God of Prompt
RT @godofprompt: instead of scrolling x, study this free course packed with INSANE value
tweet
RT @godofprompt: instead of scrolling x, study this free course packed with INSANE value
Jason Liu just open sourced his entire paid RAG course and consulting archive. all of it. free.
for context: this is the creator of Instructor (6M+ monthly downloads, cited by OpenAI as inspiration for their structured outputs feature). former staff ML engineer at Stitch Fix. ex-Meta. a16z scout. his RAG course on Maven had 400+ engineers enrolled.
but here's what's actually interesting.
look at the highlights he chose to summarize his own course:
> product mindset over one-off implementation
> measurement, feedback loops, improvement cycles first
> synthetic eval data to break the cold start
> feedback UX that actually works
> specialized retrieval and routing instead of one-size-fits-all search
notice what's missing?
no mention of vector databases. no embedding model comparisons. no chunk size optimization. no retrieval framework shootouts.
the guy who mass-taught production RAG to hundreds of engineers is telling you the hard part was never the retrieval. it was the product thinking around it.
measurement. feedback loops. knowing what to improve and how to tell if you improved it.
everyone's out here debating pgvector vs pinecone vs weaviate. meanwhile the most credible RAG practitioner in the space just told you the answer was never in the vector store.
it was in the feedback UX.
567 Labs is done. the content lives on. go read it before you build another RAG pipeline without an eval framework. - Robert Yousseftweet
X (formerly Twitter)
Robert Youssef (@rryssf_) on X
Jason Liu just open sourced his entire paid RAG course and consulting archive. all of it. free.
for context: this is the creator of Instructor (6M+ monthly downloads, cited by OpenAI as inspiration for their structured outputs feature). former staff ML engineer…
for context: this is the creator of Instructor (6M+ monthly downloads, cited by OpenAI as inspiration for their structured outputs feature). former staff ML engineer…
Offshore
Photo
God of Prompt
RT @godofprompt: Steal these prompts for Perplexity Research
🔖 Bookmark for later https://t.co/wLLJHNGwOl
tweet
RT @godofprompt: Steal these prompts for Perplexity Research
🔖 Bookmark for later https://t.co/wLLJHNGwOl
tweet
Offshore
Photo
God of Prompt
I don't need ChatGPT
I don't need Perplexity
I don't need DeepSeek
I got my Claude Opus 4.6.
Time to start cooking. https://t.co/3jmixVsg0A
tweet
I don't need ChatGPT
I don't need Perplexity
I don't need DeepSeek
I got my Claude Opus 4.6.
Time to start cooking. https://t.co/3jmixVsg0A
tweet
Offshore
Photo
Javier Blas
REACTION COLUMN: Mining giants Rio Tinto and Glencore are both losers as their M&A talks to create the world’s largest miner collapse.
But I don’t think we have seen the final word on the 20-year on-and-off saga to merge both companies.
@Opinion
https://t.co/iMoHDvwEAx
tweet
REACTION COLUMN: Mining giants Rio Tinto and Glencore are both losers as their M&A talks to create the world’s largest miner collapse.
But I don’t think we have seen the final word on the 20-year on-and-off saga to merge both companies.
@Opinion
https://t.co/iMoHDvwEAx
tweet
Offshore
Video
God of Prompt
Everyone's posting benchmarks right now.
But the scariest detail from today's drop isn't the scores.
GPT-5.3-Codex helped debug its own training, manage its own deployment, and diagnose its own test results.
OpenAI's words, not mine: "instrumental in creating itself."
Opus 4.6 agent teams are impressive. 1M context window is massive. The benchmark war is fun to watch.
But an AI model that accelerates its own development? That's not a feature update. That's a different category of thing entirely.
We just crossed from "AI that helps you code" to "AI that builds AI."
And nobody's stopping to think about what that means for the next 12 months.
tweet
Everyone's posting benchmarks right now.
But the scariest detail from today's drop isn't the scores.
GPT-5.3-Codex helped debug its own training, manage its own deployment, and diagnose its own test results.
OpenAI's words, not mine: "instrumental in creating itself."
Opus 4.6 agent teams are impressive. 1M context window is massive. The benchmark war is fun to watch.
But an AI model that accelerates its own development? That's not a feature update. That's a different category of thing entirely.
We just crossed from "AI that helps you code" to "AI that builds AI."
And nobody's stopping to think about what that means for the next 12 months.
Introducing Claude Opus 4.6. Our smartest model got an upgrade.
Opus 4.6 plans more carefully, sustains agentic tasks for longer, operates reliably in massive codebases, and catches its own mistakes.
It’s also our first Opus-class model with 1M token context in beta. https://t.co/L1iQyRgT9x - Claudetweet
Offshore
Video
God of Prompt
RT @alex_prompter: OpenClaw broke the internet
But you DON'T need to setup any servers to use it
Here's the easiest way to run OpenClaw on a website
No Mac Minis required https://t.co/6xspOtHaxT
tweet
RT @alex_prompter: OpenClaw broke the internet
But you DON'T need to setup any servers to use it
Here's the easiest way to run OpenClaw on a website
No Mac Minis required https://t.co/6xspOtHaxT
tweet
God of Prompt
RT @godofprompt: 🚨 BREAKING: OpenAI just dropped Frontier and it's basically AI employees that actually get stuff done.
Not chatbots. Not assistants.
Full AI coworkers that dig through your logs, docs, and code to solve problems end-to-end.
They went from 4 hours of hardware troubleshooting to just a few minutes.
tweet
RT @godofprompt: 🚨 BREAKING: OpenAI just dropped Frontier and it's basically AI employees that actually get stuff done.
Not chatbots. Not assistants.
Full AI coworkers that dig through your logs, docs, and code to solve problems end-to-end.
They went from 4 hours of hardware troubleshooting to just a few minutes.
Introducing OpenAI Frontier—a new platform that helps enterprises build, deploy, and manage AI coworkers that can do real work. https://t.co/4W0adQzSZ1 - OpenAItweet
X (formerly Twitter)
OpenAI (@OpenAI) on X
Introducing OpenAI Frontier—a new platform that helps enterprises build, deploy, and manage AI coworkers that can do real work. https://t.co/4W0adQzSZ1
Offshore
Photo
Quiver Quantitative
The White House posted this an hour ago.
They just deleted it. https://t.co/sy7OZxMVma
tweet
The White House posted this an hour ago.
They just deleted it. https://t.co/sy7OZxMVma
tweet
Offshore
Video
God of Prompt
RT @alex_prompter: OpenClaw broke the internet
But you DON'T need to setup any servers to use it
Here's the easiest way to run OpenClaw on a website
No Mac Minis required https://t.co/6xspOtHaxT
tweet
RT @alex_prompter: OpenClaw broke the internet
But you DON'T need to setup any servers to use it
Here's the easiest way to run OpenClaw on a website
No Mac Minis required https://t.co/6xspOtHaxT
tweet