Abel ko

Founder

[Abel ko @abe_l316]

self driving company

[Abel ko @abe_l316]

@MarkoOkhman @euqides it was super fun!

[Abel ko @abe_l316]

At SF's Anything Applied Agentic Hackathon yesterday - I built equipe's design agent, Seongjae built voice control. https://t.co/JeR97hTJjd

Thanks Geart Ferhati & @join_ef: EF raised $200M this year - heard they're planning further expansion in Asia. Korean founders, take note.

[Abel ko @abe_l316]

At Sushi & Wine w/ Consumer founders & VCs in SF. Thanks @MarkoOkhman! Met @desno365: his iPhone farm lets AI agents automate marketing with marketers' own tools - even, he says, Instagram DMs. DM me to connect. My takeaway from our chat: build for AI agents as customers.

[Abel ko @abe_l316]

Our team made the top 10 at the @elastic × @MistralAI hackathon with SF City Memory!

https://t.co/FikIIkP1Hx

Thanks, David, for building with me and contributing to equipe, my open-source AI team. Try it:

https://t.co/JeR97hTbtF

[Elon Musk @elonmusk]

Data centers in space looking pretty appealing right now

[Abel ko @abe_l316]

@nicobuilds075 @ycombinator yc is not cool anymore

[Nico Dunlap @nicobuilds075]

they just letting anybody into @ycombinator i guess

[shawn @shawn_pana]

Agents can now control phones.

Introducing Phone Harness (YC F26)

Let your agent use your personal phone, or its own iPhone/Android in the cloud

> Test and use real mobile apps
> Message and call people
> Grab verification codes for 2FA

Open source. Connect through MCP, CLI, or API.
Get started at https://t.co/81Idmd4MQb

[Abel ko @abe_l316]

I’m not proud of YC anymore

[aakarsh @pedriworshipper]

y combinator are we for real😭😭😭😭😭😭😭😭😭

[Chris Tate @ctatedev]

Introducing agent-desktop

agent-browser, for your whole computer

→ Computer Use for any coding agent
→ macOS, Windows and Linux
→ Runs in bg while you keep working
→ Agents use your computer in parallel, each with its own cursor

[沐阳 @yyyole]

以防有人不知道！！
现在任何 Agent 都能直接装上Computer Use！

Vercel Labs 正式开源了 agent-desktop，能给任何编程 Agent 加上桌面级的 Computer Use。

它和以前的做法不一样：
1、不靠截图！直接读系统的无障碍树，也就是界面上每个按钮、每个输入框的结构
2、在后台运行！不抢鼠标，你正常用电脑，它自己干它的！
3、几个 Agent 可以各用一个光标，同时干活！
4、支持macOS、Windows、Linux ！

上手很简单，一行命令安装：npm i -g agent-desktop

[plusxbt @plusxbt]

I don't understand why everyone isn't doing this yet

Anthropic documented a Claude Code feature where the STRONGEST model only kicks in at key moments instead of running the whole time

The setup: Agent Teams in Claude Code

Rather than one session doing everything, the work splits across a team:

Lead (Opus 5.5, high effort): the main session, creates the tasks and runs the team

Teammates (Sonnet 5.5, medium effort): each owns its own files, UX or backend

Advisor (Fable 5.1): consulted before picking an approach, on a repeated error, before done

Shared task list: teammates claim tasks, file locks stop two of them grabbing the same one

Start the lead from the terminal:

claude --advisor fable

Then tell it: Spawn three teammates, one on UX, one on the backend, one playing devil's advocate. Use Sonnet for each teammate

Paste this to set up your workspace:

In settings.json, add CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 to the env block, set effortLevel to high

Define roles in .claude/agents/ with model sonnet and effort medium, plus a devil's advocate role

Give each teammate its own set of files to avoid overwrites

Add a TaskCompleted hook that blocks a task from being marked done if checks fail

Show me every config change before applying it

The CLAUDE.md map your agents read, full guide in the article below

> https://t.co/bpuZk2o0YH

[Abel ko @abe_l316]

@_junhoyeo Ty sk much!

[Abel ko @abe_l316]

You can build your software 10x faster with this open source

Lead a team of AI agents
https://t.co/O5JCvGzKZE

[xsmryze @xsmryze]

THIS IS AN ACTUAL F*CKING GOLDMINE

Anthropic just shared one of the best tricks for Claude Code.

The idea: run Sonnet, Haiku 5.5 and Opus 5.5 at once, each one doing only the job it's best at.

Better results and way fewer tokens, because every task lands on the right model.

You just launch Claude Code like this:

claude --model sonnet --advisor opus

here's the split:

→ Sonnet 5.5 runs the session, writes the code and applies the fixes
→ Haiku 5.5 swarms the repo in parallel: search, grep and diff audits
→ Opus 5.5 stays on call as advisor for the big calls and signs off on the diff
→ you stop burning Opus context on work that doesn't need it

Opus only steps in at three moments:

→ before a plan locks
→ when the same error shows up twice
→ before calling it done

Sonnet builds. Haiku swarms. Opus reviews.

JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split

the full tree
> Sonnet 5.5 runs the main session and coordinates the work
> search maps the repo on Haiku 5.5, read-only
> grep finds call sites on Haiku 5.5 in its own context
> audit checks the diff on Haiku 5.5 in a throwaway worktree
> Opus 5.5 on call as advisor, reviews the synthesized diff before sign-off
> JEV routes micro-forks in milliseconds

paste the tree and this prompt into Claude Code ↓

"Reconfigure my Claude Code setup around this tree:
1. Run the main session on Sonnet 5.5 with Opus 5.5 as advisor.
2. Create three Haiku 5.5 subagents in .claude/agents: search (maps the repo), grep (finds call sites), audit (checks the diff).
3. Set isolation: worktree on audit so its checks never touch my working branch.
4. Add one rule to CLAUDE.md: delegate every repo search and test run to the Haiku 5.5 subagents to keep the main context small.
5. Route fast deterministic forks (tool choice, path selection, retries) through JEV.
Show me every change as a diff first. No edits until I say go."

↳ https://t.co/YqkjQiqRGv

save it, it'll come in handy.

[Kai @hqmank]

This is absolutely stunning!

A static physics textbook turned into an immersive, interactive 3D learning experience.

You can actually explore the concepts instead of just reading about them.

Imagine if more textbooks were built like this.

[Viktor Oddy @viktoroddy]

The MotionSites skill is live 🚀

I turned 700+ of my best website designs into one skill.

Install it and your agent stops making generic AI slop and starts building cinematic, animated sites like these.

Works with Claude Code, Codex, Cursor or any agent.

Free and open source:
https://t.co/2CyitzKzR1

[Himanshu Hingorani @himanshubuildss]

I built the AI chat interface I kept wishing existed. 👀

https://t.co/WvQ3Gln28e - animated, interactive, and none of it looks like a template.

Definitely worth saving before your next project 🔖

[Abel ko @abe_l316]

@makim414 fuck slops

[Abel ko @abe_l316]

@makim414 lfg