Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I built a macOS app for benchmarking local LLMs. 6 test suites. Multiple providers. One workspace. Open source. There are hundreds of local models now. New ones every week. How do you actually pick one? Leaderboards test for general ability. But if you're building an agent that chains tool...

stevibe's profile picture

stevibe

27,033 subscribers

50,584 Aufrufe • vor 6 Monaten •via X (Twitter)

KunstBildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Introducing HermesAgent-20, a new Bench Pack for BenchLocal. 20 scenarios extracted straight from the Hermes Agent source code, run against a REAL Hermes instance. The actual workload you'd put your model through. Why I built BenchLocal in the first place: most benchmarks are too abstract. We use local LLMs for practical work, and finding the right model for YOUR task efficiently is the single most important thing, especially when you're constrained to what fits on your machine. BenchLocal is a framework: providers, models, side-by-side comparison, all in one UI. Bench Packs are the unit of testing: ToolCall-15 and BugFind-15 shipped first, and when I launched the BenchLocal 0.1.0, added StructOutput, ReasonMath, InstructFollow, DataExtract. Now, HermesAgent-20 is the newest. Bench Packs install like VS Code extensions. The SDK is open, write your own, share it, grow the ecosystem. Here's the goal: a community-built, practical evaluation layer for the local LLM space. Early numbers on HermesAgent-20: > GLM 5.1 — 85 > Gemma4 31B — 83 > Qwen3.5 27B — 79 > MiniMax M2.7 — 76 Upgrade to the latest BenchLocal to install HermesAgent-20 (SDK update required).
0:20

Introducing HermesAgent-20, a new Bench Pack for BenchLocal. 20 scenarios extracted straight from the Hermes Agent source code, run against a REAL Hermes instance. The actual workload you'd put your model through. Why I built BenchLocal in the first place: most benchmarks are too abstract. We use local LLMs for practical work, and finding the right model for YOUR task efficiently is the single most important thing, especially when you're constrained to what fits on your machine. BenchLocal is a framework: providers, models, side-by-side comparison, all in one UI. Bench Packs are the unit of testing: ToolCall-15 and BugFind-15 shipped first, and when I launched the BenchLocal 0.1.0, added StructOutput, ReasonMath, InstructFollow, DataExtract. Now, HermesAgent-20 is the newest. Bench Packs install like VS Code extensions. The SDK is open, write your own, share it, grow the ecosystem. Here's the goal: a community-built, practical evaluation layer for the local LLM space. Early numbers on HermesAgent-20: > GLM 5.1 — 85 > Gemma4 31B — 83 > Qwen3.5 27B — 79 > MiniMax M2.7 — 76 Upgrade to the latest BenchLocal to install HermesAgent-20 (SDK update required).

stevibe

38,631 Aufrufe • vor 6 Monaten

RustGIS is now on PyPI: pip install rustgis RustGIS is a fast, free and open-source GIS in pure Rust for mapping, analyzing and sharing geospatial data. It runs natively on Windows, macOS and Linux, and in your web browser. Your data stays on your machine unless you send it to an AI model you choose, and every action is a command you can script. The new rustgis Python package brings the RustGIS engine into Python and the full RustGIS app into your Jupyter notebook, with no server to run and nothing else to install. What you can do - The engine in-process: open the same data the app opens, run any of RustGIS's commands and geoprocessing tools, style layers and render maps, all from Python. - GeoPandas in and out: turn any layer into a GeoDataFrame, or add a GeoDataFrame as a layer. - The whole app in a notebook cell: shows the ribbon, panes and map right below your code. - Two-way sync: what Python adds or styles appears in the app, and what you pan, edit or add in the app comes back to Python. - Projects that travel: save a .rgis project from Python and open it as it is in the desktop app or the web app. - Runs where you work: JupyterLab, Jupyter Notebook, VS Code and Google Colab, with prebuilt wheels for Windows, macOS and Linux. Get started in three lines: import rustgis m = m Try it out - Open the getting-started notebook in Colab: - PyPI: - Python guide: - Launch the web app: - GitHub: #GIS #Rust #Python #Jupyter #OpenSource #Geospatial
0:38

RustGIS is now on PyPI: pip install rustgis RustGIS is a fast, free and open-source GIS in pure Rust for mapping, analyzing and sharing geospatial data. It runs natively on Windows, macOS and Linux, and in your web browser. Your data stays on your machine unless you send it to an AI model you choose, and every action is a command you can script. The new rustgis Python package brings the RustGIS engine into Python and the full RustGIS app into your Jupyter notebook, with no server to run and nothing else to install. What you can do - The engine in-process: open the same data the app opens, run any of RustGIS's commands and geoprocessing tools, style layers and render maps, all from Python. - GeoPandas in and out: turn any layer into a GeoDataFrame, or add a GeoDataFrame as a layer. - The whole app in a notebook cell: shows the ribbon, panes and map right below your code. - Two-way sync: what Python adds or styles appears in the app, and what you pan, edit or add in the app comes back to Python. - Projects that travel: save a .rgis project from Python and open it as it is in the desktop app or the web app. - Runs where you work: JupyterLab, Jupyter Notebook, VS Code and Google Colab, with prebuilt wheels for Windows, macOS and Linux. Get started in three lines: import rustgis m = m Try it out - Open the getting-started notebook in Colab: - PyPI: - Python guide: - Launch the web app: - GitHub: #GIS #Rust #Python #Jupyter #OpenSource #Geospatial

Qiusheng Wu

13,435 Aufrufe • vor 6 Tagen

the NSA put its own hacking tool on GitHub and most people still haven't opened it 5 security repos that show you how exposed you actually are. all free, all open source. want to see every account tied to your username across the internet? -> Sherlock want to take any program apart and read what it really does? -> Ghidra, the reverse engineering framework built by the NSA want to watch everything your phone apps send home? -> mitmproxy want to know if your API keys and passwords are already sitting in your git history? -> TruffleHog want to test your own WiFi and Bluetooth with a $10 chip? -> ESP32 Marauder ~260k stars of tools that professionals get paid to run. none of this is hidden. it's the same kit pentesters use on the job. the catch: it's only legal on things you own or have written permission to test. the best way to learn how you get hacked is to run the attack on yourself first. bookmark this. pick one. point it at your own stuff tonight.
0:30

the NSA put its own hacking tool on GitHub and most people still haven't opened it 5 security repos that show you how exposed you actually are. all free, all open source. want to see every account tied to your username across the internet? -> Sherlock want to take any program apart and read what it really does? -> Ghidra, the reverse engineering framework built by the NSA want to watch everything your phone apps send home? -> mitmproxy want to know if your API keys and passwords are already sitting in your git history? -> TruffleHog want to test your own WiFi and Bluetooth with a $10 chip? -> ESP32 Marauder ~260k stars of tools that professionals get paid to run. none of this is hidden. it's the same kit pentesters use on the job. the catch: it's only legal on things you own or have written permission to test. the best way to learn how you get hacked is to run the attack on yourself first. bookmark this. pick one. point it at your own stuff tonight.

kiosa

45,998 Aufrufe • vor 12 Tagen

Introducing Magnitude: your actually local agent 100% private and offline. No token costs, no API keys. Open source. Today's agents are local. The model isn't. Every prompt, every file, every secret gets sent straight to Anthropic and OpenAI. Magnitude is built around local models and runs the whole stack itself. The inference engine is part of the agent, so the models run inside it, right on your computer. It lives in your terminal, and setup is one command. Magnitude profiles your hardware and shows you which models fit, with the trade-offs between quality, speed, and memory. Pick one and start working. No painful config or server to babysit. Out of the box, it can use your shell, edit files, and run scripts. Add skills and it can work with Excel, PowerPoint, PDFs or Chrome. Use it for everyday work: - Analyze sensitive data - Manage private notes - Review code and logs - Search and organize files - Build docs or slides npm i -g @magnitudedev/cli GitHub:
0:35

Introducing Magnitude: your actually local agent 100% private and offline. No token costs, no API keys. Open source. Today's agents are local. The model isn't. Every prompt, every file, every secret gets sent straight to Anthropic and OpenAI. Magnitude is built around local models and runs the whole stack itself. The inference engine is part of the agent, so the models run inside it, right on your computer. It lives in your terminal, and setup is one command. Magnitude profiles your hardware and shows you which models fit, with the trade-offs between quality, speed, and memory. Pick one and start working. No painful config or server to babysit. Out of the box, it can use your shell, edit files, and run scripts. Add skills and it can work with Excel, PowerPoint, PDFs or Chrome. Use it for everyday work: - Analyze sensitive data - Manage private notes - Review code and logs - Search and organize files - Build docs or slides npm i -g @magnitudedev/cli GitHub:

Tom Greenwald

397,870 Aufrufe • vor 2 Monaten

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.
3:44

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

1,042,568 Aufrufe • vor 4 Monaten

everyone in iOS development should watch this. seriously, it might change the whole industry. i pointed claude code at a live ios device running on revyl, typed "test everything," and walked away. here's what's actually happening: ① you don't write the tests. no scripts, no selectors, no test plan. i never told it which screens to open or what to check. it read the app, decided what mattered, and tested it. the entire instruction was "test everything." ② it built its own test team. it looked at the app, clocked that it's basically four mini apps (rides, delivery, services, account), and split itself into 4 agents, one per surface. scoping coverage like that is usually a person's whole afternoon. it did it in seconds, unprompted. ③ all four ran at the same time, each on its own live device. this is where revyl comes in. every agent gets its own live ios session in the cloud, so four running apps get tested in parallel instead of taking turns on one simulator. serial testing turns coverage into a time tax. running all of it at once removes the tax. ④ it tests like a person, not like a script. each agent drives the app the way a user would, taps through the flows, and visually checks each screen against what it expected to see. nothing is pinned to a brittle element id, so renaming a button doesn't take down half your suite. that one detail is the most annoying thing about how we test today, and it just quietly goes away. ⑤ no xcuitest, no sims melting your laptop. i didn't write a single xcuitest script, and there were no simulators booting on my machine. the agents run on cloud devices, so coverage stops being capped by what your laptop can handle. the part that got me isn't that an agent tested an app. it's that i never told it how. i handed it a device and an intent, and it figured out the scoping, the parallelizing, and the driving on its own. if you still write and maintain mobile ui tests by hand, i'm not sure that lasts the year.
0:47

everyone in iOS development should watch this. seriously, it might change the whole industry. i pointed claude code at a live ios device running on revyl, typed "test everything," and walked away. here's what's actually happening: ① you don't write the tests. no scripts, no selectors, no test plan. i never told it which screens to open or what to check. it read the app, decided what mattered, and tested it. the entire instruction was "test everything." ② it built its own test team. it looked at the app, clocked that it's basically four mini apps (rides, delivery, services, account), and split itself into 4 agents, one per surface. scoping coverage like that is usually a person's whole afternoon. it did it in seconds, unprompted. ③ all four ran at the same time, each on its own live device. this is where revyl comes in. every agent gets its own live ios session in the cloud, so four running apps get tested in parallel instead of taking turns on one simulator. serial testing turns coverage into a time tax. running all of it at once removes the tax. ④ it tests like a person, not like a script. each agent drives the app the way a user would, taps through the flows, and visually checks each screen against what it expected to see. nothing is pinned to a brittle element id, so renaming a button doesn't take down half your suite. that one detail is the most annoying thing about how we test today, and it just quietly goes away. ⑤ no xcuitest, no sims melting your laptop. i didn't write a single xcuitest script, and there were no simulators booting on my machine. the agents run on cloud devices, so coverage stops being capped by what your laptop can handle. the part that got me isn't that an agent tested an app. it's that i never told it how. i handed it a device and an intent, and it figured out the scoping, the parallelizing, and the driving on its own. if you still write and maintain mobile ui tests by hand, i'm not sure that lasts the year.

Landseer Enga

23,963 Aufrufe • vor 4 Monaten

#1 skill for developers in 2026: Automate everything you can using AI. I bet my lunch your team is dealing with all of these: • Stale documentation • Outdated dependencies • Poor test coverage • Deprecated APIs Every company I work with has these same problems. You can solve all of these right now. Automatically. Using AI. Here are 3 examples. Watch the attached video: I'm using Ona Automations to tackle this. These are background agents that run in the cloud, in a fully configured dev environment with your toolchain, your dependencies, and your services. You can run an unlimited number of these agents in parallel and across all your repositories. Claude Code and Codex only run locally, so they are hard to scale, and you can't run them when your computer is closed. Ona runs in the cloud. Here are the three examples: 1. Test coverage Run a nightly automation to identify any untested code paths, generate candidate tests, verify they pass, and open draft PRs. You wake up every morning to PRs that improve your test coverage. 2. Dependency upgrades Configure a weekly automation that bumps a dependency version, runs your full test suite, and reports any regressions. If everything is clean, it opens a PR. If something breaks, it opens a report so you can decide what to do. 3. Documentation auditing Set up a weekly automation that checks recent commits against your README file and setup guides, identifies broken examples and outdated instructions, and opens a PR with fixes.
5:18

#1 skill for developers in 2026: Automate everything you can using AI. I bet my lunch your team is dealing with all of these: • Stale documentation • Outdated dependencies • Poor test coverage • Deprecated APIs Every company I work with has these same problems. You can solve all of these right now. Automatically. Using AI. Here are 3 examples. Watch the attached video: I'm using Ona Automations to tackle this. These are background agents that run in the cloud, in a fully configured dev environment with your toolchain, your dependencies, and your services. You can run an unlimited number of these agents in parallel and across all your repositories. Claude Code and Codex only run locally, so they are hard to scale, and you can't run them when your computer is closed. Ona runs in the cloud. Here are the three examples: 1. Test coverage Run a nightly automation to identify any untested code paths, generate candidate tests, verify they pass, and open draft PRs. You wake up every morning to PRs that improve your test coverage. 2. Dependency upgrades Configure a weekly automation that bumps a dependency version, runs your full test suite, and reports any regressions. If everything is clean, it opens a PR. If something breaks, it opens a report so you can decide what to do. 3. Documentation auditing Set up a weekly automation that checks recent commits against your README file and setup guides, identifies broken examples and outdated instructions, and opens a PR with fixes.

Santiago

25,804 Aufrufe • vor 7 Monaten

Right now, I have a few dozen tools to automate my life. Every single thing that I do more than once every week is now a tool: either a Claude Code skill, a scheduled workflow, or an application. • I spend the time doing this once. • I schedule it. • I forget about it (or at least, try to) CREAO is one of the platforms I've used extensively for building some of these automations. They are partnering with me on this post. They are one of the only platforms where you can go from a conversation to a scheduled agent that quickly. This is how it works: 1. You describe the problem you want to solve 2. CREAO's agent builds the logic and executes it 3. You can iterate with the agent to improve the solution 4. When you are done, you turn that solution into a mini app 5. You can schedule that app to run any time you need it Something important: These agents are deterministic. They don't use an LLM to generate answers, so they will always return the same output given the same input. This is critical: when you're automating something that runs every Monday at 9 am, you need it to return the same result every time, not a "creative" answer.
5:00

Right now, I have a few dozen tools to automate my life. Every single thing that I do more than once every week is now a tool: either a Claude Code skill, a scheduled workflow, or an application. • I spend the time doing this once. • I schedule it. • I forget about it (or at least, try to) CREAO is one of the platforms I've used extensively for building some of these automations. They are partnering with me on this post. They are one of the only platforms where you can go from a conversation to a scheduled agent that quickly. This is how it works: 1. You describe the problem you want to solve 2. CREAO's agent builds the logic and executes it 3. You can iterate with the agent to improve the solution 4. When you are done, you turn that solution into a mini app 5. You can schedule that app to run any time you need it Something important: These agents are deterministic. They don't use an LLM to generate answers, so they will always return the same output given the same input. This is critical: when you're automating something that runs every Monday at 9 am, you need it to return the same result every time, not a "creative" answer.

Santiago

13,727 Aufrufe • vor 6 Monaten

Local AI 101: open models, Hugging Face, and businesses to build (38 min masterclass) I still think cloud AI is the default for most things, and honestly it should be, the frontier models are the strongest and easiest to use. But something shifted in the last 4-5 months. You can now run genuinely good open models directly on your own laptop, or even your phone. And once you actually try it, it changes how you think about what AI is even for. LOCAL AI, CLEARLY EXPLAINED: 1. The model is the brain doing the thinking. Gemma, Llama, Mistral, and Qwen are the main families, and each is better at different things, some at reasoning, some at coding, some small enough to run on a phone. 2. Hugging Face is the warehouse where you find them. You go there to see what each model is good at, check the license, and grab the compressed versions that run on a normal computer. 3. The software is what runs the model on your machine. Start with LM Studio if you're not technical, it feels like a normal app where you search, download, and start chatting. Ollama is the one you reach for when you want to plug a model into your own apps. 4. The workflow is the actual product you build on top of it all. That's what I'm ideating around for some businesses to create. I think local AI just made a specific kind of business way easier to start. Find an industry that: 1. Sits on sensitive data they'd never paste into ChatGPT 2. Does the same review over and over 3. Runs on software from 2003 Then build a local AI tool that does that review on their own machine, so the data never leaves the building! Take home health agencies. Nurses write visit notes all day, and if a note is missing a detail, the billing gets denied or the audit flags it. Here's how I'd start: 1. Find 5 small agencies. Offer to review a batch of their notes for them. 2. Run the notes through Gemma locally (free, private, no cloud). Read every output yourself. 3. Write down the 20 issues that keep showing up: missing vitals, vague med changes, notes that don't support the billed level. 4. That list of 20 is your checklist. The checklist is the product. 5. Turn it into a local desktop app that flags those 20 things before a note gets submitted. You just went from a service anyone could offer to a product nobody else has, and you learned exactly what to build by doing the work by hand first. Same recipe works for restoration contractors (draft the damage report on-site before the tech leaves) and wealth advisors (catch the compliance landmine in a client email before it sends). Basically the framework is sensitive data, repeated review, ancient software. I think there are tons of businesses like this! Almost none of it clicked for me until I actually started using local AI. So if you take one thing from this, go run a model on your own machine once. Also a fun thing to try with your friends. Feel free to send this to a friend. The episode is live for free on The Startup Ideas Podcast (SIP) 🧃 (thanks to Google for sponsoring today's episode and supporting local AI) I feel like local AI one of those things you need to try for it to really click. Run one model on your own machine and you'll see what I mean! I go way deeper in the full 38 minute masterclass, the models, the setup, and the businesses to build. Link below. LINK TO WATCH: OR WATCH BELOW ON X What do you think of local AI?
38:45

Local AI 101: open models, Hugging Face, and businesses to build (38 min masterclass) I still think cloud AI is the default for most things, and honestly it should be, the frontier models are the strongest and easiest to use. But something shifted in the last 4-5 months. You can now run genuinely good open models directly on your own laptop, or even your phone. And once you actually try it, it changes how you think about what AI is even for. LOCAL AI, CLEARLY EXPLAINED: 1. The model is the brain doing the thinking. Gemma, Llama, Mistral, and Qwen are the main families, and each is better at different things, some at reasoning, some at coding, some small enough to run on a phone. 2. Hugging Face is the warehouse where you find them. You go there to see what each model is good at, check the license, and grab the compressed versions that run on a normal computer. 3. The software is what runs the model on your machine. Start with LM Studio if you're not technical, it feels like a normal app where you search, download, and start chatting. Ollama is the one you reach for when you want to plug a model into your own apps. 4. The workflow is the actual product you build on top of it all. That's what I'm ideating around for some businesses to create. I think local AI just made a specific kind of business way easier to start. Find an industry that: 1. Sits on sensitive data they'd never paste into ChatGPT 2. Does the same review over and over 3. Runs on software from 2003 Then build a local AI tool that does that review on their own machine, so the data never leaves the building! Take home health agencies. Nurses write visit notes all day, and if a note is missing a detail, the billing gets denied or the audit flags it. Here's how I'd start: 1. Find 5 small agencies. Offer to review a batch of their notes for them. 2. Run the notes through Gemma locally (free, private, no cloud). Read every output yourself. 3. Write down the 20 issues that keep showing up: missing vitals, vague med changes, notes that don't support the billed level. 4. That list of 20 is your checklist. The checklist is the product. 5. Turn it into a local desktop app that flags those 20 things before a note gets submitted. You just went from a service anyone could offer to a product nobody else has, and you learned exactly what to build by doing the work by hand first. Same recipe works for restoration contractors (draft the damage report on-site before the tech leaves) and wealth advisors (catch the compliance landmine in a client email before it sends). Basically the framework is sensitive data, repeated review, ancient software. I think there are tons of businesses like this! Almost none of it clicked for me until I actually started using local AI. So if you take one thing from this, go run a model on your own machine once. Also a fun thing to try with your friends. Feel free to send this to a friend. The episode is live for free on The Startup Ideas Podcast (SIP) 🧃 (thanks to Google for sponsoring today's episode and supporting local AI) I feel like local AI one of those things you need to try for it to really click. Run one model on your own machine and you'll see what I mean! I go way deeper in the full 38 minute masterclass, the models, the setup, and the businesses to build. Link below. LINK TO WATCH: OR WATCH BELOW ON X What do you think of local AI?

GREG ISENBERG

33,878 Aufrufe • vor 1 Monat

single most useful thing for my local ai setup that made life easy is my 2x DGX Spark becoming one serving box for every device i own here is how i do it: > 1. the two sparks run one vLLM server together with one endpoint, i use dgx sparks, you can use any nodes that can run an llm > 2. install tailscale to have all your nodes and machines on the same tailnet, the endpoint lives there so every device reaches it from anywhere and no port is open to the internet > 3. that one tailnet endpoint with the exposed port is your base url for everything, it speaks OpenAI chat, OpenAI Responses and Anthropic Messages, so any chat app, coding agent or phone bot you point at it talks to the same model > 4. the server also answers to the name "local", so clients can ask for "local" instead of a model name and when i swap the model on the servers nothing on the devices needs a config change. right now it's serving GLM 5.3-Flash, next week it can be something else this video below is the whole thing running end to end, orange dots are requests going in, white and green are tokens coming back it takes however many requests you throw at it, your config decides how many run at once and the rest wait their turn, when several run together each request's tok/s drops a bit while the box moves more tokens in total. mine is set to one at a time right now, so when every device fires together they queue up this setup really improved my quality of life with local ai, if you get stuck anywhere setting it up leave a comment and i'll help you
1:04

single most useful thing for my local ai setup that made life easy is my 2x DGX Spark becoming one serving box for every device i own here is how i do it: > 1. the two sparks run one vLLM server together with one endpoint, i use dgx sparks, you can use any nodes that can run an llm > 2. install tailscale to have all your nodes and machines on the same tailnet, the endpoint lives there so every device reaches it from anywhere and no port is open to the internet > 3. that one tailnet endpoint with the exposed port is your base url for everything, it speaks OpenAI chat, OpenAI Responses and Anthropic Messages, so any chat app, coding agent or phone bot you point at it talks to the same model > 4. the server also answers to the name "local", so clients can ask for "local" instead of a model name and when i swap the model on the servers nothing on the devices needs a config change. right now it's serving GLM 5.3-Flash, next week it can be something else this video below is the whole thing running end to end, orange dots are requests going in, white and green are tokens coming back it takes however many requests you throw at it, your config decides how many run at once and the rest wait their turn, when several run together each request's tok/s drops a bit while the box moves more tokens in total. mine is set to one at a time right now, so when every device fires together they queue up this setup really improved my quality of life with local ai, if you get stuck anywhere setting it up leave a comment and i'll help you

Sudo su

32,890 Aufrufe • vor 19 Tagen

Ant Group's AI agents found a trading strategy on their own, and with it the fund hasn't lost once in the past year Sharpe ratio came out at 2.5. What used to take a team of PhDs and years of work, the agents did overnight, for free But the real power of this result isn't the number itself Agents can run thousands of times more strategy variations than any human could in a lifetime And the more variations you test, the higher the chance that one of them looks profitable purely by accident Your brain can't tell "I found a pattern" from "I got lucky on the hundredth try." The feeling is identical in both cases The only way to tell them apart: test the result on data the strategy has never seen A real edge survives there. Luck falls apart I got curious what this difference looks like live, so I took two real academic quant strategies and ran both through this exact test The first, Time Series Momentum on Bitcoin, passed: +1,537%, Sharpe 1.02. It looked honest, and it stayed honest The second, Betting Against Beta, a textbook classic in every finance course, looked flawless on paper. Under this test it fell apart: -7.78% a year, while the market grew 14.86% And the second result turned out to be the more valuable one. Not because it's positive, but because it's true, and it showed that before it could take real money I simply described both ideas in plain words, the AI built the exact rules itself and ran them on real data, with no peeking at future data You can test your own idea here (free trial period after sign-up): The same test on momentum and Betting Against Beta, step by step, so you can run it on your own idea tonight, is in the article below
0:24

Ant Group's AI agents found a trading strategy on their own, and with it the fund hasn't lost once in the past year Sharpe ratio came out at 2.5. What used to take a team of PhDs and years of work, the agents did overnight, for free But the real power of this result isn't the number itself Agents can run thousands of times more strategy variations than any human could in a lifetime And the more variations you test, the higher the chance that one of them looks profitable purely by accident Your brain can't tell "I found a pattern" from "I got lucky on the hundredth try." The feeling is identical in both cases The only way to tell them apart: test the result on data the strategy has never seen A real edge survives there. Luck falls apart I got curious what this difference looks like live, so I took two real academic quant strategies and ran both through this exact test The first, Time Series Momentum on Bitcoin, passed: +1,537%, Sharpe 1.02. It looked honest, and it stayed honest The second, Betting Against Beta, a textbook classic in every finance course, looked flawless on paper. Under this test it fell apart: -7.78% a year, while the market grew 14.86% And the second result turned out to be the more valuable one. Not because it's positive, but because it's true, and it showed that before it could take real money I simply described both ideas in plain words, the AI built the exact rules itself and ran them on real data, with no peeking at future data You can test your own idea here (free trial period after sign-up): The same test on momentum and Betting Against Beta, step by step, so you can run it on your own idea tonight, is in the article below

qwinsi

16,825 Aufrufe • vor 16 Tagen

How to survive the Geophysical Event, from the worst-case scenarios to the less severe ones that involve only abrupt climate change and civilization collapse. There are suggested places for survival, budgets, how many people you are planning to survive with, what kinds of skills you need, how much food you need, what kind of food, water requirements, how to build a small community, where the closest place for survival is, etc... Are you interested in my app? I can finish it and upload it to my website, but bear in mind that today, almost anyone can create an app like this. You can even “vibe code” your own app...
1:57

How to survive the Geophysical Event, from the worst-case scenarios to the less severe ones that involve only abrupt climate change and civilization collapse. There are suggested places for survival, budgets, how many people you are planning to survive with, what kinds of skills you need, how much food you need, what kind of food, water requirements, how to build a small community, where the closest place for survival is, etc... Are you interested in my app? I can finish it and upload it to my website, but bear in mind that today, almost anyone can create an app like this. You can even “vibe code” your own app...

Open Minded Approach

20,370 Aufrufe • vor 18 Tagen

I'm now building Executor full time as a startup! The state of tool calling is a mess: - Everyone is using different agents - You have no idea what actions are going to run - Destructive actions are treated the same as normal Executor lets you set up everything once & use it with any agent. You're able to control what tools can be called, require approval on destructive actions, and invite your team to all use them. Under the hood, it's built on codemode to let you add thousands of tools with 0 context bloat. I've been using it for a month so far and it has completely changed how I interact with agents. There's so much to be built here, immediately next up on the roadmap is workspaces, skills, workflows, and generative ui. Everything is being built open source over at there's a lot more coming on an SDK to embed it into your own agents, a self hostable cloud app, and plugins There's an early beta version over at It's very early on - if you hit any bugs let me know and I'll get them fixed up, excited to share more as I build it!
0:36

I'm now building Executor full time as a startup! The state of tool calling is a mess: - Everyone is using different agents - You have no idea what actions are going to run - Destructive actions are treated the same as normal Executor lets you set up everything once & use it with any agent. You're able to control what tools can be called, require approval on destructive actions, and invite your team to all use them. Under the hood, it's built on codemode to let you add thousands of tools with 0 context bloat. I've been using it for a month so far and it has completely changed how I interact with agents. There's so much to be built here, immediately next up on the roadmap is workspaces, skills, workflows, and generative ui. Everything is being built open source over at there's a lot more coming on an SDK to embed it into your own agents, a self hostable cloud app, and plugins There's an early beta version over at It's very early on - if you hit any bugs let me know and I'll get them fixed up, excited to share more as I build it!

Rhys

220,984 Aufrufe • vor 5 Monaten

AI is moving fast. Transparency should too. So, what is PublicAI? It opens up two parts of AI that are often kept behind the curtain: **the data models are trained on and the benchmarks used to evaluate them.** One product for each. Both fully open. That means more transparency, more accountability, and a clearer view of how AI systems actually perform. 🛰️ Trajector An open source CLI that turns your own Claude Code sessions into paid data contributions. you opt in per project, it routes that project's traffic through a local proxy, masks secrets on your machine, and uploads only the redacted result. a project you don't opt in isn't just excluded, the code to record it doesn't exist. what comes out is real multi turn coding agent work. the kind that's hard to buy and impossible to fake. labs license it, the people who made it get paid. 📊 PublicAI Index 15 public leaderboards from 14 publishers, standardized onto 1 scale. no benchmark of their own. launch post figures get marked and never rank a model alone. the weighting is printed next to the table, not hidden as a trade secret. free to read, free to query, with a JSON API and an MCP server for agents. → Install Trajector: → Sign-up:
0:28

AI is moving fast. Transparency should too. So, what is PublicAI? It opens up two parts of AI that are often kept behind the curtain: **the data models are trained on and the benchmarks used to evaluate them.** One product for each. Both fully open. That means more transparency, more accountability, and a clearer view of how AI systems actually perform. 🛰️ Trajector An open source CLI that turns your own Claude Code sessions into paid data contributions. you opt in per project, it routes that project's traffic through a local proxy, masks secrets on your machine, and uploads only the redacted result. a project you don't opt in isn't just excluded, the code to record it doesn't exist. what comes out is real multi turn coding agent work. the kind that's hard to buy and impossible to fake. labs license it, the people who made it get paid. 📊 PublicAI Index 15 public leaderboards from 14 publishers, standardized onto 1 scale. no benchmark of their own. launch post figures get marked and never rank a model alone. the weighting is printed next to the table, not hidden as a trade secret. free to read, free to query, with a JSON API and an MCP server for agents. → Install Trajector: → Sign-up:

ɱҽԃι✨

26,542 Aufrufe • vor 28 Tagen

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.
2:15

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 3 Monaten

Hermes just made its in-app browser a whole lot more useful. You can now keep multiple browser tabs open inside Hermes Desktop instead of every new page replacing the one you were already using. And that matters more than it sounds. Because this is not just about “having tabs.” It means Hermes can work across multiple pages without forcing you to keep losing your place every time you open the next thing. Research one source, keep it open, open another tab, compare them side by side, and keep moving. Check a few products before buying something. Look at multiple hotel or travel options at once. Keep a YouTube tutorial open in one tab while Hermes looks through docs or another page in the next. And because this lives inside Hermes Desktop, you are not limited to one basic browser view either. You can keep multiple tabs open. You can view two pages side by side. You can stack them top and bottom. You can even run a four-panel view when you want several pages open at once. So the browser inside Hermes is starting to feel a lot more like a real workspace instead of one page you keep replacing. There is also some nice polish that comes with it. Browser tabs now label themselves based on the page, and the address bar behaves more cleanly while pages are loading. And remember, this is the same in-app browser Hermes can already read, click through, type in, scroll, and annotate. So this is not just a prettier browser. It is a more capable workspace for the browser Hermes is actually using. If Hermes is going to do more of your work on the web, this is exactly the kind of browser upgrade it needed.
0:33

Hermes just made its in-app browser a whole lot more useful. You can now keep multiple browser tabs open inside Hermes Desktop instead of every new page replacing the one you were already using. And that matters more than it sounds. Because this is not just about “having tabs.” It means Hermes can work across multiple pages without forcing you to keep losing your place every time you open the next thing. Research one source, keep it open, open another tab, compare them side by side, and keep moving. Check a few products before buying something. Look at multiple hotel or travel options at once. Keep a YouTube tutorial open in one tab while Hermes looks through docs or another page in the next. And because this lives inside Hermes Desktop, you are not limited to one basic browser view either. You can keep multiple tabs open. You can view two pages side by side. You can stack them top and bottom. You can even run a four-panel view when you want several pages open at once. So the browser inside Hermes is starting to feel a lot more like a real workspace instead of one page you keep replacing. There is also some nice polish that comes with it. Browser tabs now label themselves based on the page, and the address bar behaves more cleanly while pages are loading. And remember, this is the same in-app browser Hermes can already read, click through, type in, scroll, and annotate. So this is not just a prettier browser. It is a more capable workspace for the browser Hermes is actually using. If Hermes is going to do more of your work on the web, this is exactly the kind of browser upgrade it needed.

Hermes Release Watch

52,493 Aufrufe • vor 1 Monat

✨ I built a Cursor-style right sidebar on my site Photo AI which is a regular AI chatbot BUT it can fully control my app! It can take photos of you, or shoot videos, run photo packs, remix content you upload etc. anything you see in the interface. Like an AI photographer that does everything for you inside the web app The convo history is stored in localStorage, and the chat uses xAI Grok 4 to send messages, there I define the tools it can use, and when it gets a response JS controls the site like prompt textareas, or photo pack section, or take photo button It also knows what's on your screen, so you can say you want to mix the blue jacket from one photo and the red hair from the other A few weeks ago I told Yasser it'd be cool if Chatbase (an AI customer support pop up chat) would be able to fully control my site too, and this week I saw Farza 🇵🇰🇺🇸 building an AI desktop app that fully controls his computer too so I think that's where things are going, you don't see it on the web that much though Very fun to build and hopefully useful for people!!!
2:00

✨ I built a Cursor-style right sidebar on my site Photo AI which is a regular AI chatbot BUT it can fully control my app! It can take photos of you, or shoot videos, run photo packs, remix content you upload etc. anything you see in the interface. Like an AI photographer that does everything for you inside the web app The convo history is stored in localStorage, and the chat uses xAI Grok 4 to send messages, there I define the tools it can use, and when it gets a response JS controls the site like prompt textareas, or photo pack section, or take photo button It also knows what's on your screen, so you can say you want to mix the blue jacket from one photo and the red hair from the other A few weeks ago I told Yasser it'd be cool if Chatbase (an AI customer support pop up chat) would be able to fully control my site too, and this week I saw Farza 🇵🇰🇺🇸 building an AI desktop app that fully controls his computer too so I think that's where things are going, you don't see it on the web that much though Very fun to build and hopefully useful for people!!!

@levelsio

214,132 Aufrufe • vor 5 Monaten

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW
1:14

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

MAX

13,282 Aufrufe • vor 1 Monat

Fusion Models by robinhood:0xa92768863a55d8a0591709f7f5e594a249d36ea3, explained properly. Why a panel beats one model: Ask three models the same hard question and they disagree. The disagreement is the information, where they contradict each other is where one of them is wrong, and a judge can see it. OpenRouter shipped exactly this in June and their panels beat any single frontier model. Credit to them and their $10B sale to stripe. Why the same panel for everyone is the wrong shape: You don't have one best model. You have a best model per job. The one you trust for code is not the one you trust for writing, and neither is the one you'd pick for a five-line reply. A panel chosen per request, identical for every user, can't know that. A panel arranged around you can. The number that matters isn't price: It's cost per answer that works. Model A costs $4 per million tokens and gets your job right one time in four. Model B costs $10 and gets it right three times in four. Per answer you actually keep, A costs $16 and B costs $13. The cheap model was the expensive one. Everyone comparing price lists is measuring the wrong thing. You never rate anything: Stopping an answer halfway is a rating. Regenerating is a rating. Switching model and asking again is the loudest rating there is. Every one of those already writes a row we can learn from. The router learns which models earn your credits, per job, and tries a cheaper one now and then to check. Fusion only when it pays: Cost mode tries the cheap model first and escalates only if a judge says it failed. Performance mode fans out to your panel and merges. Most simple prompts never fuse. That's why it costs less, not more. Put it together and you have a personal model: Not trained. Assembled. Your profile from a two-minute questionnaire and everything you've imported from Claude or ChatGPT. Your memory, shared across every model so switching never starts from zero. Your skills, workflows you build once and run on any model. Your scorecard, which models earn your credits per job. One per person. Nobody else has yours. Every model is someone else's; the arrangement is you, and it leaves with you. People aren't loyal to models. They're loyal to results. A moat can't be a commodity, but it can be our own creation.
0:46

Fusion Models by robinhood:0xa92768863a55d8a0591709f7f5e594a249d36ea3, explained properly. Why a panel beats one model: Ask three models the same hard question and they disagree. The disagreement is the information, where they contradict each other is where one of them is wrong, and a judge can see it. OpenRouter shipped exactly this in June and their panels beat any single frontier model. Credit to them and their $10B sale to stripe. Why the same panel for everyone is the wrong shape: You don't have one best model. You have a best model per job. The one you trust for code is not the one you trust for writing, and neither is the one you'd pick for a five-line reply. A panel chosen per request, identical for every user, can't know that. A panel arranged around you can. The number that matters isn't price: It's cost per answer that works. Model A costs $4 per million tokens and gets your job right one time in four. Model B costs $10 and gets it right three times in four. Per answer you actually keep, A costs $16 and B costs $13. The cheap model was the expensive one. Everyone comparing price lists is measuring the wrong thing. You never rate anything: Stopping an answer halfway is a rating. Regenerating is a rating. Switching model and asking again is the loudest rating there is. Every one of those already writes a row we can learn from. The router learns which models earn your credits, per job, and tries a cheaper one now and then to check. Fusion only when it pays: Cost mode tries the cheap model first and escalates only if a judge says it failed. Performance mode fans out to your panel and merges. Most simple prompts never fuse. That's why it costs less, not more. Put it together and you have a personal model: Not trained. Assembled. Your profile from a two-minute questionnaire and everything you've imported from Claude or ChatGPT. Your memory, shared across every model so switching never starts from zero. Your skills, workflows you build once and run on any model. Your scorecard, which models earn your credits per job. One per person. Nobody else has yours. Every model is someone else's; the arrangement is you, and it leaves with you. People aren't loyal to models. They're loyal to results. A moat can't be a commodity, but it can be our own creation.

askr

13,900 Aufrufe • vor 29 Tagen