Video wird geladen...

Video konnte nicht geladen werden

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

Say “oh my” to Pi. Full omp TUI, native GUI on top with inline diffs and rich tool calls. Switch mid-chat, no context lost.

super.engineering

5,445 subscribers

62,867 Aufrufe • vor 2 Monaten •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

OpenCode just got a major upgrade. Native GUI chat, switch to terminal anytime, inline diffs, git panel, message queueing, steering, rich tool calls, switch providers mid-conversation, and more.

OpenCode just got a major upgrade. Native GUI chat, switch to terminal anytime, inline diffs, git panel, message queueing, steering, rich tool calls, switch providers mid-conversation, and more.

super.engineering

232,009 Aufrufe • vor 5 Monaten

Tool UI is a React framework for conversation-native UIs. Tools return JSON, and Tool UI renders it as inline, narrated, referenceable surfaces inside messages, optimized for chat width and scroll. It’s schema-first: every surface is driven by a serializable schema with stable IDs, so results stay consistent and reusable. It’s assistant-anchored and stack-agnostic, working with any LLM/provider and orchestration layer. If you’re building agents, it’s a clean bridge from tool outputs to real product UX.

Tool UI is a React framework for conversation-native UIs. Tools return JSON, and Tool UI renders it as inline, narrated, referenceable surfaces inside messages, optimized for chat width and scroll. It’s schema-first: every surface is driven by a serializable schema with stable IDs, so results stay consistent and reusable. It’s assistant-anchored and stack-agnostic, working with any LLM/provider and orchestration layer. If you’re building agents, it’s a clean bridge from tool outputs to real product UX.

Tw93

66,900 Aufrufe • vor 8 Monaten

NEW: “People say to me sometimes, ‘Oh, you’ve found your voice’. — I never lost my voice…Maybe you weren’t listening to it, but it wasn’t lost.” ~ @kamalaharris on a new episode of At Our Table with Jaime Harrison

NEW: “People say to me sometimes, ‘Oh, you’ve found your voice’. — I never lost my voice…Maybe you weren’t listening to it, but it wasn’t lost.” ~ @kamalaharris on a new episode of At Our Table with Jaime Harrison

harris4potus

27,259 Aufrufe • vor 9 Monaten

Exciting news! Bing is now integrated into SwiftKey on Android and iOS. Search, chat and rewrite messages using Bing from any app. As someone who communicates daily in my non-native language, the tone feature is a great tool for adapting my words to the style of the conversation.

Exciting news! Bing is now integrated into SwiftKey on Android and iOS. Search, chat and rewrite messages using Bing from any app. As someone who communicates daily in my non-native language, the tone feature is a great tool for adapting my words to the style of the conversation.

Jordi Ribas

68,731 Aufrufe • vor 3 Jahren

This is my MacBook Air M2 (16GB) with Hermes Agent powered by MiniCPM5-2B. 96k context, and a very respectable output of 20-24 tok/s. This is totally usable, and MiniCPM5 can do all the tool calls to manage the basics with Hermes in a personal agent context. I wouldn't use it to build the next Salesforce, but for the home enthusiast this is a powerful and fast local model that can really punch above its weight, and runs on almost anything. Look at it go.. Amazing!

This is my MacBook Air M2 (16GB) with Hermes Agent powered by MiniCPM5-2B. 96k context, and a very respectable output of 20-24 tok/s. This is totally usable, and MiniCPM5 can do all the tool calls to manage the basics with Hermes in a personal agent context. I wouldn't use it to build the next Salesforce, but for the home enthusiast this is a powerful and fast local model that can really punch above its weight, and runs on almost anything. Look at it go.. Amazing!

GooGZ AI

23,255 Aufrufe • vor 17 Tagen

Code mode lost by 39 seconds. It is supposed to be the faster way for agents to call MCP tools. Fewer round trips, smaller context. We raced it against classic tool calling on the same Linear task and it lost. The reason isn't a code mode problem. Most MCP servers ship input schemas and nothing else, so the agent knows exactly what to send and has to guess what comes back. It guessed wrong three times, and every wrong guess is a full extra turn. So we built a shape cache that remembers what each tool returns and carries it across sessions. Rematch: 27% faster than classic, 47% cheaper, 42% less context. Mark Hetherington on making [code]smith fast:

Code mode lost by 39 seconds. It is supposed to be the faster way for agents to call MCP tools. Fewer round trips, smaller context. We raced it against classic tool calling on the same Linear task and it lost. The reason isn't a code mode problem. Most MCP servers ship input schemas and nothing else, so the agent knows exactly what to send and has to guess what comes back. It guessed wrong three times, and every wrong guess is a full extra turn. So we built a shape cache that remembers what each tool returns and carries it across sessions. Rematch: 27% faster than classic, 47% cheaper, 42% less context. Mark Hetherington on making [code]smith fast:

Blacksmith

13,748 Aufrufe • vor 1 Monat

Oscar De La Hoya: “He(Ryan Garcia) is hungry to get on top!” Crowd: “ayooooo” Ryan Garcia: “You forgot to pause & say NO DIDDY” Oscar De La Hoya: “Oh dang, sorry. my bad. You know he’s just ready to get on top” 😭😭💀💀 #Boxing #BarriosGarcia 🤣🤣🥊🥊🥊

Oscar De La Hoya: “He(Ryan Garcia) is hungry to get on top!” Crowd: “ayooooo” Ryan Garcia: “You forgot to pause & say NO DIDDY” Oscar De La Hoya: “Oh dang, sorry. my bad. You know he’s just ready to get on top” 😭😭💀💀 #Boxing #BarriosGarcia 🤣🤣🥊🥊🥊

Danny

136,066 Aufrufe • vor 8 Monaten

I built a tool that brought in 80+ leads and let me raise my prices 123% this year. I also stopped writing proposals, sending pricing emails, and sitting on calls with people who have no budget. It's called Ballpark. Here's how it works:

I built a tool that brought in 80+ leads and let me raise my prices 123% this year. I also stopped writing proposals, sending pricing emails, and sitting on calls with people who have no budget. It's called Ballpark. Here's how it works:

Will Thomson

34,544 Aufrufe • vor 10 Monaten

Oh, I forgot to mention, they also surprised us with +1s each on top of everything!! 😭 took care of all flights (national AND international btw), hotels, tickets, etc.. Experiencing this with Moe 10 years later was EVERYTHING! 😩 FULL. CIRCLE. MOMENT! My heart is full. ❤️🙏🏽

Oh, I forgot to mention, they also surprised us with +1s each on top of everything!! 😭 took care of all flights (national AND international btw), hotels, tickets, etc.. Experiencing this with Moe 10 years later was EVERYTHING! 😩 FULL. CIRCLE. MOMENT! My heart is full. ❤️🙏🏽

D A L I A

46,431 Aufrufe • vor 1 Jahr

I hated how bad Claude code was at video prompting I hated how I was prompting blind, with no real reference to anchor my content formats So I built LazyReel: it turns any winning video into the reference + context your model needs - 5,560+ real videos decoded (21B+ views) - frames → true context, not another prompt - 1 MCP (Claude/Codex), pairs with Higgsfield 100% Free...AI native...no rate limits...no subscriptions.. Enjoy (and tell a friend) 🫡

I hated how bad Claude code was at video prompting I hated how I was prompting blind, with no real reference to anchor my content formats So I built LazyReel: it turns any winning video into the reference + context your model needs - 5,560+ real videos decoded (21B+ views) - frames → true context, not another prompt - 1 MCP (Claude/Codex), pairs with Higgsfield 100% Free...AI native...no rate limits...no subscriptions.. Enjoy (and tell a friend) 🫡

Kid Pak

31,676 Aufrufe • vor 3 Monaten

this is f*cking beyond comprehension. Google engineers just shipped the entire agent lifecycle in one release: build, scale, govern. and every piece answers a specific way agents die in production > context layers (Static, Turn, User, Cache): you decide what the model carries between turns, so token spend stops being a mystery > a self heal plugin: the agent notices a tool call failed and retries it a different way instead of dying mid run > adk deploy: one command from your laptop to the managed runtime, no packaging, no infra ticket > Go joins Python and Java, with its own A2A SDK then the part nobody builds for themselves: > a dashboard on token consumption, latency, error rates and tool calls: the four things that actually kill an agent > a traces tab that opens the real sequence of actions the agent took, step by step > a playground wired to the deployed agent, past sessions included, so debugging is not a redeploy loop > an Evaluation Layer with a User Simulator, because you cannot unit test a non deterministic system and the part that decides whether it ever ships: > agents get native identities as first class IAM principals: least privilege applies to them like it does to people > Model Armor screens prompt injection, tool calls and responses, inline for Gemini or over REST > Security Command Center inventories every agentic asset and flags data exfiltration by an agent ADK is already at 7 million downloads. the runtime has a free tier, and express mode runs off a Gmail address. the prototype was never the hard part.

this is f*cking beyond comprehension. Google engineers just shipped the entire agent lifecycle in one release: build, scale, govern. and every piece answers a specific way agents die in production > context layers (Static, Turn, User, Cache): you decide what the model carries between turns, so token spend stops being a mystery > a self heal plugin: the agent notices a tool call failed and retries it a different way instead of dying mid run > adk deploy: one command from your laptop to the managed runtime, no packaging, no infra ticket > Go joins Python and Java, with its own A2A SDK then the part nobody builds for themselves: > a dashboard on token consumption, latency, error rates and tool calls: the four things that actually kill an agent > a traces tab that opens the real sequence of actions the agent took, step by step > a playground wired to the deployed agent, past sessions included, so debugging is not a redeploy loop > an Evaluation Layer with a User Simulator, because you cannot unit test a non deterministic system and the part that decides whether it ever ships: > agents get native identities as first class IAM principals: least privilege applies to them like it does to people > Model Armor screens prompt injection, tool calls and responses, inline for Gemini or over REST > Security Command Center inventories every agentic asset and flags data exfiltration by an agent ADK is already at 7 million downloads. the runtime has a free tier, and express mode runs off a Gmail address. the prototype was never the hard part.

NO1ennn

24,666 Aufrufe • vor 15 Tagen

"It's on my todo to build my own stack of apple minis and run Llama on my own little cluster on my desk." - Garry Tan Quick AI homelab tutorial: - Install EXO Labs on each mini (open source, steps in README) - Make sure all the minis are on the same WiFi network or for faster/more reliable results, connected over Thunderbolt/Ethernet. Devices will auto-discover each other and auto-shard the LLMs. - Now you can chat to your cluster with your preferred LLM GUI (the tiny corp tinychat ships with exo)

"It's on my todo to build my own stack of apple minis and run Llama on my own little cluster on my desk." - Garry Tan Quick AI homelab tutorial: - Install EXO Labs on each mini (open source, steps in README) - Make sure all the minis are on the same WiFi network or for faster/more reliable results, connected over Thunderbolt/Ethernet. Devices will auto-discover each other and auto-shard the LLMs. - Now you can chat to your cluster with your preferred LLM GUI (the tiny corp tinychat ships with exo)

Alex Cheema

244,754 Aufrufe • vor 1 Jahr

Hyperscape social is here on Quest 3! I invited Jdun over to my back deck to chat and I visited his studio. It's insane how amazing this is already. Full video out on the channel with more.

Hyperscape social is here on Quest 3! I invited Jdun over to my back deck to chat and I visited his studio. It's insane how amazing this is already. Full video out on the channel with more.

BMFVR

24,132 Aufrufe • vor 10 Monaten

Not a top reason the Lions lost — they got thoroughly outplayed — but it’s worth noting: on Jack Campbell’s roughing-the-passer penalty, he actually put his right hand out to brace the impact and avoid landing with his full body weight on J.J. McCarthy.

Not a top reason the Lions lost — they got thoroughly outplayed — but it’s worth noting: on Jack Campbell’s roughing-the-passer penalty, he actually put his right hand out to brace the impact and avoid landing with his full body weight on J.J. McCarthy.

Al Karsten

31,723 Aufrufe • vor 11 Monaten

someone just open-sourced their own neuro-sama. and it might be better than the original. it's called airi. a fully autonomous ai companion that speaks with you in real time, joins you in minecraft and factorio, chats through discord and telegram, and comes with a live2d/vrm avatar. runs entirely on your machine. → real-time voice chat and speech recognition → animated avatar with automatic blinking, eye tracking, and idle movements → persistent memory between sessions → local inference through webgpu, no api calls required supports 30+ llm providers, including openai, claude, gemini, deepseek, ollama, groq, mistral, xai, and local models. switch the brain with a config change. uses native cuda and apple metal for real gpu acceleration. 17.5k stars. 101 contributors. 46 releases. completely free. open source.

Simplifying AI

188,298 Aufrufe • vor 4 Tagen

📷 Sora 2 is outdated - Veo 3.1 just dropped on ImagineArt! Say hello to next-gen realism 📷 • Lifelike motion with context-aware audio • First- and last-frame reference for seamless transitions • Generate cinematic videos from a single image A true Sora 2 challenger has entered the chat. The AI video race never sleeps. 📷

📷 Sora 2 is outdated - Veo 3.1 just dropped on ImagineArt! Say hello to next-gen realism 📷 • Lifelike motion with context-aware audio • First- and last-frame reference for seamless transitions • Generate cinematic videos from a single image A true Sora 2 challenger has entered the chat. The AI video race never sleeps. 📷

ImagineArt

770,037 Aufrufe • vor 11 Monaten

This is an interesting case with Grok Imagine: I wrote the prompt of animation in French, my native language. I asked that the woman be delighted to be on this flower. Grok understood my request so well and went even further by having my character speak in French. "Oh, it's so sweet, I feel so light and happy here. This flower is magical."

This is an interesting case with Grok Imagine: I wrote the prompt of animation in French, my native language. I asked that the woman be delighted to be on this flower. Grok understood my request so well and went even further by having my character speak in French. "Oh, it's so sweet, I feel so light and happy here. This flower is magical."

Déborah

4,048,485 Aufrufe • vor 8 Monaten

My class “Chibi Me Up! Designing Expressive VTuber Models and Toggles” is now up for pre-order on Coloso(Coloso Global) We'll learn how to make your VTuber move more naturally & also to switch between full to chibi versions with just one click! Link:

My class “Chibi Me Up! Designing Expressive VTuber Models and Toggles” is now up for pre-order on Coloso(Coloso Global) We'll learn how to make your VTuber move more naturally & also to switch between full to chibi versions with just one click! Link:

👾【𝐗𝐄𝐀𝐏𝐇𝐄𝐑】

22,178 Aufrufe • vor 9 Monaten