 10x more creative output.

and he's now testing more variations across more channels than most full marketing teams

a $380 billion company.

and their entire growth marketing operation (not GTM) = just one person and claude code lol

truly unbelievable

[JG @jamesgunja]

@vivekhaldar taste and distribution are biggest problems now.

even if designed to agents discovery is problem.

[JG @jamesgunja]

@tarunsachdeva how different is this from Claude Code History Viewer?

[JG @jamesgunja]

@ankrgyl I have built a dynamic checklist manager for verification, has registry, discovery. Hooked various phases of agentic lifecycle

[JG @jamesgunja]

@playwhatai @dani_avila7 Handout summary after completing a task, sent it as event context to next agent or dropped on to the topic. Claude code sonnet 4.5 does it very verbose.

[JG @jamesgunja]

@TimesNow @YakkatiSowmith Shame on you times now journalist, how pathetic journalism.

[JG @jamesgunja]

@sama Thanks to @openclaw

[Ejaaz @cryptopunk7213]

so just to recap this week (so far)

- musk industries is real (spacex, tesla, xai merger)

- clawdbot explosion leading to a bankrun on mac minis but then anthropic released their own version

- tesla dropped the bomb they’re halting production on model s and x to scale 1M optimus humanoid robots this year instead

- china dropped the mother of all open source models kimi k2.5 that turn video into production-ready apps but then google dropped a gemini update ON THE SAME DAY that does the same thing gg

- google said fuck it and also launched the worlds greatest world model genie and switched on gemini for 3.8B chrome browser users AND released alpha genome model that one-shots 1M dna base pairs for 3000 researchers across 160 countries AND teased new veo model

- microsoft crushed earnings, launched a new ai chip but stock still tanked 10% because they *only* grew rev 39%

- anthropic round 2X oversubbed raised to 20B 🏌️

- openai raising another $100B, 750B val 🏌️

- intel leaked they’re gonna help produce nvidias next gen feynman gpus - hello americas tsmc

- a robot (built by figure) washed the dishes with zero human interaction

- apple acquired stealth startup for $2B that can lip read - integrating their tech for new ai consumer airpods with cameras and mics

- demis confirms google glass 2.0 coming this summer

fckin hell

[JG @jamesgunja]

@elonmusk One is goods and other is services. Both are most populous countries