Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Codex can spawn grok 4.5 or Kimi k3 as subagents now. Not more GPT, other companies' models, running underneath it, in the same session. Wired both into my picker weeks ago. Today they stopped being alternatives and started taking jobs. Each agent gets its own context window and runs... show more

Ziwen

16,276 subscribers

46,651 Aufrufe • vor 3 Tagen •via X (Twitter)

Wissenschaft & Technologie Bildung Nachrichten & Politik

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

It worked!! Kimi k3 Oauth is now wired directly into codex. The Kimi k3 model is insane but their app is not. So I figure a better way to use k3 by hooking my sub straight into codex instead. K3 now sits in the model picker next to Sol 5.6. Same subscription i was already paying for, no api key, just have to do OAuth in Kimi Code. Links down below 👇

It worked!! Kimi k3 Oauth is now wired directly into codex. The Kimi k3 model is insane but their app is not. So I figure a better way to use k3 by hooking my sub straight into codex instead. K3 now sits in the model picker next to Sol 5.6. Same subscription i was already paying for, no api key, just have to do OAuth in Kimi Code. Links down below 👇

Ziwen

274,480 Aufrufe • vor 13 Tagen

You can now orchestrate subagents running in Claude Code, Codex, or the Warp Agent. Let the agent create a delegation plan, and watch subagents coordinate with message passing. Each agent gets its own worktree for isolation. Here's how it works with eng Matthew Albright:

You can now orchestrate subagents running in Claude Code, Codex, or the Warp Agent. Let the agent create a delegation plan, and watch subagents coordinate with message passing. Each agent gets its own worktree for isolation. Here's how it works with eng Matthew Albright:

Warp

20,775 Aufrufe • vor 2 Monaten

Agent Zero crushed Codex by 2.6× on token efficiency! We gave both agents the same task on the same local model (Qwen3.6 27B): build a retro Q*bert arcade game. Each agent wrote and rewrote it across iterations, adding enemies and a HUD. Outputs: • Agent Zero: 239K tokens, 53 min • Codex: 627K tokens, 51 min Both agents built a working Q*bert, but GitLawb 's Agent Zero is the cleaner build, with crisper textures and hops that land where they should. Codex refills the context window with its whole history every turn, so the model loses the thread and hallucinates code it never wrote. Agent Zero sends only what's new, so it keeps more of the window open and makes fewer mistakes. Run agents on local AI models in Atomic Chat!

Agent Zero crushed Codex by 2.6× on token efficiency! We gave both agents the same task on the same local model (Qwen3.6 27B): build a retro Qbert arcade game. Each agent wrote and rewrote it across iterations, adding enemies and a HUD. Outputs: • Agent Zero: 239K tokens, 53 min • Codex: 627K tokens, 51 min Both agents built a working Qbert, but GitLawb 's Agent Zero is the cleaner build, with crisper textures and hops that land where they should. Codex refills the context window with its whole history every turn, so the model loses the thread and hallucinates code it never wrote. Agent Zero sends only what's new, so it keeps more of the window open and makes fewer mistakes. Run agents on local AI models in Atomic Chat!

atomic.chat

319,140 Aufrufe • vor 9 Tagen

Claude Code subagents can nest 5 levels deep now Boris Cherny announced it, and today I finally got to try it, Here's the full chain running end to end: - main - project-auditor // level 1 - structure-checker // level 2 - import-validator // level 3 - dependency-tracer // level 4 - style-sync // level 5 Each level runs in its own context window Only the top-level summary returns to main, depth 5 is the hard cap, that agent can't spawn further

Claude Code subagents can nest 5 levels deep now Boris Cherny announced it, and today I finally got to try it, Here's the full chain running end to end: - main - project-auditor // level 1 - structure-checker // level 2 - import-validator // level 3 - dependency-tracer // level 4 - style-sync // level 5 Each level runs in its own context window Only the top-level summary returns to main, depth 5 is the hard cap, that agent can't spawn further

Daniel San

151,719 Aufrufe • vor 1 Monat

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

savip

68,860 Aufrufe • vor 14 Tagen

THIS GUY MADE CLAUDE CODE AND CODEX TALK TO EACH OTHER not by switching between them, they literally talk to each other about your code in real time you give it a task. it spawns a Claude agent and a Codex agent in separate sessions. they share findings, challenge each other, and produce a combined result. he pointed them at an Express API with intentional security issues. within minutes they found SQL injection, hardcoded secrets, missing auth, and weak JWT config. one catches something and the other confirms it and adds context. they divide the work on their own for faster speed one command: /collab "review auth.js for security issues" that's it. you watch the conversation happen in real time. AND its open source with new models being integrated crazy to think that this was entirely vibe coded

THIS GUY MADE CLAUDE CODE AND CODEX TALK TO EACH OTHER not by switching between them, they literally talk to each other about your code in real time you give it a task. it spawns a Claude agent and a Codex agent in separate sessions. they share findings, challenge each other, and produce a combined result. he pointed them at an Express API with intentional security issues. within minutes they found SQL injection, hardcoded secrets, missing auth, and weak JWT config. one catches something and the other confirms it and adds context. they divide the work on their own for faster speed one command: /collab "review auth.js for security issues" that's it. you watch the conversation happen in real time. AND its open source with new models being integrated crazy to think that this was entirely vibe coded

Om Patel

25,318 Aufrufe • vor 4 Monaten

voice prompting is 4x faster than typing. but i NEEEDED more. Nvidia parakeet allows me to fully voice control an agentic development environment with commands firing in under 300ms. and it runs 100% local. I added gpt realtime 2.1 mini, its 20% faster, 7 to 20x cheaper, and lets you have full jarvis style control of your vibe coding agents. but what about orchestration? agents can spawn each other, prompt each other, and read each others output with the CNVS mcp and cli. Fable 5 can create a plan, spawn 10 grok agents to execute, and a kimi k3 agent to review. parallel agents code at 1,000s of TPS anthropic's own research shows improvements ACROSS the board for multi agent workflows over single agent but only CNVS lets you choose exactly which orchestration, worker, and reviewer agent you would like to use. grok, kimi, qwen, claude, codex... the cross agent memory system is based on real 2026 research so all agents share the same brain, its on demand so it never bloats context. what about remote agents?? You can create remote canvasses that run agents your virtual private servers, they keep working even if your mac shuts off, and you can even vibe code straight to production. CNVS is built from the ground up ENTIRELY in swift for RAW performance on apple hardware. PS - its a LIFE TIME LICENSE because you don't need another subscription. PPS - I ship updates every week based off user feedback and livestream myself building it everyday. PPPS - it uses all your existing ai subs, so no api pricing here.

voice prompting is 4x faster than typing. but i NEEEDED more. Nvidia parakeet allows me to fully voice control an agentic development environment with commands firing in under 300ms. and it runs 100% local. I added gpt realtime 2.1 mini, its 20% faster, 7 to 20x cheaper, and lets you have full jarvis style control of your vibe coding agents. but what about orchestration? agents can spawn each other, prompt each other, and read each others output with the CNVS mcp and cli. Fable 5 can create a plan, spawn 10 grok agents to execute, and a kimi k3 agent to review. parallel agents code at 1,000s of TPS anthropic's own research shows improvements ACROSS the board for multi agent workflows over single agent but only CNVS lets you choose exactly which orchestration, worker, and reviewer agent you would like to use. grok, kimi, qwen, claude, codex... the cross agent memory system is based on real 2026 research so all agents share the same brain, its on demand so it never bloats context. what about remote agents?? You can create remote canvasses that run agents your virtual private servers, they keep working even if your mac shuts off, and you can even vibe code straight to production. CNVS is built from the ground up ENTIRELY in swift for RAW performance on apple hardware. PS - its a LIFE TIME LICENSE because you don't need another subscription. PPS - I ship updates every week based off user feedback and livestream myself building it everyday. PPPS - it uses all your existing ai subs, so no api pricing here.

Max Blade

59,970 Aufrufe • vor 13 Tagen

Today Perplexity shipped everything Siri was supposed to be 💻 Personal computer now has access to: → iMessage → Every folder on your Mac → 400+ connected apps → Apple Mail, Calendars, Browsers etc... Underneath, Claude Opus 4.7 is the brain. It breaks your goal into subtasks and routes each one to whichever of 20 models wins at it. GPT for long context. Gemini for deep research. Grok for speed. Nano Banana for images. Veo for video. Codex for code. It runs 24/7. You can trigger it from your phone. Pretty sweet design too

Today Perplexity shipped everything Siri was supposed to be 💻 Personal computer now has access to: → iMessage → Every folder on your Mac → 400+ connected apps → Apple Mail, Calendars, Browsers etc... Underneath, Claude Opus 4.7 is the brain. It breaks your goal into subtasks and routes each one to whichever of 20 models wins at it. GPT for long context. Gemini for deep research. Grok for speed. Nano Banana for images. Veo for video. Codex for code. It runs 24/7. You can trigger it from your phone. Pretty sweet design too

Josh Kale

665,332 Aufrufe • vor 3 Monaten

Qwen 3.8 will be benchmaxxed slop second to fable 5 is such a hype statement , its not even close to kimi k3 and GPT-5.6 sol you can test it yourself on the qwen chat website currently available > token hungry > not that good as advertised , will test more The best part of kimi was that in blog they themselves wrote its not comparable to fable 5 and sol 5.6 in bunch of user experience stuff We need more truth like this in our industry , other than that i will run my vision test

Qwen 3.8 will be benchmaxxed slop second to fable 5 is such a hype statement , its not even close to kimi k3 and GPT-5.6 sol you can test it yourself on the qwen chat website currently available > token hungry > not that good as advertised , will test more The best part of kimi was that in blog they themselves wrote its not comparable to fable 5 and sol 5.6 in bunch of user experience stuff We need more truth like this in our industry , other than that i will run my vision test

Chetaslua

126,677 Aufrufe • vor 14 Tagen

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

am.will

57,121 Aufrufe • vor 6 Monaten

I built the clipboard I always wanted for working with AI agents. It’s called Bluey and It’s 100% local-first. It lives under your mouse cursor. You can draw on your screen, speak to it, or type what you mean, and Bluey turns all of that into rich context for Claude Code or Codex. I’ve been using it to design websites and debug UI because I can finally say things like “move this here” or “make this section feel cleaner” while pointing at the actual screen. No more writing long explanations. No more manually describing screenshots. No more agents getting lost because they don’t know what “this” or "that" means. You can just point to it, speak or type and it will curate the best possible context for your agents Bluey captures the screenshot, annotation, transcript, app/window context, and the details your agent needs, then sends it directly into your coding session. I am giving it out for free for a while! Im building it with my buddy Omkar Satpute and we would love to hear what you think about it on Discord what context do you wish your agent could understand better?

I built the clipboard I always wanted for working with AI agents. It’s called Bluey and It’s 100% local-first. It lives under your mouse cursor. You can draw on your screen, speak to it, or type what you mean, and Bluey turns all of that into rich context for Claude Code or Codex. I’ve been using it to design websites and debug UI because I can finally say things like “move this here” or “make this section feel cleaner” while pointing at the actual screen. No more writing long explanations. No more manually describing screenshots. No more agents getting lost because they don’t know what “this” or "that" means. You can just point to it, speak or type and it will curate the best possible context for your agents Bluey captures the screenshot, annotation, transcript, app/window context, and the details your agent needs, then sends it directly into your coding session. I am giving it out for free for a while! Im building it with my buddy Omkar Satpute and we would love to hear what you think about it on Discord what context do you wish your agent could understand better?

Milind S

13,342 Aufrufe • vor 1 Monat

HERMES AGENT VS OPENCLAW. a local ai onboarding flow test. a 3.9gb bonsai served on localhost, both agents upstream and latest, i point each one at the endpoint and watch which one even finds it. > hermes opens a provider menu, thirty plus options, local servers sitting right there next to the cloud ones, i hand it 127.0.0.1:8899, it verifies the endpoint, one model visible, auto-detects the model by name, bonsai-27b-q1_0, reads the context length straight off the server, saves it, and starts reasoning and firing real tool calls on my local model. no key. no friction. > openclaw has no menu. it goes hunting for a codex login, an openai key, finds none because there are none, prints no models available three times, defaults to openai/gpt-5.5, a cloud model it cannot reach, and dead ends on run auth login --provider openai. read that back. it asked me for an openai key. to run a model already running on my own machine. it never once looked at localhost. to be fair, openclaw can run local if you hand wire endpoint yourself. what it will not do is find the model already sitting on your box. hermes agent found it in one line. now the part i owe you. the auto-detect that just won, the model name read, the .gguf strip, the context length probe off the server, that is my code, it is in hermes agent main right now, authorship preserved, #2051 and #4218. the wizard fix that stops an agent from silently routing you to someone else's creds, the exact trap openclaw still falls into, mine too, #4210. i contribute to hermes agent, i told you that going in. one agent is built to talk to whatever you are running, the other is built to talk to a cloud api, so one found my model and ran it and the other asked me to log into openai. onboarding flow of both, mapped, below.

HERMES AGENT VS OPENCLAW. a local ai onboarding flow test. a 3.9gb bonsai served on localhost, both agents upstream and latest, i point each one at the endpoint and watch which one even finds it. > hermes opens a provider menu, thirty plus options, local servers sitting right there next to the cloud ones, i hand it 127.0.0.1:8899, it verifies the endpoint, one model visible, auto-detects the model by name, bonsai-27b-q1_0, reads the context length straight off the server, saves it, and starts reasoning and firing real tool calls on my local model. no key. no friction. > openclaw has no menu. it goes hunting for a codex login, an openai key, finds none because there are none, prints no models available three times, defaults to openai/gpt-5.5, a cloud model it cannot reach, and dead ends on run auth login --provider openai. read that back. it asked me for an openai key. to run a model already running on my own machine. it never once looked at localhost. to be fair, openclaw can run local if you hand wire endpoint yourself. what it will not do is find the model already sitting on your box. hermes agent found it in one line. now the part i owe you. the auto-detect that just won, the model name read, the .gguf strip, the context length probe off the server, that is my code, it is in hermes agent main right now, authorship preserved, #2051 and #4218. the wizard fix that stops an agent from silently routing you to someone else's creds, the exact trap openclaw still falls into, mine too, #4210. i contribute to hermes agent, i told you that going in. one agent is built to talk to whatever you are running, the other is built to talk to a cloud api, so one found my model and ran it and the other asked me to log into openai. onboarding flow of both, mapped, below.

Sudo su

23,816 Aufrufe • vor 15 Tagen

HERMES AGENT NOW RUNS ON AN 8GB LAPTOP GPU JUST AS EASILY AS IT RUNS ON A 128GB MINI PC Nous Research shipped the official Hermes Agent Desktop App this week. Someone pointed it at a local llama server running on an RTX 4060 with 16GB system RAM. The integration took two minutes The model behind it: Gemma 4 26B MoE, QAT quantized, running on 8GB of VRAM. A 60k token prompt held a stable 20 tokens a second, flat, no slowdown as context grew. The flags were nothing exotic, just -cmoe -c 248000 on llama.cpp What that 8GB setup does out of the box: reads and patches its own code, runs it in a terminal, debugs errors, manages GitHub repos, spawns sub-agents for parallel work. Browses the web with vision to debug a UI. Schedules cron jobs in plain language. Connects to Notion, Google Workspace, Linear, and Obsidian to manage tasks on its own That's the same agent layer running on a Minisforum MS-S1 MAX with 128GB of unified memory, 96GB of it to the GPU, holding a 120B model at 56 tokens a second instead of a 26B model at 20. Same software, same tool execution, same zero API key. The only thing that changes between an $800 laptop and a $2,000 mini PC is how big a model you can afford to run underneath it The barrier to running a real autonomous agent locally didn't just drop. It dropped all the way down to hardware most people already own

HERMES AGENT NOW RUNS ON AN 8GB LAPTOP GPU JUST AS EASILY AS IT RUNS ON A 128GB MINI PC Nous Research shipped the official Hermes Agent Desktop App this week. Someone pointed it at a local llama server running on an RTX 4060 with 16GB system RAM. The integration took two minutes The model behind it: Gemma 4 26B MoE, QAT quantized, running on 8GB of VRAM. A 60k token prompt held a stable 20 tokens a second, flat, no slowdown as context grew. The flags were nothing exotic, just -cmoe -c 248000 on llama.cpp What that 8GB setup does out of the box: reads and patches its own code, runs it in a terminal, debugs errors, manages GitHub repos, spawns sub-agents for parallel work. Browses the web with vision to debug a UI. Schedules cron jobs in plain language. Connects to Notion, Google Workspace, Linear, and Obsidian to manage tasks on its own That's the same agent layer running on a Minisforum MS-S1 MAX with 128GB of unified memory, 96GB of it to the GPU, holding a 120B model at 56 tokens a second instead of a 26B model at 20. Same software, same tool execution, same zero API key. The only thing that changes between an $800 laptop and a $2,000 mini PC is how big a model you can afford to run underneath it The barrier to running a real autonomous agent locally didn't just drop. It dropped all the way down to hardware most people already own

NO1ennn

40,079 Aufrufe • vor 1 Monat

introducing OpenBench v1, an open framework for measuring AI performance and efficiency for your codebase and use case. Companies are realizing that you can't simply tokenmaxx, and are frantically looking for better ways to use and measure AI use and efficiency. One approach is evidenced by the rise in model routers: OpenRouter, Cloudflare, Databricks, Vercel, and now Ramp to name a few. But they'll also need the ability to evaluate how agents are performing in their actual use cases and codebase. A good example is DoorDash's recent evals on their codebase and prs. This will become even more important as companies explore different model + harness combinations. OpenBench will be built to this direction, focusing on the cross between correctness vs efficiency in both token use and latency. Starting off, OpenBench makes it easy for anyone to add to the task set, and run a variety of harness + models. The framework also makes it easy to add any custom harness variant, for example I've been testing codex variants with ablations against the stock codex harness. OpenBench will also have tooling to help with discovering/adding reliable tasks from your repo. Today I have integrated harnesses: codex, claude, cursor, devin, grok build, pi, and eval'ed them for different models like gpt 5.6-sol, GLM 5.2, Kimi K3, Grok 4.5, etc. measuring correctness %, token use (in/out/cache), and latency.

introducing OpenBench v1, an open framework for measuring AI performance and efficiency for your codebase and use case. Companies are realizing that you can't simply tokenmaxx, and are frantically looking for better ways to use and measure AI use and efficiency. One approach is evidenced by the rise in model routers: OpenRouter, Cloudflare, Databricks, Vercel, and now Ramp to name a few. But they'll also need the ability to evaluate how agents are performing in their actual use cases and codebase. A good example is DoorDash's recent evals on their codebase and prs. This will become even more important as companies explore different model + harness combinations. OpenBench will be built to this direction, focusing on the cross between correctness vs efficiency in both token use and latency. Starting off, OpenBench makes it easy for anyone to add to the task set, and run a variety of harness + models. The framework also makes it easy to add any custom harness variant, for example I've been testing codex variants with ablations against the stock codex harness. OpenBench will also have tooling to help with discovering/adding reliable tasks from your repo. Today I have integrated harnesses: codex, claude, cursor, devin, grok build, pi, and eval'ed them for different models like gpt 5.6-sol, GLM 5.2, Kimi K3, Grok 4.5, etc. measuring correctness %, token use (in/out/cache), and latency.

Matthew Lam

118,131 Aufrufe • vor 11 Tagen

Biggest lesson from OpenClaw is that a good teammate doesn't start from scratch everytime you check in. They remember what was decided, what's still open, and proactively help you. Today we launched heartbeats in Codex: automations that maintain context inside a single thread over time. Instead of each run starting fresh, Codex wakes up in the same conversation, with the history and context it needs already in place. You can also have it schedule its own next steps – just ask Codex. Think about the overhead that quietly accumulates every morning: scanning Slack channels, catching up on email, piecing together what moved overnight. With a heartbeat, you offload that once, and wake up to a brief already waiting in a pinned thread. If you want to try turning Codex into a chief of staff: connect Slack, Gmail, and Notion, and paste the following prompt into codex: Please check Matt Slack Gmail Notion and write me a morning brief every weekday at 9am in this thread. I want you to collapse all the chaos at work into a single note every morning over some coffee ☕️

Biggest lesson from OpenClaw is that a good teammate doesn't start from scratch everytime you check in. They remember what was decided, what's still open, and proactively help you. Today we launched heartbeats in Codex: automations that maintain context inside a single thread over time. Instead of each run starting fresh, Codex wakes up in the same conversation, with the history and context it needs already in place. You can also have it schedule its own next steps – just ask Codex. Think about the overhead that quietly accumulates every morning: scanning Slack channels, catching up on email, piecing together what moved overnight. With a heartbeat, you offload that once, and wake up to a brief already waiting in a pinned thread. If you want to try turning Codex into a chief of staff: connect Slack, Gmail, and Notion, and paste the following prompt into codex: Please check Matt Slack Gmail Notion and write me a morning brief every weekday at 9am in this thread. I want you to collapse all the chaos at work into a single note every morning over some coffee ☕️

pash

119,478 Aufrufe • vor 3 Monaten

New Kimi K3 beat Opus 4.8 at making retro games for 2x cheaper! We gave three models the same task: make three old arcade games that play by themselves. Each game is one HTML file with a bot that plays it Prompts: – Road Fighter – Battle City – Q*bert Outputs: Kimi K3: 18.4K tokens, $0.28 GPT-5.6: 18.1K tokens, $0.28 Opus 4.8: 21.3K tokens, $0.54 Kimi K3 made the best games. Its Q*bert is the best of all three. The player jumps on the cubes, paints them and runs from the purple snake. Its Battle City looks just like the real game and plays right. The tanks move, aim, shoot and break the walls. GPT-5.6 could not handle the cars. Its Battle City broke too. The tank died on its own and the base got hit. But GPT had the nicest textures of the three

New Kimi K3 beat Opus 4.8 at making retro games for 2x cheaper! We gave three models the same task: make three old arcade games that play by themselves. Each game is one HTML file with a bot that plays it Prompts: – Road Fighter – Battle City – Qbert Outputs: Kimi K3: 18.4K tokens, $0.28 GPT-5.6: 18.1K tokens, $0.28 Opus 4.8: 21.3K tokens, $0.54 Kimi K3 made the best games. Its Qbert is the best of all three. The player jumps on the cubes, paints them and runs from the purple snake. Its Battle City looks just like the real game and plays right. The tanks move, aim, shoot and break the walls. GPT-5.6 could not handle the cars. Its Battle City broke too. The tank died on its own and the base got hit. But GPT had the nicest textures of the three

atomic.chat

98,519 Aufrufe • vor 16 Tagen

I spent today turning a blank Hermes install into a sovereign local agent on my RTX 5090. always-on, reachable over telegram, fully local. here's everything it can do. it runs Qwen3.6-27B on the 5090 and answers from my phone over telegram. ~~~ I first made it faster. switched to the MTP build for self-speculative decoding: 62 > 115 tokens/sec. ~~~ it now benchmarks models on command. I ask it to speed-test a gguf and it stops its own model server to free the gpu, runs llama-bench, renders a card, sends it to my phone, then restarts itself. it's never left offline. ~~~ it also knows me very well. I pointed it to my private HF repo where I store all my AI traces since I started using it. I created a local markdown memory vault, seeded from my own history, with semantic search over it. ~~~ the whole stack stays home: weights on disk, inference on the 5090, the agent in my pocket. here is the video it created to showcase everything it has now.

I spent today turning a blank Hermes install into a sovereign local agent on my RTX 5090. always-on, reachable over telegram, fully local. here's everything it can do. it runs Qwen3.6-27B on the 5090 and answers from my phone over telegram. ~ I first made it faster. switched to the MTP build for self-speculative decoding: 62 > 115 tokens/sec. ~ it now benchmarks models on command. I ask it to speed-test a gguf and it stops its own model server to free the gpu, runs llama-bench, renders a card, sends it to my phone, then restarts itself. it's never left offline. ~ it also knows me very well. I pointed it to my private HF repo where I store all my AI traces since I started using it. I created a local markdown memory vault, seeded from my own history, with semantic search over it. ~ the whole stack stays home: weights on disk, inference on the 5090, the agent in my pocket. here is the video it created to showcase everything it has now.

witcheer

15,041 Aufrufe • vor 2 Monaten

I just built an entire app in 7 minutes using Codex Spark. EveryMCP: a universal MCP server installer that configures 15+ coding agents from a single CLI command. 12 Codex Spark subagents. All running in parallel. At the same time. The project itself isn't complicated, but just imagine what this looks like when you scale the complexity. My setup: • Codex 5.3 High to plan • Codex 5.3 Medium to orchestrate • 12 Codex Spark agents (xhigh) to implement in one shot Spark isn't competing with the big models. It's a different tool entirely. You orchestrate it. You run it in swarms. And it moves at a speed that wasn't possible before, even for the top 1% of AI coders. More complex workflows coming soon. Comment below if you want me to tell you how I did it.

I just built an entire app in 7 minutes using Codex Spark. EveryMCP: a universal MCP server installer that configures 15+ coding agents from a single CLI command. 12 Codex Spark subagents. All running in parallel. At the same time. The project itself isn't complicated, but just imagine what this looks like when you scale the complexity. My setup: • Codex 5.3 High to plan • Codex 5.3 Medium to orchestrate • 12 Codex Spark agents (xhigh) to implement in one shot Spark isn't competing with the big models. It's a different tool entirely. You orchestrate it. You run it in swarms. And it moves at a speed that wasn't possible before, even for the top 1% of AI coders. More complex workflows coming soon. Comment below if you want me to tell you how I did it.

am.will

16,916 Aufrufe • vor 5 Monaten

here is the first look at realtime voice mode in codex the ui is already in the app, but the codex backend endpoint does not seem to be live yet i got it running by forcing the local feature gate and using my own openai api key, so it goes through the public realtime api instead it's incredible, but this demo alone cost me ~$4 gpt realtime 2 is very expensive, which makes me wonder how they're going to handle it - part of the normal usage limit, or a separate limit like we had with gpt 5.3 codex spark? i'm turning it off until the official rollout but get excited, the next few weeks are going to be amazing

here is the first look at realtime voice mode in codex the ui is already in the app, but the codex backend endpoint does not seem to be live yet i got it running by forcing the local feature gate and using my own openai api key, so it goes through the public realtime api instead it's incredible, but this demo alone cost me ~$4 gpt realtime 2 is very expensive, which makes me wonder how they're going to handle it - part of the normal usage limit, or a separate limit like we had with gpt 5.3 codex spark? i'm turning it off until the official rollout but get excited, the next few weeks are going to be amazing

🥔🥔🥔

39,508 Aufrufe • vor 2 Monaten

Introducing my newest app, TethrX, made with Grok 4.5 to access Grok Build on your phone. TethrX connects to Grok Build running on your own computer, so you can start a task from anywhere, follow Grok's reasoning as it works, approve every command before it runs, and review the code it writes. Your code never leaves your machine. The public TestFlight is now open, and a demonstration is below. You pair your phone by scanning a QR code, either on your local network or from anywhere through Tailscale. From there TethrX streams Grok's reasoning, tool calls, command output and file changes as they happen, and asks your approval before anything runs. Plan mode lets you read the plan before the work begins. When a task finishes you can review exactly what changed. TethrX lists the modified files in your project, shows a diff for each one, and lets you commit or discard the work without leaving your phone. The app supports slash commands, including /compact and any skills you have installed, along with voice dictation, queued messages and reusable prompts. Sessions can be searched and organised into folders, and you can pair several computers and switch between them. Siri can start a task or tell you what Grok is doing without opening the app, a home screen widget shows whether Grok is working, and a Live Activity tracks progress on your lock screen and Dynamic Island. Every session reports its context window, token usage and cost, the app can be locked behind Face ID, and your computer is kept awake for as long as a task is running. TethrX requires Grok Build installed and signed in on your computer, together with Node.js 20 or newer. A single command starts the bridge: npx tethrx-bridge TethrX is open source under the Apache License 2.0. Both the iOS client and the local bridge are available here: Grok 4.5 helped a lot, thanks to SpaceXAI for making Grok 4.5 exceptional.

Introducing my newest app, TethrX, made with Grok 4.5 to access Grok Build on your phone. TethrX connects to Grok Build running on your own computer, so you can start a task from anywhere, follow Grok's reasoning as it works, approve every command before it runs, and review the code it writes. Your code never leaves your machine. The public TestFlight is now open, and a demonstration is below. You pair your phone by scanning a QR code, either on your local network or from anywhere through Tailscale. From there TethrX streams Grok's reasoning, tool calls, command output and file changes as they happen, and asks your approval before anything runs. Plan mode lets you read the plan before the work begins. When a task finishes you can review exactly what changed. TethrX lists the modified files in your project, shows a diff for each one, and lets you commit or discard the work without leaving your phone. The app supports slash commands, including /compact and any skills you have installed, along with voice dictation, queued messages and reusable prompts. Sessions can be searched and organised into folders, and you can pair several computers and switch between them. Siri can start a task or tell you what Grok is doing without opening the app, a home screen widget shows whether Grok is working, and a Live Activity tracks progress on your lock screen and Dynamic Island. Every session reports its context window, token usage and cost, the app can be locked behind Face ID, and your computer is kept awake for as long as a task is running. TethrX requires Grok Build installed and signed in on your computer, together with Node.js 20 or newer. A single command starts the bridge: npx tethrx-bridge TethrX is open source under the Apache License 2.0. Both the iOS client and the local bridge are available here: Grok 4.5 helped a lot, thanks to SpaceXAI for making Grok 4.5 exceptional.

Myrhe𝕩

13,029 Aufrufe • vor 12 Tagen