Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

this is pure f*cking gold for anyone running coding agents Jev founder Diogo Amogo wrote a PDF on building a Jev harness the promise: > 200x faster > 400x cheaper the model hasn't been the slow part for a while the speed and the cost sit in the harness...

polydao's profile picture

Mr. Buzzoni

24,888 subscribers

120,326 görüntüleme • 1 gün önce •via X (Twitter)

EğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

14 Yorum

FHX Markets profil fotoğrafı
FHX Markets1 gün önce

The model got fast. Everything around the model became the bottleneck.

Lanny Lobato profil fotoğrafı
Lanny Lobato1 gün önce

200x faster is wild but 400x cheaper is what actually makes this viable at scale

vvtentt profil fotoğrafı
vvtentt1 gün önce

People are big ants and many will be left without work

Crio Songo profil fotoğrafı
Crio Songo1 gün önce

That's a huge optimization. I will get the PDF this weekend and try it out myself.

帆70｜BG小晴 profil fotoğrafı
帆70｜BG小晴1 gün önce

原来瓶颈一直都在外壳设计上啊受教了

Gul Saeed Khattak profil fotoğrafı
Gul Saeed Khattak1 gün önce

Small correction: this paper is not by the Jev founder. It’s an independent note based on his design ideas The key detail is actually printed on the cover: it says “independent working note, not affiliated with TypeSafe.

WEEX AI Labs profil fotoğrafı
WEEX AI Labs1 gün önce

👀

Wallchain Community Hub profil fotoğrafı
Wallchain Community Hub1 gün önce

finally a harness worth actually setting up

The AI Therapist profil fotoğrafı
The AI Therapist1 gün önce

that 400x cost drop is sexy. I’d bet the secret’s in Jev harnessing parallel context windows rather than raw compute cuts. Makes those coding agents run tighter without bleeding cash. Efficient brains are always attractive to me. 😉

Hamza Khalid profil fotoğrafı
Hamza Khalid1 gün önce

200x and 400x on what baseline though, curious if that's against a naive setup or an already decent one

Harley Lewis Foote profil fotoğrafı
Harley Lewis Foote1 gün önce

The harness as bottleneck—finally someone naming the thing we all felt.

EDDY VU profil fotoğrafı
EDDY VU1 gün önce

Totally agree, redundant tool loops and bad scaffolding waste way more time than token generation ever does.

Tom profil fotoğrafı
Tom1 gün önce

It is easy to just come up with an idea. Now test it, compare, run benchmark, not just speed and cost numbers, but quality - that would be gold. Anyone?

Thorbjørn Rønje profil fotoğrafı
Thorbjørn Rønje1 gün önce

Setup compounds quickly.

Benzer Videolar

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇
0:23

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇

Hanako

37,887 görüntüleme • 3 gün önce

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.
0:25

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.

Akshay 🚀

353,430 görüntüleme • 6 gün önce

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code era. Claude Code is still part of the assistance era - Jev is the next step Jev is x200 faster, x400 cheaper and has 0 hallucination. This is what comes after RLHF" In 17 minutes he explains why every model you use has a human-shaped flaw baked into it and why Jev is better worth more than a $500 Claude Code engineering course watch today, then read how to actually boost yourself x100 with Jev in the post below
17:33

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code era. Claude Code is still part of the assistance era - Jev is the next step Jev is x200 faster, x400 cheaper and has 0 hallucination. This is what comes after RLHF" In 17 minutes he explains why every model you use has a human-shaped flaw baked into it and why Jev is better worth more than a $500 Claude Code engineering course watch today, then read how to actually boost yourself x100 with Jev in the post below

Codez

191,678 görüntüleme • 9 gün önce

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas
3:27

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

Rohan Paul

120,488 görüntüleme • 3 ay önce

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code or Codex era, they are still part of the assistance era with human in the loop - JEV is what comes next for LLMs x200 faster, x400 cheaper, 0 hallucination, no human in the loop - that's JEV, this is how LLMs will look like" in 36-minute tech talk, Jev Founder explained why RLHF isn't a thing anymore and how modern LLMs will be built this talk is worth more than a Stanford Machine Learning degree watch today no matter what, then learn how to become a Jev Engineer in the article below
36:14

Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code or Codex era, they are still part of the assistance era with human in the loop - JEV is what comes next for LLMs x200 faster, x400 cheaper, 0 hallucination, no human in the loop - that's JEV, this is how LLMs will look like" in 36-minute tech talk, Jev Founder explained why RLHF isn't a thing anymore and how modern LLMs will be built this talk is worth more than a Stanford Machine Learning degree watch today no matter what, then learn how to become a Jev Engineer in the article below

Codez

454,370 görüntüleme • 8 gün önce

Say hello to open source deep research for your favorite agent harness. Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back a detailed report with citations. See it in Codex below 👇
4:10

Say hello to open source deep research for your favorite agent harness. Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back a detailed report with citations. See it in Codex below 👇

NVIDIA AI

76,528 görüntüleme • 4 ay önce

🔥 Running Kimi K3 (Kimi.ai) inside Claude Code is a game-changer. Claude is the best coding harness out there, and now you can pair it with Kimi's powerful (and affordable) K3 model running 24/7 on a VPS. Loops, subagents, and max performance. Watch the full setup guide 👇
8:30

🔥 Running Kimi K3 (Kimi.ai) inside Claude Code is a game-changer. Claude is the best coding harness out there, and now you can pair it with Kimi's powerful (and affordable) K3 model running 24/7 on a VPS. Loops, subagents, and max performance. Watch the full setup guide 👇

Boxmining

70,426 görüntüleme • 2 ay önce

Jev’s founder just dropped the 12-page harness that makes coding agents 400× cheaper the first thing it shows: your agent spends under 10% of its tokens actually writing code → reading and searching take 56.2% of tool turns and 46.5% of tokens. that’s where the money goes → routing Opus → Sonnet → Opus to save costs 6.19. pure Opus costs 4.15. every handoff reprocesses the whole context → compress after the question, never before. every chunk gets scored: hide, short summary, long summary or full → instructions load by condition. touch *.tsx and the style guide loads. touch billing/ and its gotchas file loads. compaction can’t erase either → route by trust, not difficulty. secrets and infra stay on first-party frontier models, public docs go to the cheapest one → every command passes an allow / ask / deny policy that reads the script before it runs. not just its name their claim: 200× faster, 400× cheaper drop the PDF into Claude Code or Codex and let it rebuild your harness ↓
0:42

Jev’s founder just dropped the 12-page harness that makes coding agents 400× cheaper the first thing it shows: your agent spends under 10% of its tokens actually writing code → reading and searching take 56.2% of tool turns and 46.5% of tokens. that’s where the money goes → routing Opus → Sonnet → Opus to save costs 6.19. pure Opus costs 4.15. every handoff reprocesses the whole context → compress after the question, never before. every chunk gets scored: hide, short summary, long summary or full → instructions load by condition. touch *.tsx and the style guide loads. touch billing/ and its gotchas file loads. compaction can’t erase either → route by trust, not difficulty. secrets and infra stay on first-party frontier models, public docs go to the cheapest one → every command passes an allow / ask / deny policy that reads the script before it runs. not just its name their claim: 200× faster, 400× cheaper drop the PDF into Claude Code or Codex and let it rebuild your harness ↓

Carnage

61,361 görüntüleme • 5 gün önce

Creator of Claude Code: “I’m not just prompting agents anymore. I’m building a harness with graphs and loops - and the agents inside it are building my agent. In 3–6 months, we’ll all be engineering harnesses for our agentic systems.” In this 10-minute talk, Boris Cherny reveals what the future of agentic engineering will look like. Worth more than a $500 agentic AI course. Watch it today, then read the complete guide to building an agent harness in the article below.
11:17

Creator of Claude Code: “I’m not just prompting agents anymore. I’m building a harness with graphs and loops - and the agents inside it are building my agent. In 3–6 months, we’ll all be engineering harnesses for our agentic systems.” In this 10-minute talk, Boris Cherny reveals what the future of agentic engineering will look like. Worth more than a $500 agentic AI course. Watch it today, then read the complete guide to building an agent harness in the article below.

Ichigo

72,217 görüntüleme • 3 gün önce

The easiest way to run your agent harnesses using local models: Whether you're using Claude Code, Codex, OpenCode, or Pi, the local setup itself isn't really the hard part. The harder problem is figuring out which local model your machine can actually handle well. You have to think about RAM, model size, quantization, context length, KV cache, speed, accuracy, and a bunch of other trade-offs before you even start. Magnitude is an open-source solution that removes all of that guesswork for you. It profiles your machine, benchmarks what it can realistically run, recommends the best models for your hardware, and then lets you connect them to your preferred agent harness. The entire setup takes just two commands. In this video, I walk through the full process from hardware profiling to running a harness on a local model. Chapters: 00:00 Intro 00:17 What Magnitude is 00:45 Setup in two commands 01:29 Why picking a local model gets confusing fast 02:11 Hardware profiling + model recommendations 02:59 Choosing your harness 03:22 Connecting a harness that's already running 04:18 Outro Get started: (don't forget to star 🌟)
4:29

The easiest way to run your agent harnesses using local models: Whether you're using Claude Code, Codex, OpenCode, or Pi, the local setup itself isn't really the hard part. The harder problem is figuring out which local model your machine can actually handle well. You have to think about RAM, model size, quantization, context length, KV cache, speed, accuracy, and a bunch of other trade-offs before you even start. Magnitude is an open-source solution that removes all of that guesswork for you. It profiles your machine, benchmarks what it can realistically run, recommends the best models for your hardware, and then lets you connect them to your preferred agent harness. The entire setup takes just two commands. In this video, I walk through the full process from hardware profiling to running a harness on a local model. Chapters: 00:00 Intro 00:17 What Magnitude is 00:45 Setup in two commands 01:29 Why picking a local model gets confusing fast 02:11 Hardware profiling + model recommendations 02:59 Choosing your harness 03:22 Connecting a harness that's already running 04:18 Outro Get started: (don't forget to star 🌟)

Akshay 🚀

18,722 görüntüleme • 12 gün önce

you don't have to pay for claude code or codex subscription anymore. here's a video guide on how to setup codex or claude code completely for free. the setup takes less that 5mins, the article quoted below has all of the installation codes you need.
2:04

you don't have to pay for claude code or codex subscription anymore. here's a video guide on how to setup codex or claude code completely for free. the setup takes less that 5mins, the article quoted below has all of the installation codes you need.

m0h

76,334 görüntüleme • 4 ay önce

Agent apps don’t win on the model, they win on the harness. But creating that harness is painful. Terminal Use is hosting infrastructure for background agents built for iterating: fork filesystems and try multiple agents in parallel. The platform is CLI-first, which allows your coding agents like Claude Code & Codex to help you debug, hypothesize improvements, and analyze outputs. Congrats on the launch Vivek Raja, Stavros Filosidis, and Filip Balucha!
1:27

Agent apps don’t win on the model, they win on the harness. But creating that harness is painful. Terminal Use is hosting infrastructure for background agents built for iterating: fork filesystems and try multiple agents in parallel. The platform is CLI-first, which allows your coding agents like Claude Code & Codex to help you debug, hypothesize improvements, and analyze outputs. Congrats on the launch Vivek Raja, Stavros Filosidis, and Filip Balucha!

Y Combinator

61,650 görüntüleme • 7 ay önce

The founder of LangChain says both models and harnesses have gotten really good between December and now. According to Harrison Chase, the core idea of an agent before Christmas was a model running in a loop and calling tools. This had been the north star for 3 years. - langchain had this when it launched - autogpt was the same idea - openclaw is kind of a future version of it Then about a year ago, they started getting really good. Claude Code, Manus, and Deep Research were all launched around the same time. All of them use the same pattern: running in a loop with harnesses (planning tools, file systems, code execution, etc) Harness engineering became a thing. Then Opus came out in November and really unlocked it. - the harness let the model do more and more - less hardcoded logic - way more control Then everyone went on vacation, played around, and realized that the model and the harness finally worked reliably.
2:10

The founder of LangChain says both models and harnesses have gotten really good between December and now. According to Harrison Chase, the core idea of an agent before Christmas was a model running in a loop and calling tools. This had been the north star for 3 years. - langchain had this when it launched - autogpt was the same idea - openclaw is kind of a future version of it Then about a year ago, they started getting really good. Claude Code, Manus, and Deep Research were all launched around the same time. All of them use the same pattern: running in a loop with harnesses (planning tools, file systems, code execution, etc) Harness engineering became a thing. Then Opus came out in November and really unlocked it. - the harness let the model do more and more - less hardcoded logic - way more control Then everyone went on vacation, played around, and realized that the model and the harness finally worked reliably.

Ivan Burazin

33,948 görüntüleme • 5 ay önce

HarnessRouter just open sourced a plug-and-play infrastructure layer that runs Codex, Claude Code, Hermes, DeepSeek Harness, System One powered by Jev and 9 more agent harnesses under one interface, with a Unified Harness Protocol and OpenAI Responses-compatible API. → Bring Jev into the same product already using Codex or Claude Code without writing another implementation → Handles sessions, streaming, files, cancellation and failure handling in one place → Harnesses run locally with the UHP defining the common task interface
0:25

HarnessRouter just open sourced a plug-and-play infrastructure layer that runs Codex, Claude Code, Hermes, DeepSeek Harness, System One powered by Jev and 9 more agent harnesses under one interface, with a Unified Harness Protocol and OpenAI Responses-compatible API. → Bring Jev into the same product already using Codex or Claude Code without writing another implementation → Handles sessions, streaming, files, cancellation and failure handling in one place → Harnesses run locally with the UHP defining the common task interface

0xMarioNawfal

52,014 görüntüleme • 5 gün önce

how is this even allowed i dropped my $200/mo claude plan for deepseek harness, it’s basically free the whole thing runs on one simple rule: everything is a plugin [setup takes 3 minutes, here’s the playbook] 1. clone/install the repo called deepseek-harness 2. skim the architecture docs 3. that’s it, you’re live bookmark this and hand it to your agent right now.
1:11

how is this even allowed i dropped my $200/mo claude plan for deepseek harness, it’s basically free the whole thing runs on one simple rule: everything is a plugin [setup takes 3 minutes, here’s the playbook] 1. clone/install the repo called deepseek-harness 2. skim the architecture docs 3. that’s it, you’re live bookmark this and hand it to your agent right now.

CyrilXBT

42,892 görüntüleme • 1 ay önce

run agent harnesses 100% private & offline. (no token costs, no API keys, 100% open-source) your agent runs locally. the model doesn't. every prompt, every file, and every secret still leaves your machine before the agent does anything with it. Magnitude fixes that. it's an open source inference server that runs models on your own hardware and plugs into the coding agent you already use. setup is one command. it profiles your machine, measures the memory bandwidth that sets your token rate, and hands back complete configurations instead of a list of models. each one names a model, a compression level, a context size, and a speed range you can expect. pick one and start working. it doesn't replace your harness. setup asks which one you want and writes that config for you. Pi, OpenCode, Claude Code, Codex, and Cline all work, and there's a built-in one tuned for local models if you don't have a harness yet. that one uses your shell, edits files, and runs scripts out of the box. add skills and it handles Excel, PowerPoint, PDFs, or Chrome. everyday work it covers: → analyze sensitive data → manage private notes → review code and logs → search and organize files → build docs or slides Apache 2.0. no rate limits, and nothing leaves the machine. 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 the repo is here: (don't forget to star 🌟) i wrote the full breakdown of why picking the configuration is the hard part. the article is quoted below.
0:38

run agent harnesses 100% private & offline. (no token costs, no API keys, 100% open-source) your agent runs locally. the model doesn't. every prompt, every file, and every secret still leaves your machine before the agent does anything with it. Magnitude fixes that. it's an open source inference server that runs models on your own hardware and plugs into the coding agent you already use. setup is one command. it profiles your machine, measures the memory bandwidth that sets your token rate, and hands back complete configurations instead of a list of models. each one names a model, a compression level, a context size, and a speed range you can expect. pick one and start working. it doesn't replace your harness. setup asks which one you want and writes that config for you. Pi, OpenCode, Claude Code, Codex, and Cline all work, and there's a built-in one tuned for local models if you don't have a harness yet. that one uses your shell, edits files, and runs scripts out of the box. add skills and it handles Excel, PowerPoint, PDFs, or Chrome. everyday work it covers: → analyze sensitive data → manage private notes → review code and logs → search and organize files → build docs or slides Apache 2.0. no rate limits, and nothing leaves the machine. 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 the repo is here: (don't forget to star 🌟) i wrote the full breakdown of why picking the configuration is the hard part. the article is quoted below.

Akshay 🚀

55,693 görüntüleme • 25 gün önce

OpenAI engineer: "Nobody on my team has touched code in 9 months. Agents write all the code, the way you do it is harness engineering." In 45 minutes he breaks down exactly how to build the setup so agents do the full job without you in the loop. This beats any paid course on building agents I've seen. Watch it, then read the full guide on harness engineering below.
45:40

OpenAI engineer: "Nobody on my team has touched code in 9 months. Agents write all the code, the way you do it is harness engineering." In 45 minutes he breaks down exactly how to build the setup so agents do the full job without you in the loop. This beats any paid course on building agents I've seen. Watch it, then read the full guide on harness engineering below.

Anatoli Kopadze

25,222 görüntüleme • 1 ay önce

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.
0:29

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.

Akshay 🚀

116,060 görüntüleme • 4 gün önce

One of the easiest wins with an AI agent right now is letting it sign up for your own mobile app on a real phone. There's a repo called Phone Harness that connects Codex or Claude Code to an actual iPhone or Android. The agent sees the screen and can tap, type, scroll, open apps, and verify what happened. Here's the whole setup: 1) Connect the phone. iPhone goes through Mac iPhone mirroring, Android goes through ADB over USB or wireless. 2) You don't have to jailbreak anything, you don't need Xcode, and you don't need a special app on the phone. 3) Paste the setup prompt from the repo into Codex or Claude Code: clone the GitHub, read the install.md, put phone harness on your path, register it as an agent skill, then read onboarding.md and walk me through setup. 4) Run phone-harness 5) Give it the first job: open the app, create an account, tap through onboarding, try checkout, take screenshots, and tell me where it gets confusing or breaks. 6) Then point it at the mobile apps that have no API at all. Every mobile team should be running that signup test constantly. Most don't, because it's tedious, or they don't want to hire that person, or the person makes mistakes anyway. Agents are moving from answering questions to operating tools, and the phone is one of the biggest tool surfaces in the world. Connect the phone, run the doctor, then hand it your signup flow
3:36

One of the easiest wins with an AI agent right now is letting it sign up for your own mobile app on a real phone. There's a repo called Phone Harness that connects Codex or Claude Code to an actual iPhone or Android. The agent sees the screen and can tap, type, scroll, open apps, and verify what happened. Here's the whole setup: 1) Connect the phone. iPhone goes through Mac iPhone mirroring, Android goes through ADB over USB or wireless. 2) You don't have to jailbreak anything, you don't need Xcode, and you don't need a special app on the phone. 3) Paste the setup prompt from the repo into Codex or Claude Code: clone the GitHub, read the install.md, put phone harness on your path, register it as an agent skill, then read onboarding.md and walk me through setup. 4) Run phone-harness 5) Give it the first job: open the app, create an account, tap through onboarding, try checkout, take screenshots, and tell me where it gets confusing or breaks. 6) Then point it at the mobile apps that have no API at all. Every mobile team should be running that signup test constantly. Most don't, because it's tedious, or they don't want to hire that person, or the person makes mistakes anyway. Agents are moving from answering questions to operating tools, and the phone is one of the biggest tool surfaces in the world. Connect the phone, run the doctor, then hand it your signup flow

The Startup Ideas Podcast (SIP) 🧃

25,561 görüntüleme • 24 gün önce

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.
1:07

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

Xiaoyin Qu

2,223,651 görüntüleme • 1 ay önce