Загрузка видео...

Не удалось загрузить видео

На главную

▣ Introducing Endless: infinite inference (kinda). An experimental harness to milk every ounce out of your Codex subscription. Since Codex can let an in-progress turn keep going even after your usage hits 100%, why not put that to the test? Endless starts one Codex turn and gives the agent...

maria_rcks's profile picture

maria

18,534 subscribers

254,287 просмотров • 1 день назад •via X (Twitter)

Наука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

As bad things happen to you, your Rage builds. Once full, it gives you access to powerful revenge abilities that can help turn the tide of a race. It's another tool in your toolbox, not a replacement for skill.
0:10

As bad things happen to you, your Rage builds. Once full, it gives you access to powerful revenge abilities that can help turn the tide of a race. It's another tool in your toolbox, not a replacement for skill.

Playtonic Games & Friends - WISHLIST SUPER YL KART

27,824 просмотров • 2 месяцев назад

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:
0:13

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:

Sergio Paniego

36,159 просмотров • 17 дней назад

NanoBanana 2 just made your static ad agency obsolete. And I just open sourced the entire tool. Drop your product page URL. It pulls your logos, product images, fonts, colors, and brand voice automatically. Builds a full brand guide for you. Then generates ad creatives at scale using nearly 4,000 high-performing ad templates across 8 niches. It dynamically matches the best templates to your brand and brief. Here's what makes it different: → Instant resizing Get any ad in 1x1, 4x5, 9x16 with one click. No regeneration. No broken text. → Highlight-to-edit See an issue? Highlight the area and tell it what to fix. → Multiple brand profiles Run different brands or segments from one tool. → Auto persona building from real customer reviews → Multiple QC loops on briefs and final assets Catches AI-isms before you do. → Upload your own templates or use ours Runs locally. Just needs your Claude and Google API keys. This is the lite version of what we use internally. You get the full finished tool AND the open source code to make it your own. Creatives still design the system, this handles iteration and scale. Want a copy to download? 1. Like this post 2. Comment "AI" Will DM you the tool along with a tutorial shortly after.
0:13

NanoBanana 2 just made your static ad agency obsolete. And I just open sourced the entire tool. Drop your product page URL. It pulls your logos, product images, fonts, colors, and brand voice automatically. Builds a full brand guide for you. Then generates ad creatives at scale using nearly 4,000 high-performing ad templates across 8 niches. It dynamically matches the best templates to your brand and brief. Here's what makes it different: → Instant resizing Get any ad in 1x1, 4x5, 9x16 with one click. No regeneration. No broken text. → Highlight-to-edit See an issue? Highlight the area and tell it what to fix. → Multiple brand profiles Run different brands or segments from one tool. → Auto persona building from real customer reviews → Multiple QC loops on briefs and final assets Catches AI-isms before you do. → Upload your own templates or use ours Runs locally. Just needs your Claude and Google API keys. This is the lite version of what we use internally. You get the full finished tool AND the open source code to make it your own. Creatives still design the system, this handles iteration and scale. Want a copy to download? 1. Like this post 2. Comment "AI" Will DM you the tool along with a tutorial shortly after.

Peter Quadrel

292,205 просмотров • 5 месяцев назад

for everyone in the doodles community who’s ever wanted a toy of their OG: the wait is over. i built a tool for that gives you a copy and past prompt to make your own toy. try it out at ⬇️
0:19

for everyone in the doodles community who’s ever wanted a toy of their OG: the wait is over. i built a tool for that gives you a copy and past prompt to make your own toy. try it out at ⬇️

doodlifts

13,365 просмотров • 1 день назад

Alright, now that we know *what* an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.
0:15

Alright, now that we know *what* an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.

Google AI

22,487 просмотров • 9 месяцев назад

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.
0:16

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 просмотров • 3 дней назад

if you use claude code, this will save you real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.
0:11

if you use claude code, this will save you real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.

Alvaro Cintas

74,076 просмотров • 20 дней назад

this is the worst local ai will ever be. it only gets better from here. if you are not expanding your mind with these small models you are missing what's happening right now 99 percent tool call success rate. when steered well with the right skills and a framework like hermes agent the node becomes a cognition layer. not a chatbot. not a toy. an extension of how you think. i was cranking this node at 35 to 50 tok/s all day on personal experiments and now after all the work is done qwen 3.5 9B is iterating on its own code. the game it created. fixing its own bugs autonomously. and the part you should probably not miss is that all of this is happening on a RTX 3060. not an H100. not an A100. the card most of you have sitting in a drawer right now. if you just open that drawer and put that intelligence to work every tensor core on that card should be running for you. your work. your experiments. your thinking. you all have it but because nobody told you what this hardware can actually do in 2026 you never tried. the day it unlocks is the day you test your workload, understand the tradeoffs, debug the loops, and then decide if you need to scale the hardware. there is no point buying 3 mac studios when things done well you can squeeze a similar level of intelligence from 9B compared to 70B. but only when you create the right environment for your model through the right harness. and let me tell you i have tried claude code as a local harness. i have tried opencode. i have tried various others. somehow i landed on hermes agent and never left. there is something magical going on at Nous Research. the tool call parsers, the skills system, the way it handles small models natively. nothing else comes close for local inference. own your cognition. your AI. your agent. your prompts. your experiments. why give them away for free. those are who you are and they don't belong on someone else's servers being monitored. just give it a shot with your existing hardware. you run into a problem the community will help you. and if you are migrating from openclaw to hermes i will personally help you make the switch.
0:13

this is the worst local ai will ever be. it only gets better from here. if you are not expanding your mind with these small models you are missing what's happening right now 99 percent tool call success rate. when steered well with the right skills and a framework like hermes agent the node becomes a cognition layer. not a chatbot. not a toy. an extension of how you think. i was cranking this node at 35 to 50 tok/s all day on personal experiments and now after all the work is done qwen 3.5 9B is iterating on its own code. the game it created. fixing its own bugs autonomously. and the part you should probably not miss is that all of this is happening on a RTX 3060. not an H100. not an A100. the card most of you have sitting in a drawer right now. if you just open that drawer and put that intelligence to work every tensor core on that card should be running for you. your work. your experiments. your thinking. you all have it but because nobody told you what this hardware can actually do in 2026 you never tried. the day it unlocks is the day you test your workload, understand the tradeoffs, debug the loops, and then decide if you need to scale the hardware. there is no point buying 3 mac studios when things done well you can squeeze a similar level of intelligence from 9B compared to 70B. but only when you create the right environment for your model through the right harness. and let me tell you i have tried claude code as a local harness. i have tried opencode. i have tried various others. somehow i landed on hermes agent and never left. there is something magical going on at Nous Research. the tool call parsers, the skills system, the way it handles small models natively. nothing else comes close for local inference. own your cognition. your AI. your agent. your prompts. your experiments. why give them away for free. those are who you are and they don't belong on someone else's servers being monitored. just give it a shot with your existing hardware. you run into a problem the community will help you. and if you are migrating from openclaw to hermes i will personally help you make the switch.

Sudo su

58,717 просмотров • 5 месяцев назад

🚨 do you understand what OpenAI just announced.. ChatGPT Pro is now $100/month. 10x more Codex usage. and Codex isn't autocomplete - it writes, debugs, builds entire apps. autonomously. if you've used Claude Opus for coding you know the feeling. Codex hits the same way. except Claude Opus limits burn through in hours. you blink and you're out. Codex just got a $100 tier built to run 24/7. no cooldowns. no "you've reached your limit" at 2am mid-build. they're not selling you a chatbot. they're selling you a software engineer that never sleeps and never asks for equity. and they're doing it quietly while everyone argues about tariffs.
0:15

🚨 do you understand what OpenAI just announced.. ChatGPT Pro is now $100/month. 10x more Codex usage. and Codex isn't autocomplete - it writes, debugs, builds entire apps. autonomously. if you've used Claude Opus for coding you know the feeling. Codex hits the same way. except Claude Opus limits burn through in hours. you blink and you're out. Codex just got a $100 tier built to run 24/7. no cooldowns. no "you've reached your limit" at 2am mid-build. they're not selling you a chatbot. they're selling you a software engineer that never sleeps and never asks for equity. and they're doing it quietly while everyone argues about tariffs.

BuBBliK

439,422 просмотров • 4 месяцев назад

Every AI tool wants its own subscription. We built ours around a token you already hold. Stake once and it earns Sorin credits at 1 per $SAHARA every month, on top of the 3,500 every user gets free. The same stake earns Sahara compute credits next, spendable inside ClawApp or straight through our API. Every product we add plugs into that stake, and there is never anything to restake. And you keep the SAHARA the whole time. Unstake whenever you want and you walk away with everything you came in with. Own your compute.
0:16

Every AI tool wants its own subscription. We built ours around a token you already hold. Stake once and it earns Sorin credits at 1 per $SAHARA every month, on top of the 3,500 every user gets free. The same stake earns Sahara compute credits next, spendable inside ClawApp or straight through our API. Every product we add plugs into that stake, and there is never anything to restake. And you keep the SAHARA the whole time. Unstake whenever you want and you walk away with everything you came in with. Own your compute.

Sahara AI 🔆

16,527 просмотров • 6 дней назад

The Matrix launch video lands on one line; in Matrix, anyone can become a CEO. That’s the real claim. Not one assistant doing one task. A company that keeps running after the first prompt, routing intent through a CEO Office, into OKRs, down to departments that do the work and send back proof to review. Connect Codex, point your leftover credits at it, and the first agent company is live.
0:17

The Matrix launch video lands on one line; in Matrix, anyone can become a CEO. That’s the real claim. Not one assistant doing one task. A company that keeps running after the first prompt, routing intent through a CEO Office, into OKRs, down to departments that do the work and send back proof to review. Connect Codex, point your leftover credits at it, and the first agent company is live.

Iseunife The First

19,414 просмотров • 1 месяц назад

THIS GUY VIBE CODED A BROWSER TOOL WITH CLAUDE CODE THAT DRAWS PROPERTY LINES ONTO DRONE FOOTAGE AND KEEPS THEM LOCKED TO THE GROUND AS THE DRONE MOVES real estate agents kept asking for those property boundary overlays on drone videos so buyers can see exactly where a lot ends. the only real option was after effects, which is a massive pro tool for one small repeatable job so he built a browser tool that does just that one thing > drop in a drone clip and draw the parcel outline once on the first frame > gpu motion tracking keeps that boundary stuck to the ground as the drone flies and the perspective shifts > if the line drifts anywhere, you drop a keyframe to correct it and it re-tracks the segments around it > style the line however you want, then export the finished video > free to use, you dont even need an account until you export he built one tool that solves one annoying job perfectly, for people who were never going to learn after effects anyway
0:13

THIS GUY VIBE CODED A BROWSER TOOL WITH CLAUDE CODE THAT DRAWS PROPERTY LINES ONTO DRONE FOOTAGE AND KEEPS THEM LOCKED TO THE GROUND AS THE DRONE MOVES real estate agents kept asking for those property boundary overlays on drone videos so buyers can see exactly where a lot ends. the only real option was after effects, which is a massive pro tool for one small repeatable job so he built a browser tool that does just that one thing > drop in a drone clip and draw the parcel outline once on the first frame > gpu motion tracking keeps that boundary stuck to the ground as the drone flies and the perspective shifts > if the line drifts anywhere, you drop a keyframe to correct it and it re-tracks the segments around it > style the line however you want, then export the finished video > free to use, you dont even need an account until you export he built one tool that solves one annoying job perfectly, for people who were never going to learn after effects anyway

Om Patel

403,842 просмотров • 1 месяц назад

Want to reduce a LOT of the censorship in Seedance 2.0? I’m going to show you a simple method that almost nobody is using — and it can completely change the results of your videos. Tutorial: First, ask ChatGPT to translate your entire prompt into the Tibetan language. Since it is a less common language in China, this can sometimes help bypass some of the censorship limitations. After that, use the translated prompt inside Seedance 2.0 to generate the video. This is exactly how the video shown above was created. To generate the videos, use Yapper . The recommendation is to create multiple videos at the same time — for example, generate 8 videos at once — to increase the chances of getting an even better result.
0:15

Want to reduce a LOT of the censorship in Seedance 2.0? I’m going to show you a simple method that almost nobody is using — and it can completely change the results of your videos. Tutorial: First, ask ChatGPT to translate your entire prompt into the Tibetan language. Since it is a less common language in China, this can sometimes help bypass some of the censorship limitations. After that, use the translated prompt inside Seedance 2.0 to generate the video. This is exactly how the video shown above was created. To generate the videos, use Yapper . The recommendation is to create multiple videos at the same time — for example, generate 8 videos at once — to increase the chances of getting an even better result.

nachos2d

30,513 просмотров • 5 месяцев назад

Another WTF moment. A developer just open-sourced a coding agent harness that boots 245x faster than Claude Code. It's called jcode. You launch it and the first frame renders in 14 milliseconds. Claude Code takes 3,436. One active session uses 27.8 MB of RAM. Claude Code uses 386.6. Run ten sessions in parallel and jcode holds at 117 MB while OpenCode swells to 3.2 GB. Each agent has a semantic memory graph instead of a scratchpad. Every turn gets embedded as a vector. The graph is queried on every turn for related memories, and a sideagent verifies the hits before injecting them into context. Consolidation runs in the background to check for stale or conflicting facts. No manual /remember calls. No token burn on lookup tools. The provider list is 30+ deep. Claude, ChatGPT, Gemini, GitHub Copilot, Azure, OpenRouter, DeepSeek, Groq, Mistral, Perplexity, Fireworks, Ollama, LM Studio, and any OpenAI-compatible endpoint you point it at. Ran out of tokens on your first ChatGPT Pro sub? /account swaps to the second. Then there's Swarm. Spawn two agents in the same repo and the server manages them. When agent A edits a file agent B has been reading, agent B gets pinged and can check the diff. Agents can DM each other, broadcast to the room, or spawn their own worker teams for parallel tasks. Groups, channels, and completion statuses are handled automatically. The UI has live side panels that render mermaid diagrams inline. To make it fast, the author wrote a Rust mermaid renderer 1800x faster than the JavaScript one, then wrote a custom terminal called Handterm because no existing terminal could do smooth partial-line scrolling. Self-dev mode is where it gets wild. Tell your agent to enter self-dev and it starts editing jcode's own source code, rebuilds the binary, reloads it live, and keeps working across your existing sessions. You can also resume broken sessions from Claude Code, Codex, OpenCode, or pi directly inside jcode. Anthropic's cache goes cold at the 5-minute mark and you're staring down a big cache miss on your next turn? The UI warns you before you spend the tokens. Written in Rust. MIT licensed. Runs on macOS, Windows, Linux, and Termux. Sitting at 11.2k stars with a native iOS app coming.
0:17

Another WTF moment. A developer just open-sourced a coding agent harness that boots 245x faster than Claude Code. It's called jcode. You launch it and the first frame renders in 14 milliseconds. Claude Code takes 3,436. One active session uses 27.8 MB of RAM. Claude Code uses 386.6. Run ten sessions in parallel and jcode holds at 117 MB while OpenCode swells to 3.2 GB. Each agent has a semantic memory graph instead of a scratchpad. Every turn gets embedded as a vector. The graph is queried on every turn for related memories, and a sideagent verifies the hits before injecting them into context. Consolidation runs in the background to check for stale or conflicting facts. No manual /remember calls. No token burn on lookup tools. The provider list is 30+ deep. Claude, ChatGPT, Gemini, GitHub Copilot, Azure, OpenRouter, DeepSeek, Groq, Mistral, Perplexity, Fireworks, Ollama, LM Studio, and any OpenAI-compatible endpoint you point it at. Ran out of tokens on your first ChatGPT Pro sub? /account swaps to the second. Then there's Swarm. Spawn two agents in the same repo and the server manages them. When agent A edits a file agent B has been reading, agent B gets pinged and can check the diff. Agents can DM each other, broadcast to the room, or spawn their own worker teams for parallel tasks. Groups, channels, and completion statuses are handled automatically. The UI has live side panels that render mermaid diagrams inline. To make it fast, the author wrote a Rust mermaid renderer 1800x faster than the JavaScript one, then wrote a custom terminal called Handterm because no existing terminal could do smooth partial-line scrolling. Self-dev mode is where it gets wild. Tell your agent to enter self-dev and it starts editing jcode's own source code, rebuilds the binary, reloads it live, and keeps working across your existing sessions. You can also resume broken sessions from Claude Code, Codex, OpenCode, or pi directly inside jcode. Anthropic's cache goes cold at the 5-minute mark and you're staring down a big cache miss on your next turn? The UI warns you before you spend the tokens. Written in Rust. MIT licensed. Runs on macOS, Windows, Linux, and Termux. Sitting at 11.2k stars with a native iOS app coming.

Brady Long

205,781 просмотров • 26 дней назад

I went a little overboard with Codex last week and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.
0:16

I went a little overboard with Codex last week and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.

雪踏乌云

23,107 просмотров • 28 дней назад

Introducing fx, a tiny, open, native coding agent from Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑
0:11

Introducing fx, a tiny, open, native coding agent from Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑

Vercel Developers

927,479 просмотров • 4 дней назад

Updated the subagents system in my custom Pi extension to include: - Pi subagents - Codex subagents - Claude Code subagents The Pi thread can call and spin up any of them, and instead of just using the "codex exec" or whatever, it'll do a tool call that wraps it up in a first class way. Have a decent UI for them already added in as well. Pi being the main thread then having Codex/Claude Code as tools when needed feels so good. A flow I'm already using a ton is: "Implement feature ___, have a cc fable subagent research and plan out the api design + feature, then have a codex subagent implement it, then have a cc fable subagent do a review/fixes focused on simplicity and correctness" I also have a dynamic workflows extension setup and working, but it's not nearly as polished yet. Probably gonna make the subagent system more robust, then built it around that so u could have a workflow that flows between codex/cc/pi...
0:19

Updated the subagents system in my custom Pi extension to include: - Pi subagents - Codex subagents - Claude Code subagents The Pi thread can call and spin up any of them, and instead of just using the "codex exec" or whatever, it'll do a tool call that wraps it up in a first class way. Have a decent UI for them already added in as well. Pi being the main thread then having Codex/Claude Code as tools when needed feels so good. A flow I'm already using a ton is: "Implement feature ___, have a cc fable subagent research and plan out the api design + feature, then have a codex subagent implement it, then have a cc fable subagent do a review/fixes focused on simplicity and correctness" I also have a dynamic workflows extension setup and working, but it's not nearly as polished yet. Probably gonna make the subagent system more robust, then built it around that so u could have a workflow that flows between codex/cc/pi...

Ben Davis

24,827 просмотров • 1 месяц назад

TikTok Shop + Seedance 2 + Claude Code is f*cking cracked i just built a tool that scrapes the top-selling TikTok Shop products in your niche, pulls every creator video selling them, and lets you recreate any one as an on-brand video for your own product using AI. if you're a DTC brand or ecom operator and you're still paying creators $500 per video or briefing an agency every week, this replaces that entire workflow. here's how it works: > drop in your brand info and 1-3 product photos search your niche on TikTok Shop like "gut health supplements" or "skincare" or whatever you're selling > browse the top-selling products and every creator video promoting them pick a viral video that's already proven to convert > the AI analyzes the hook, structure, and pacing > one click and Seedance 2 generates a new version built around your product why test from scratch when you can just recreate what's already working? RT + reply "VIRAL" and i'll send you the full app + setup guide (must follow so i can dm)
0:13

TikTok Shop + Seedance 2 + Claude Code is f*cking cracked i just built a tool that scrapes the top-selling TikTok Shop products in your niche, pulls every creator video selling them, and lets you recreate any one as an on-brand video for your own product using AI. if you're a DTC brand or ecom operator and you're still paying creators $500 per video or briefing an agency every week, this replaces that entire workflow. here's how it works: > drop in your brand info and 1-3 product photos search your niche on TikTok Shop like "gut health supplements" or "skincare" or whatever you're selling > browse the top-selling products and every creator video promoting them pick a viral video that's already proven to convert > the AI analyzes the hook, structure, and pacing > one click and Seedance 2 generates a new version built around your product why test from scratch when you can just recreate what's already working? RT + reply "VIRAL" and i'll send you the full app + setup guide (must follow so i can dm)

Miko

100,067 просмотров • 3 месяцев назад

I’m joining OpenAI Codex to work on the future of agentic development! At Cursor, I got to see the shift from autocomplete to agents. The next step isn’t a better IDE. It’s an Agent Development Environment (ADE): systems and tools for orchestrating agents, reasoning over their outputs, and making them autonomous enough to reliably complete ambitious work. After chatting with Alexander Embiricos and Tibo, it was clear that Codex is the best place to realize this vision. The team has consistently shipped SOTA models for agentic coding (check out gpt-5.3-codex) and I’m pumped for the future that the new Codex App points to. What I’m most excited about is the broader mission: accelerating the knowledge work economy. All agents are coding agents, and we’re already seeing Codex used across every job function within organizations. I’m extremely grateful for my time at Cursor, working with the incredible team, and I’m proud of what we built together. I’m excited to take an even bigger swing with Codex. If you’re curious to get a glimpse of where we are headed, download the Codex App! If you want to work on this mission, please apply or reach out - we are hiring across all functions! You can just build things.
0:12

I’m joining OpenAI Codex to work on the future of agentic development! At Cursor, I got to see the shift from autocomplete to agents. The next step isn’t a better IDE. It’s an Agent Development Environment (ADE): systems and tools for orchestrating agents, reasoning over their outputs, and making them autonomous enough to reliably complete ambitious work. After chatting with Alexander Embiricos and Tibo, it was clear that Codex is the best place to realize this vision. The team has consistently shipped SOTA models for agentic coding (check out gpt-5.3-codex) and I’m pumped for the future that the new Codex App points to. What I’m most excited about is the broader mission: accelerating the knowledge work economy. All agents are coding agents, and we’re already seeing Codex used across every job function within organizations. I’m extremely grateful for my time at Cursor, working with the incredible team, and I’m proud of what we built together. I’m excited to take an even bigger swing with Codex. If you’re curious to get a glimpse of where we are headed, download the Codex App! If you want to work on this mission, please apply or reach out - we are hiring across all functions! You can just build things.

Rohan Varma

759,796 просмотров • 6 месяцев назад