Vikash Kumar

Abecedarian

[Xiangyi Li @xdotli]

sharing my personal library on evals 1/n

i put together the highest quality blogs, podcasts, papers, and projects on evals. additions are welcome!

[Avid @Av1dlive]

Spacex just bought Cursor for $60 billion.

the same day, Kevin Niparko ( Product Lead at Cursor) showed exactly what Elon bet on:

"we're moving towards an era of loops and agent systems

where agents are going to continue to be working on our behalf at all times"

13 minutes that laid out the next five years of how software gets built: agent swarms + loops.

i wrote the full guide on building agent swarms two weeks ago.

bookmark it before you need it.

[Khusboo Tayal @KhusbooT14835]

Anthropic engineers just showed how they build apps with AI.

Not one agent.

A loop of agents:

→ Planner
→ Builder
→ Judge
They keep cycling until the app actually works.
The winners won't have the smartest model.

They'll have the best feedback loop.

40 minutes from the team behind Claude Code.

Watch it👇

[Bindu Reddy @bindureddy]

LLM combinations that create powerful agents

Backend-coder- GPT 5.5 + Codex 5.3
Ppt creator - Opus 4.8 + Sonnet 4.8
Search - Flash 3.5 + Grok API
Video agent - Sonnet + SeeDance 2.0
Image agent - Haiku + GPT Image 2
Massively parallel - Opus 4.8 + Kimi 2.7 / Deepseek Flash
Expert coding - Opus 4.8 xhigh + GPT 5.5 xHigh

[Movez @0xMovez]

https://t.co/OMBzNQETKM

[Nav Toor @heynavtoor]

stop asking Claude one question and thinking you understand the topic. you don't.

Stanford proved a better way. it's called STORM. peer reviewed. 25% more organized output. open source.

the trick: don't ask one question. ask five. from five different experts.

>the practitioner: what do they know that academics miss?
>the skeptic: what's the strongest counterargument?
>the economist: who profits from the current narrative?
>the historian: what pattern has played out before?
>the academic: what does the evidence actually say?

4 prompts. 5 minutes. no software. no GitHub. just paste into Claude.

single prompts give you what everyone already knows.
STORM gives you what nobody else found.

this article has all 4 prompts ready to copy. pick your hardest topic. paste prompt 1. you'll know more in 5 minutes than people who spent days reading.

[Yarchi @undefinedKi]

ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK.

It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass.

How to run it:

1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart.

2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done.

3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents.

Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens.

Bookmark this.

[Sydney Runkle @sydneyrunkle]

https://t.co/0rSDtJGB9T

[CyrilXBT @cyrilXBT]

https://t.co/bsV5kJcWDO

[spect @spectnfa]

Nobel Prize winner and Google DeepMind CEO Demis Hassabis just revealed the real AI skill gap:

“The next generation will do things that used to take teams of 10, 20, 30, 50 people”

Most people heard that and thought:

“Cool, AI makes me faster”

Wrong.

AI does not just make people faster.

It changes what one person can become.

A startup used to need:

> researcher
> designer
> developer
> marketer
> analyst
> support team
> ops manager

Now one AI-native person can wire all of that into workflows.

> Agents that research.
> Tools that write.
> Workflows that test.
> Automations that publish.
> Memory that compounds.

This is not prompt engineering.

This is leverage.

The next 5 years will not belong to people who write better prompts.

They will belong to people who build better workflows.

Watch the full interview.

Bookmark this. It is one of the most important ideas of the decade.

[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.

[Codez @0xCodez]

Anthropic Managed Agents team:

"Fable 5 is our best model for running self-improving agent systems.

Add /loops, dynamic workflows, dreaming and you are unstoppable"

in 13-minutes, Anthropic team shows how to build self-improving agent systems with Fable 5 from scratch.

Worth more than a $500 agent building course.

Live from the last Anthropic stage in Japan. Unpublished.

[Aparna Dhinakaran @aparnadhinak]

https://t.co/UYVNLOxocO

[Simon Willison @simonw]

@jakedahn I've been writing a whole guide! https://t.co/voyLwJpMcU

[Thariq @trq212]

https://t.co/R6exTuF7P8