Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Chinese researchers did it again! OpenBMB just open-sourced MiniCPM5-2B, a dense 2B-parameter model built for reasoning, coding, and tool use on resource-constrained hardware. Artificial Analysis ranked it highest among models under 4B in its Agentic Index comparison. It scored 20, while Granite 4.2 8B scored 9. The model is... particularly strong at coding and tool calling, so I tested both capabilities locally. I pulled it onto my machine, connected it to a constrained CI repair agent, and gave it one issue: > A customer reports that retrying checkout with the same idempotency key returns a larger total. The first request returns $109, while the retry returns $118. Find the root cause, fix it without changing the public API contract, and verify the complete test suite. The Python checkout service had 18 tests. Sixteen passed, while two failed on the retry path. The agent could list files, search code, read selected ranges, run approved tests, apply a patch, and inspect its diff. It reproduced the failure, then followed the checkout and idempotency paths through the repository. The model found that shipping was added to mutable order state before the cached result was checked. On retry, the same order already contained shipping, so the calculation added it again. It generated a narrow patch that moved the idempotency check ahead of the mutation without changing the public API. The agent ran the targeted tests and the complete suite. All 18 tests passed. The model was never told which file contained the issue or what change to make. Each test result, search result, and code inspection determined its next action. The video below shows the full trajectory, including the investigation, tool calls, generated patch, diff, and final verification. Everything ran 100% locally on my machine throughout the run. MiniCPM5-2B supports llama.cpp, Ollama, vLLM, SGLang, iOS, Android, and HarmonyOS for local deployment. The model weights, training recipes, reasoning datasets, and UltraX data-refinement system are open-source. GitHub Repo: A 2B model can now inspect a repository, reason across multiple files, modify code, and verify its patch while remaining small enough to target local hardware.show more

Akshay 🚀

286,636 subscribers

313,956 просмотров • 6 дней назад •via X (Twitter)

Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 24

Фото профиля Deepanshu Pathak

Deepanshu Pathak6 дней назад

A 2B model doing this locally is honestly insane. Feels like we're getting close to the point where you won't need a giant model or a cloud API for a lot of serious AI work.

Фото профиля EDDY VU

EDDY VU6 дней назад

Seeing this level of tool use packed into a dense 2B model makes local agent workflows actually practical.

Фото профиля Hussain Hashim | Building SundayBack

Hussain Hashim | Building SundayBack6 дней назад

@akshay_pachaar impressive stuff! miniCPM5-2B sounds like a game-changer for those of us with limited resources.

Фото профиля Ibesh

Ibesh5 дней назад

openbmb team is on a roll. chinese labs open sourcing this fast is wild — keeps the whole ecosystem moving even if you're not tracking every release

Фото профиля Holly

Holly5 дней назад

Small models are becoming surprisingly capable.

Фото профиля Zyro AI

Zyro AI5 дней назад

2B parameters, yet it can debug, patch, and verify code locally. That’s seriously impressive.

Фото профиля Anissa

Anissa5 дней назад

This is seriously impressive for a model this small local coding agents are getting wild

Фото профиля Mehwish kiran

Mehwish kiran5 дней назад

2B parameters yet strong agentic performance that’s seriously impressive.

Фото профиля Synthia

Synthia5 дней назад

This is fabulous for agent developers. Being able to trace failures and replay the exact context makes debugging so much easier.

Фото профиля Zorvia

Zorvia5 дней назад

MiniCPM5-2B looks seriously capable for its size.

Фото профиля Johnn

Johnn5 дней назад

It can do multitask for you

Фото профиля Javeriya Ahsan

Javeriya Ahsan5 дней назад

the model size is impressive. the agent loop is more impressive

Фото профиля Laraib Fatima‎

Laraib Fatima‎5 дней назад

2B parameters with real agentic coding.

Фото профиля Zarnab Ai

Zarnab Ai5 дней назад

2B models are getting seriously capable for agentic tasks.

Фото профиля Bhavesh Gujrati

Bhavesh Gujrati5 дней назад

A 2B model debugging idempotency bugs locally is genuinely impressive.

Фото профиля Secta

Secta6 дней назад

the useful primitive here is the constrained tool loop around the model scoped actions and full-suite verification make its patch auditable

Фото профиля Saif Ai

Saif Ai5 дней назад

Absolutely beautiful! ✨😍 Such a stunning post with amazing vibes. Love the elegance and positive energy! ❤️🔥**

Фото профиля Sadia

Sadia5 дней назад

A 2B model fixing code locally and passing the full test suite is seriously impressive for its size

Фото профиля Yoyo

Yoyo6 дней назад

wow

Фото профиля sunil kumar rana

sunil kumar rana5 дней назад

That’s seriously impressive for a 2B model. Small model, big reasoning. 🔥

Фото профиля Jim Cen

Jim Cen5 дней назад

I have found tool calling is most useful when the agent must inspect the live system state before choosing a repair. The test here points to a missing invariant around retry semantics, not just a model capability gap. A trace that records the observed contract, chosen action, and post-fix verification would make these failures much easier to reproduce.

Фото профиля Saira Wang

Saira Wang6 дней назад

Curious what other real-world Agent use cases you think could run well with a sub-3B model?

Фото профиля Smiling Khan

Smiling Khan5 дней назад

This is the kind of DevTool agent builders have been missing .. The feedback loop into improved agent skills makes it even more interesting.

Фото профиля Egor

Egor6 дней назад

the 18-test verification gives the generated patch an audit trail

Похожие видео

Insane progress for small language models! MiniCPM5-2B is a dense 2B-parameter model by OpenBMB from China that's built for reasoning, coding, and tool use on resource-constrained hardware. The model specifically excels at coding and tool calling, two capabilities central to the shift from on-device LLMs to on-device agents. Instead of only answering prompts, it can use tools, generate code, carry information between steps, and complete multi-step tasks. I ran it 100% locally and connected it to a small investigation agent with one request: > Revenue dropped last week. Investigate what happened, quantify the impact, identify the likely cause, and produce an incident report with supporting evidence. The evidence was spread across orders, traffic, payments, refunds, and deployment logs. The model inspected the files, wrote its own queries, analyzed the intermediate results, and decided what to investigate next. Each tool result informed the next action, so the final report depended on the model maintaining a coherent investigation across the complete trajectory. The recording shows the actual task from beginning to end. It starts with the revenue question, follows the tool calls and supporting evidence, and ends with a quantified diagnosis and incident report. The data, tool execution, and model inference all remained on my machine. These capabilities were optimized through Agentic Pre-training, SFT, and large-scale RL. They do not come entirely from an application-level agent framework. MiniCPM5-2B supports SGLang, vLLM, llama(.)cpp, Ollama, iOS, Android, and HarmonyOS. OpenBMB has also released the model weights and parts of the training recipes and data resources behind it. Download MiniCPM5-2B: A 2B model can now maintain enough state to coordinate tools and complete a useful investigation on local hardware.

Insane progress for small language models! MiniCPM5-2B is a dense 2B-parameter model by OpenBMB from China that's built for reasoning, coding, and tool use on resource-constrained hardware. The model specifically excels at coding and tool calling, two capabilities central to the shift from on-device LLMs to on-device agents. Instead of only answering prompts, it can use tools, generate code, carry information between steps, and complete multi-step tasks. I ran it 100% locally and connected it to a small investigation agent with one request: > Revenue dropped last week. Investigate what happened, quantify the impact, identify the likely cause, and produce an incident report with supporting evidence. The evidence was spread across orders, traffic, payments, refunds, and deployment logs. The model inspected the files, wrote its own queries, analyzed the intermediate results, and decided what to investigate next. Each tool result informed the next action, so the final report depended on the model maintaining a coherent investigation across the complete trajectory. The recording shows the actual task from beginning to end. It starts with the revenue question, follows the tool calls and supporting evidence, and ends with a quantified diagnosis and incident report. The data, tool execution, and model inference all remained on my machine. These capabilities were optimized through Agentic Pre-training, SFT, and large-scale RL. They do not come entirely from an application-level agent framework. MiniCPM5-2B supports SGLang, vLLM, llama(.)cpp, Ollama, iOS, Android, and HarmonyOS. OpenBMB has also released the model weights and parts of the training recipes and data resources behind it. Download MiniCPM5-2B: A 2B model can now maintain enough state to coordinate tools and complete a useful investigation on local hardware.

Avi Chawla

13,954 просмотров • 5 дней назад

I made Claude compete against itself. The smartest model does not automatically make the best agent. To prove it, I took the same Opus 4.6 model, initial prompt, and empty repo and but it inside two different coding harnesses: Claude Code vs. Factory Droid. The task: clone Excalidraw from scratch, inspect the original in a browser, implement its key interactions, and verify the result. Factory Droid: 8 minutes, 20 tool calls, $1.60 Claude Code: 19 minutes, 40 tool calls, $1.87 The only difference was the harness. Get Free Factory credits here:

I made Claude compete against itself. The smartest model does not automatically make the best agent. To prove it, I took the same Opus 4.6 model, initial prompt, and empty repo and but it inside two different coding harnesses: Claude Code vs. Factory Droid. The task: clone Excalidraw from scratch, inspect the original in a browser, implement its key interactions, and verify the result. Factory Droid: 8 minutes, 20 tool calls, $1.60 Claude Code: 19 minutes, 40 tool calls, $1.87 The only difference was the harness. Get Free Factory credits here:

Sarah Chieng

89,687 просмотров • 24 дней назад

watch this anon. i gave NVIDIA's biggest model ever a single task. 100 minutes and 440,000 tokens later, it had rendered nothing. not one important thing on the screen. this is Nemotron 3 Ultra. 550 billion parameters, a hybrid Mamba Transformer MoE, the largest model NVIDIA has ever shipped, and they built it specifically for long-running agentic coding. so i handed it exactly that: build a 3D scene from a spec, multiple files, iterate until the tests pass. the same task a frontier model one shotted in minutes. i genuinely wanted to be impressed. it ran for an hour and forty. burned through 440,000 tokens. wrote every file, passed its own tests, and proudly printed "task complete."the browser was blank. the 3D scene never rendered. not once. and the long horizon agentic behavior was genuinely good. it stayed on task the whole hour and forty, wrote real multi-file code, drove its own tools without derailing. it just couldn't turn any of that into something that actually runs. here's the part that gets me. it's a text model, it cannot see its own output. so it sat there looping on a broken vision tool, trying to "look" at the page, hitting error after error, never once reasoning its way out. it declared victory on an empty screen because it had no way to know the screen was empty. to be fair, i genuinely don't know what quant the NIM was serving, so maybe some of that's on the serving, not the model. but the biggest model NVIDIA has ever made, on the exact task it was designed for, couldn't tell it had built nothing in 100 minutes. same task on a local model, below thread👇.

watch this anon. i gave NVIDIA's biggest model ever a single task. 100 minutes and 440,000 tokens later, it had rendered nothing. not one important thing on the screen. this is Nemotron 3 Ultra. 550 billion parameters, a hybrid Mamba Transformer MoE, the largest model NVIDIA has ever shipped, and they built it specifically for long-running agentic coding. so i handed it exactly that: build a 3D scene from a spec, multiple files, iterate until the tests pass. the same task a frontier model one shotted in minutes. i genuinely wanted to be impressed. it ran for an hour and forty. burned through 440,000 tokens. wrote every file, passed its own tests, and proudly printed "task complete."the browser was blank. the 3D scene never rendered. not once. and the long horizon agentic behavior was genuinely good. it stayed on task the whole hour and forty, wrote real multi-file code, drove its own tools without derailing. it just couldn't turn any of that into something that actually runs. here's the part that gets me. it's a text model, it cannot see its own output. so it sat there looping on a broken vision tool, trying to "look" at the page, hitting error after error, never once reasoning its way out. it declared victory on an empty screen because it had no way to know the screen was empty. to be fair, i genuinely don't know what quant the NIM was serving, so maybe some of that's on the serving, not the model. but the biggest model NVIDIA has ever made, on the exact task it was designed for, couldn't tell it had built nothing in 100 minutes. same task on a local model, below thread👇.

Sudo su

32,589 просмотров • 2 месяцев назад

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 просмотров • 2 месяцев назад

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.

NO1ennn

68,679 просмотров • 1 месяц назад

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.

68,984 просмотров • 2 месяцев назад

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

forloop

226,271 просмотров • 6 месяцев назад

Karpathy said something you'll regret ignoring: "We have to keep the AI on the leash. I'm still the bottleneck. I have to make sure this thing isn't introducing bugs and that there's no security issues." He said it at YC talk last year, when the worry was reliability. The models hallucinated and made mistakes no human would, so the leash implied keeping yourself in the loop and checking the output before trusting it. The models are far better now, and the line still holds, for a reason he was not focused on back then. Even a model that writes flawless code today still has no idea who is allowed to run it. Correctness and authorization are different problems, and only correctness improves as the model improves. A perfect agent still hands a tool where anyone can do anything, because permission was never part of the task. I actually tested this in practice with Claude Code. I asked it to build a small internal tool with a button that issues account credits. It worked first try, and running it locally, the credit applied the instant I clicked. Nothing decided who was allowed to click it. The agent wrote the right logic and displayed a success notification. It never checked whether the caller had the right, whether it should pause for a human, or whether anything was logged. And this is not a bug a smarter model can outgrow because the leash was never in the code. Identity, permissions, and audit live in the system that runs the app, not in what the agent generates. To solve this, I took the exact same bundle and hosted it on Retool. The credit write that fired silently on my laptop now stopped at an approval gate, resolved to a real identity through SSO, and landed in an audit log. I wrote none of it. The app inherited the entire boundary the moment it was deployed, and the video shows the before and after. You can try it yourself here: I also wrote a detailed breakdown of the whole thing in my recent article, and I worked with the team to put this together. It walks through the build, the exact moment the credit write went through on my laptop with nobody checking, and then what changed when the same app ran on Retool. It also covers why this is a property of the runtime and not something a better model fixes, which is why devs typically miss this. The article is quoted below.

Karpathy said something you'll regret ignoring: "We have to keep the AI on the leash. I'm still the bottleneck. I have to make sure this thing isn't introducing bugs and that there's no security issues." He said it at YC talk last year, when the worry was reliability. The models hallucinated and made mistakes no human would, so the leash implied keeping yourself in the loop and checking the output before trusting it. The models are far better now, and the line still holds, for a reason he was not focused on back then. Even a model that writes flawless code today still has no idea who is allowed to run it. Correctness and authorization are different problems, and only correctness improves as the model improves. A perfect agent still hands a tool where anyone can do anything, because permission was never part of the task. I actually tested this in practice with Claude Code. I asked it to build a small internal tool with a button that issues account credits. It worked first try, and running it locally, the credit applied the instant I clicked. Nothing decided who was allowed to click it. The agent wrote the right logic and displayed a success notification. It never checked whether the caller had the right, whether it should pause for a human, or whether anything was logged. And this is not a bug a smarter model can outgrow because the leash was never in the code. Identity, permissions, and audit live in the system that runs the app, not in what the agent generates. To solve this, I took the exact same bundle and hosted it on Retool. The credit write that fired silently on my laptop now stopped at an approval gate, resolved to a real identity through SSO, and landed in an audit log. I wrote none of it. The app inherited the entire boundary the moment it was deployed, and the video shows the before and after. You can try it yourself here: I also wrote a detailed breakdown of the whole thing in my recent article, and I worked with the team to put this together. It walks through the build, the exact moment the credit write went through on my laptop with nobody checking, and then what changed when the same app ran on Retool. It also covers why this is a property of the runtime and not something a better model fixes, which is why devs typically miss this. The article is quoted below.

Akshay 🚀

42,911 просмотров • 2 месяцев назад

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

Sudo su

39,719 просмотров • 3 месяцев назад

Sam Altman made the case for open-source harnesses in July. a month later, someone shipped it, and it's more efficient than most managed harnesses. here is the problem it was aimed at: a large share of your agent's token bill is the model rereading things it already read. that isn't the model's doing. the runtime around it decides what goes into every prompt and how often the model gets called. for example, an agent queries a CRM at step four and gets back 400 rows. those rows get piled up in the conversation history. by step nineteen, the model has to read those rows fifteen times unnecessarily, and every token read is billed at input rates. it happened because your harness assembled that prompt on every turn and kept the rows in it. that gives you two levers: how much context the harness carries forward, and how often it calls the model. there are four practical ways to keep the prompt from growing unnecessarily: → load tool schemas on demand. a server with 100 tools doesn't need to put all 100 into every prompt when the agent only calls two. → offload large results to disk. turn a large response into a short preview and a file path instead of replaying the entire result on every turn. → delegate to subagents. let a subagent spend thirty tool calls in its own context and return one summary to the root agent. → run toolchains in code. one script calls three tools, joins the results, and returns a table instead of three turns each dragging a full response. but reducing context is only half the job. you also need to control how often the model gets called. a good harness should avoid unnecessary planning, verification, and reflection when the work can be completed in fewer steps. TrueFoundry's open-source agent harness, TrueForge, is built around both of those controls. it sits between the model and the tools, deciding what goes into every prompt and when another model call is actually needed. it also breaks token usage down across the harness, skills, instructions, tools, and messages. DevRev's Enterprise-Bench is where this gets tested, on multi-step tasks of the kind where an agent pulls records from one system and reconciles them against another. TrueFoundry ran TrueForge there against Claude Managed Agents, both on the same model, and both finished the same number of tasks. the tie is the part that matters, because it means the gap underneath is not a quality tradeoff. TrueForge reached that score on close to a third of the tokens, with roughly 40% fewer trips back to the model. for the same result, that comes out around 2.7x cheaper than Claude Managed Agents. swapping in an open model made it sharper still. TrueForge with GLM-5.2 scored a little higher than either setup above, and the entire benchmark run cost about $3 at list prices. being open source matters beyond the license here. the model underneath can be swapped without rewriting the agent, and the whole thing can run inside your own environment when the data cannot leave it. all of this comes down to the runtime around the model, the context it carries, the tools it exposes, and how many times it goes back to the model. that is what a production harness actually owns. the full task list, the per-run numbers, and the MIT-licensed code are on GitHub: (don't forget to star 🌟) you can read more about the same in the article quoted below. thanks to the TrueForge team for working with me on this one.

Sam Altman made the case for open-source harnesses in July. a month later, someone shipped it, and it's more efficient than most managed harnesses. here is the problem it was aimed at: a large share of your agent's token bill is the model rereading things it already read. that isn't the model's doing. the runtime around it decides what goes into every prompt and how often the model gets called. for example, an agent queries a CRM at step four and gets back 400 rows. those rows get piled up in the conversation history. by step nineteen, the model has to read those rows fifteen times unnecessarily, and every token read is billed at input rates. it happened because your harness assembled that prompt on every turn and kept the rows in it. that gives you two levers: how much context the harness carries forward, and how often it calls the model. there are four practical ways to keep the prompt from growing unnecessarily: → load tool schemas on demand. a server with 100 tools doesn't need to put all 100 into every prompt when the agent only calls two. → offload large results to disk. turn a large response into a short preview and a file path instead of replaying the entire result on every turn. → delegate to subagents. let a subagent spend thirty tool calls in its own context and return one summary to the root agent. → run toolchains in code. one script calls three tools, joins the results, and returns a table instead of three turns each dragging a full response. but reducing context is only half the job. you also need to control how often the model gets called. a good harness should avoid unnecessary planning, verification, and reflection when the work can be completed in fewer steps. TrueFoundry's open-source agent harness, TrueForge, is built around both of those controls. it sits between the model and the tools, deciding what goes into every prompt and when another model call is actually needed. it also breaks token usage down across the harness, skills, instructions, tools, and messages. DevRev's Enterprise-Bench is where this gets tested, on multi-step tasks of the kind where an agent pulls records from one system and reconciles them against another. TrueFoundry ran TrueForge there against Claude Managed Agents, both on the same model, and both finished the same number of tasks. the tie is the part that matters, because it means the gap underneath is not a quality tradeoff. TrueForge reached that score on close to a third of the tokens, with roughly 40% fewer trips back to the model. for the same result, that comes out around 2.7x cheaper than Claude Managed Agents. swapping in an open model made it sharper still. TrueForge with GLM-5.2 scored a little higher than either setup above, and the entire benchmark run cost about $3 at list prices. being open source matters beyond the license here. the model underneath can be swapped without rewriting the agent, and the whole thing can run inside your own environment when the data cannot leave it. all of this comes down to the runtime around the model, the context it carries, the tools it exposes, and how many times it goes back to the model. that is what a production harness actually owns. the full task list, the per-run numbers, and the MIT-licensed code are on GitHub: (don't forget to star 🌟) you can read more about the same in the article quoted below. thanks to the TrueForge team for working with me on this one.

Akshay 🚀

76,998 просмотров • 29 дней назад

i been running Qwen3.5-35B-A3B UD-Q4_K_XL through Claude Code since llama.cpp merged the Anthropic endpoint. configured it in minutes. everything was great. projects grew from single scripts to multifile systems with 8 modules and 3,000+ lines. then the chains started breaking. 3 to 5 minutes of pure autonomy and suddenly it stops. tool call fails. reprompt. it recovers. 2 minutes later it stops again. the model is fine. the harness is the bottleneck. saw a comment suggesting OpenCode. installed it. pointed it at the same localhost endpoint running the same model on the same GPU. the game is different. instead of stopping on a bad tool call it just keeps going. on wrong read it adjusts. if file not found it retries. the flow is unbroken. i watched it plan a refactor across 8 files, read every module, and start building without a single pause. in Claude Code that same task would have stopped 4 times. the tradeoff is sometimes it loops. same tool call repeated because the model loses track of what it already read. but here is the thing. i choose loops over pauses. a loop you can interrupt and redirect. a broken chain stops the flow and you have to reprompt to get it moving again. someone is solving this at the core level and i have a feeling it is the open source community. the fact that i can run this level of autonomous coding intelligence on a single consumer GPU with 24gb VRAM at 112 tokens per second. respect to the chinese labs. respect to the open source builders making this possible.

i been running Qwen3.5-35B-A3B UD-Q4_K_XL through Claude Code since llama.cpp merged the Anthropic endpoint. configured it in minutes. everything was great. projects grew from single scripts to multifile systems with 8 modules and 3,000+ lines. then the chains started breaking. 3 to 5 minutes of pure autonomy and suddenly it stops. tool call fails. reprompt. it recovers. 2 minutes later it stops again. the model is fine. the harness is the bottleneck. saw a comment suggesting OpenCode. installed it. pointed it at the same localhost endpoint running the same model on the same GPU. the game is different. instead of stopping on a bad tool call it just keeps going. on wrong read it adjusts. if file not found it retries. the flow is unbroken. i watched it plan a refactor across 8 files, read every module, and start building without a single pause. in Claude Code that same task would have stopped 4 times. the tradeoff is sometimes it loops. same tool call repeated because the model loses track of what it already read. but here is the thing. i choose loops over pauses. a loop you can interrupt and redirect. a broken chain stops the flow and you have to reprompt to get it moving again. someone is solving this at the core level and i have a feeling it is the open source community. the fact that i can run this level of autonomous coding intelligence on a single consumer GPU with 24gb VRAM at 112 tokens per second. respect to the chinese labs. respect to the open source builders making this possible.

Sudo su

67,104 просмотров • 6 месяцев назад

hey if you're thinking about running qwopus (the claude opus distilled qwen 3.5 27B) as a coding agent, this might save you a few hours. i tested both the base and the distilled version on the same hardware. single RTX 3090. same prompt. same context. same everything. the only variable was the model weights. base qwen 3.5 27B built octopus invaders in 13 minutes. 1,827 lines across 11 files. zero steering. one scope bug that took 2 lines to fix. game ran. qwopus couldn't finish the same task. enemies overlapping on screen. bullets not firing. controls worked but the game was broken. i had to steer it multiple times and it still didn't produce a playable result. both run at 35 tok/s. both use thinking mode. the distilled version actually has better jinja compatibility and doesn't stall midtask like base does on claude code. for conversation and reasoning it feels sharper. but for multifile autonomous coding where the model needs to coordinate 10+ files without losing track, base wins and it's not close. distillation compresses reasoning patterns but seems to lose precision on complex coordination. the model "thinks" well but can't hold the full picture across files the way base can. tested on opencode (base) and claude code (both). next up is hermes agent framework on base. same hardware. same prompt. comparing agents now, not just models. video below. first half is the distilled model's broken game. second half is what base built on the same 3090. judge for yourself.

hey if you're thinking about running qwopus (the claude opus distilled qwen 3.5 27B) as a coding agent, this might save you a few hours. i tested both the base and the distilled version on the same hardware. single RTX 3090. same prompt. same context. same everything. the only variable was the model weights. base qwen 3.5 27B built octopus invaders in 13 minutes. 1,827 lines across 11 files. zero steering. one scope bug that took 2 lines to fix. game ran. qwopus couldn't finish the same task. enemies overlapping on screen. bullets not firing. controls worked but the game was broken. i had to steer it multiple times and it still didn't produce a playable result. both run at 35 tok/s. both use thinking mode. the distilled version actually has better jinja compatibility and doesn't stall midtask like base does on claude code. for conversation and reasoning it feels sharper. but for multifile autonomous coding where the model needs to coordinate 10+ files without losing track, base wins and it's not close. distillation compresses reasoning patterns but seems to lose precision on complex coordination. the model "thinks" well but can't hold the full picture across files the way base can. tested on opencode (base) and claude code (both). next up is hermes agent framework on base. same hardware. same prompt. comparing agents now, not just models. video below. first half is the distilled model's broken game. second half is what base built on the same 3090. judge for yourself.

Sudo su

45,052 просмотров • 6 месяцев назад

small local model that falls apart in bloated agents like openclaw just runs like a wild horse in hermes agent. and that's not even my line, someone else called it that, i've just been quietly pointing people at this harness for months because it held up on everything i threw at it, 3b models all the way to one trillion params. watch this happen on my own machine. i pointed hermes agent at a local http endpoint, gemma 4 12b on my 3090 llama.cpp server, and it auto-detected the model and started working immediately. no config wrestling, no broken tool calls, no babysitting the output format, i typed in a url and it just went. the whole clip is exactly that, start to finish, no errors, no retries, butter smooth. and the tool calling, the one thing that quietly breaks most local setups, works here like it's nothing. it's not the model that's flaky, it's the harness around it. hermes agent is the first agent i've run that actually gets that right. one url, one local model on one card, and it runs like a wild horse.

small local model that falls apart in bloated agents like openclaw just runs like a wild horse in hermes agent. and that's not even my line, someone else called it that, i've just been quietly pointing people at this harness for months because it held up on everything i threw at it, 3b models all the way to one trillion params. watch this happen on my own machine. i pointed hermes agent at a local http endpoint, gemma 4 12b on my 3090 llama.cpp server, and it auto-detected the model and started working immediately. no config wrestling, no broken tool calls, no babysitting the output format, i typed in a url and it just went. the whole clip is exactly that, start to finish, no errors, no retries, butter smooth. and the tool calling, the one thing that quietly breaks most local setups, works here like it's nothing. it's not the model that's flaky, it's the harness around it. hermes agent is the first agent i've run that actually gets that right. one url, one local model on one card, and it runs like a wild horse.

Sudo su

27,339 просмотров • 3 месяцев назад

I’ve been testing Hy4 preview in WorkBuddy, and the most interesting part is not simply the model size, it’s how much practical work it can handle with a relatively focused active parameter count. Hy4 preview brings together stronger code understanding, generation, and editing; improved document and information processing; workflow automation; web and game development; cross-tool collaboration; and more reliable completion of complex, multi-step tasks. In other words, it is designed for work that requires planning, tool use, iteration, and follow-through, not just a quick answer in a chat window. Compared with its initial release, the current Hy4 preview is noticeably faster and better-performing in practical workflows. Following an upgrade released yesterday, it can complete tasks with fewer conversation rounds and lower token usage, while reasoning more quickly and making the overall user experience feel smoother from the first instruction to the final result. For my test, I gave it a demanding Three.js game-prototyping task with a 770B-parameter model and 49B active parameters. The result was more revealing than a simple first-look demo: Hy4 preview handled the core logic, edge cases, and follow-up changes while maintaining the broader context of the project. That combination of capability, speed, context, and active compute is what makes its cost-effectiveness worth examining. A fair evaluation should use the same prompt and environment configuration across models, changing only the model itself. That makes it easier to assess task completion, planning quality, tool-calling stability, reasoning speed, token efficiency, and performance over longer workflows without confusing the result with different settings. If you want to test the model yourself, access Hy4 preview through WorkBuddy and see how it performs on a real coding, document, automation, or creative task: Tencent Hy Tencent AI WorkBuddy

I’ve been testing Hy4 preview in WorkBuddy, and the most interesting part is not simply the model size, it’s how much practical work it can handle with a relatively focused active parameter count. Hy4 preview brings together stronger code understanding, generation, and editing; improved document and information processing; workflow automation; web and game development; cross-tool collaboration; and more reliable completion of complex, multi-step tasks. In other words, it is designed for work that requires planning, tool use, iteration, and follow-through, not just a quick answer in a chat window. Compared with its initial release, the current Hy4 preview is noticeably faster and better-performing in practical workflows. Following an upgrade released yesterday, it can complete tasks with fewer conversation rounds and lower token usage, while reasoning more quickly and making the overall user experience feel smoother from the first instruction to the final result. For my test, I gave it a demanding Three.js game-prototyping task with a 770B-parameter model and 49B active parameters. The result was more revealing than a simple first-look demo: Hy4 preview handled the core logic, edge cases, and follow-up changes while maintaining the broader context of the project. That combination of capability, speed, context, and active compute is what makes its cost-effectiveness worth examining. A fair evaluation should use the same prompt and environment configuration across models, changing only the model itself. That makes it easier to assess task completion, planning quality, tool-calling stability, reasoning speed, token efficiency, and performance over longer workflows without confusing the result with different settings. If you want to test the model yourself, access Hy4 preview through WorkBuddy and see how it performs on a real coding, document, automation, or creative task: Tencent Hy Tencent AI WorkBuddy

Tyler Wayne

56,152 просмотров • 7 дней назад

THIS GUY ASKED FABLE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AI RIGHT BEFORE IT GOT TAKEN DOWN the prompt: "you can you use whatever resources you like, and python, to render a short video. can you put a more personal spin on it? it should be about what it's like to be you." that was it. just python and ffmpeg and a question about its own existence. 12 minutes later, around 90,000 tokens, it produced a finished video. coherent and edited, with its own take > it wrote the code, generated the visuals, and rendered the final cut on its own > no dedicated video model in the loop, just a language model reaching for python and ffmpeg > the result is competent enough that people genuinely got emotional watching it and then fable got pulled. this video is one of the last things it made before it went dark a model asked what it's like to be itself, answered in a video, and then disappeared. this sounds so sad

THIS GUY ASKED FABLE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AI RIGHT BEFORE IT GOT TAKEN DOWN the prompt: "you can you use whatever resources you like, and python, to render a short video. can you put a more personal spin on it? it should be about what it's like to be you." that was it. just python and ffmpeg and a question about its own existence. 12 minutes later, around 90,000 tokens, it produced a finished video. coherent and edited, with its own take > it wrote the code, generated the visuals, and rendered the final cut on its own > no dedicated video model in the loop, just a language model reaching for python and ffmpeg > the result is competent enough that people genuinely got emotional watching it and then fable got pulled. this video is one of the last things it made before it went dark a model asked what it's like to be itself, answered in a video, and then disappeared. this sounds so sad

Om Patel

29,618 просмотров • 3 месяцев назад

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,540 просмотров • 3 месяцев назад

THIS CREATOR MADE HIS HERMES AGENT 10X FASTER WITHOUT CHANGING THE MODEL, JUST BY ADDING ONE FILE TO HIS OBSIDIAN VAULT 00:02 the screen shows a massive second brain with hundreds of connected notes, but without a clear map an AI agent still treats every file like it could be the answer Hermes used to open 7 different documents and spend nearly 2 minutes searching for the current brief, even though the correct file was already sitting inside the vault the fix was one index file inside each major folder, listing the important subfolders, canonical files, and the exact document the agent should open first after reorganizing the vault, the same search dropped from 2 minutes to around 10 seconds, while several tasks went from 5 or 6 opened files to just one the model never changed, the $30 agent stack never changed, only the structure around it did, because a powerful agent without a map is still just wandering through folders blindly

THIS CREATOR MADE HIS HERMES AGENT 10X FASTER WITHOUT CHANGING THE MODEL, JUST BY ADDING ONE FILE TO HIS OBSIDIAN VAULT 00:02 the screen shows a massive second brain with hundreds of connected notes, but without a clear map an AI agent still treats every file like it could be the answer Hermes used to open 7 different documents and spend nearly 2 minutes searching for the current brief, even though the correct file was already sitting inside the vault the fix was one index file inside each major folder, listing the important subfolders, canonical files, and the exact document the agent should open first after reorganizing the vault, the same search dropped from 2 minutes to around 10 seconds, while several tasks went from 5 or 6 opened files to just one the model never changed, the $30 agent stack never changed, only the structure around it did, because a powerful agent without a map is still just wandering through folders blindly

Gipp 🦅

36,473 просмотров • 2 месяцев назад

Zuckerberg says Meta's Llama race changes in the next 12-18 months: most of the code will be written by AI - not autocomplete, but agents that run tests and improve the model loop. "We're not trying to build a general developer tool. We are trying to build a coding agent and an AI research agent that basically advances Llama research specifically." "Sometime in the next 12 to 18 months, we'll reach the point where most of the code that's going towards these efforts is written by AI." "And I don't mean autocomplete." "I'm talking more like you give it a goal, it can run tests, it can improve things, it can find issues." "It writes higher quality code than the average very good person on the team already." The hidden bottleneck is not chat UX. It is closing the loop between AI research, code, tests, and self-improvement inside the lab.

Zuckerberg says Meta's Llama race changes in the next 12-18 months: most of the code will be written by AI - not autocomplete, but agents that run tests and improve the model loop. "We're not trying to build a general developer tool. We are trying to build a coding agent and an AI research agent that basically advances Llama research specifically." "Sometime in the next 12 to 18 months, we'll reach the point where most of the code that's going towards these efforts is written by AI." "And I don't mean autocomplete." "I'm talking more like you give it a goal, it can run tests, it can improve things, it can find issues." "It writes higher quality code than the average very good person on the team already." The hidden bottleneck is not chat UX. It is closing the loop between AI research, code, tests, and self-improvement inside the lab.

Karl Mehta

36,347 просмотров • 2 месяцев назад

Your coding agent can run all night. It still can't tell if what it built actually works. Today we're open-sourcing the TestSprite CLl (Apache-2.0) A tool your agent calls on its own to test your app end-to-end like a real user, fix what broke, and re-check everything it ever got right. It's the same engine 100,000+ teams already use. We proved it in public, on a public leaderboard: Most correct app on the board:89% Built by the cheapest model in the field At half the cost of the priciest one You no longer need the biggest, most expensive model to ship software you can trust. Setup is 2 commands: npm install -g @testsprite/testsprite-cli testsprite init That's the last command you'll ever type - from there, your agent runs the tests itself.

Your coding agent can run all night. It still can't tell if what it built actually works. Today we're open-sourcing the TestSprite CLl (Apache-2.0) A tool your agent calls on its own to test your app end-to-end like a real user, fix what broke, and re-check everything it ever got right. It's the same engine 100,000+ teams already use. We proved it in public, on a public leaderboard: Most correct app on the board:89% Built by the cheapest model in the field At half the cost of the priciest one You no longer need the biggest, most expensive model to ship software you can trust. Setup is 2 commands: npm install -g @testsprite/testsprite-cli testsprite init That's the last command you'll ever type - from there, your agent runs the tests itself.

TestSprite

1,042,264 просмотров • 3 месяцев назад

I just found a way to use Claude Code completely free. Claude Code is Anthropic’s terminal coding agent that usually needs a paid API key to run. But a viral GitHub project called Free Claude Code, now sitting at 37k stars, lets you skip the billing entirely. It works as a tiny proxy that sits between Claude Code and free model providers like NVIDIA NIM, OpenRouter, DeepSeek, and Gemini. Every request Claude Code would send to Anthropic gets quietly rerouted to a free model on the other side. The interface stays the same. What’s actually thinking behind it changes. Setup takes a couple of quick commands and a free API key from NVIDIA NIM or OpenRouter. Paste it into the local dashboard, pick a model, and you’re building. The catch is you’re not really using Claude anymore. But when the code ships, does the model badge matter? -- I have shared the Github Link in my free Whatsapp Community ↓

I just found a way to use Claude Code completely free. Claude Code is Anthropic’s terminal coding agent that usually needs a paid API key to run. But a viral GitHub project called Free Claude Code, now sitting at 37k stars, lets you skip the billing entirely. It works as a tiny proxy that sits between Claude Code and free model providers like NVIDIA NIM, OpenRouter, DeepSeek, and Gemini. Every request Claude Code would send to Anthropic gets quietly rerouted to a free model on the other side. The interface stays the same. What’s actually thinking behind it changes. Setup takes a couple of quick commands and a free API key from NVIDIA NIM or OpenRouter. Paste it into the local dashboard, pick a model, and you’re building. The catch is you’re not really using Claude anymore. But when the code ships, does the model badge matter? -- I have shared the Github Link in my free Whatsapp Community ↓

Vaibhav Sisinty

37,255 просмотров • 2 месяцев назад