Anthropic research lead:
"99% of our engineers are running swarms of 300+ self-improving agents.
close the agent loop. Give the model a way to verify its own output"
in a 20-minute session, Anthropic team member explains how to build a model that improves itself.
Claude + loops + plan mode + dynamic workflows -that’s the secret.
Watch the talk, then save the playbook below.
Cursor just held their first ever conference.
And they dropped:
- 1.5T model trained from scratch
- Github direct replacement Origin
- iOS app
nobody saw this coming...
full breakdown (thread):
It’s now easier to move local agents to the cloud so they can keep working with your laptop closed.
Prompt Cursor from your phone, run many agents in parallel, and get back PRs with demos of their work.
PhysicsWallah prepares over 36 millions of students across India for competitive exams, and government entrance exams.
Their AI doubt-solving tool, Ask AI, found that 52% of students learn better through audio. A text-only tool was leaving half their users behind.
They integrated ElevenLabs to turn Ask AI into a voice AI tutor - with native Hinglish support, because that is how their students actually speak.
Students who learn by listening, stay:
- 3x more queries per session vs. non-voice users
- 2.4x higher retention at Day 15
Cursor CEO Michael Truell on the future of writing code: "Our goal with Cursor is to invent a new type of programming."
"It looks like a world where you have a representation of the logic of your software that does look more like English."
"You can imagine kind of an evolution of programming language towards pseudocode. You have written down the logic of the software, and you can edit that at a high level."
"It won't be the impenetrable millions of lines of code, it'll instead be something that's much terser and easier to understand and easier to navigate."
@mntruell with @lennysan on Lenny's Podcast
We're thrilled to announce that we have raised $234M in the first close of our $300M Series B at a $1.5B valuation.
@HCLTech and @BessemerVP have joined us in this round, alongside continued support from @khoslaventures and @peakxvpartners
For countries and companies, sovereign control on the AI stack is no longer an optionality. Sarvam will be the partner of choice for this aspiration. The capital allows us to accelerate our momentum towards this full stack of models, compute, and deployments.
A huge thank you to our customers, partners, investors, and the Sarvam team for your trust and belief in what we are building. We’re just getting started.
Read more: https://t.co/VmLtpnj8gx
Andrej Karpathy in 1 hour reveal how he actually works with AI: "i just tell the machine what i want, in plain words"
no prompt frameworks. no 40-line system prompts. no magic.
by 2026 the engineer who dismisses LLMs loses to the junior who configured one right
1 hour. free. the most honest look at how the best in the world actually uses AI
bookmark & watch
Anthropic engineer:
"you're not supposed to prompt Claude. you're supposed to build a system that prompts itself [loops]."
this is one of the best workflows I've seen in a long time
in this video he breaks down exactly how most people are building loops wrong:
- the memory file you never set up, so every loop starts from zero
- the sub-agents that 95% of builders have never split apart
- the stop condition setup that keeps loops from running forever and billing you in your sleep
- why writing one prompt a day is the slowest way to use Claude
if you've been using Claude for more than a month and still typing every task by hand, you've been running one prompt when you could be running a system of loops
instead of another prompt tonight, watch this
make sure to bookmark it before it gets buried
full guide in the article below