Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Transcribe. Translate. Recognise. And now — Synthesise. Introducing Indic-Speak: 4B params, 23 languages, one model. Built by BodhanAI and AI4Bharat There's a bit in this video where two speakers, Parth and Dhara, have a podcast style conversation about "Attention Is All You Need" in Hindi — generated in a...

MiteshKhapra's profile picture

Mitesh Khapra

1,996 subscribers

130,697 görüntüleme • 10 gün önce •via X (Twitter)

Bilim & TeknolojiEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

28 Yorum

Cryptlesh profil fotoğrafı
Cryptlesh10 gün önce

@Bodhan_AI @ai4bharat Excited to try. Is it open source?

Mitesh Khapra profil fotoğrafı
Mitesh Khapra10 gün önce

@Bodhan_AI @ai4bharat Yes, it will be a open weights model.

Sasank Chilamkurthy profil fotoğrafı
Sasank Chilamkurthy10 gün önce

@Bodhan_AI @ai4bharat Please publish a paper on the work!

wood at work profil fotoğrafı
wood at work10 gün önce

@Bodhan_AI @ai4bharat really good especially in hindi . tried all the tts , hindi one one seem to close to real . love it

Jikku Jose profil fotoğrafı
Jikku Jose10 gün önce

@Bodhan_AI @ai4bharat Amazing first time feeling Malayalam sounding natural from something other than Gemini! And I so happy that you guys did code mix! Excited to check this one!

vesh profil fotoğrafı
vesh10 gün önce

@Bodhan_AI @ai4bharat All your other models video stated as live in hughingface also, but this model not mentioned why? Will it be open weight model?

harsh profil fotoğrafı
harsh10 gün önce

@Bodhan_AI @ai4bharat Irony! I was learning abouf transformers and attention from your course itself today. This approach seems much better , with better pronounciation and vocals. Great work.

Shawn Chauhan profil fotoğrafı
Shawn Chauhan10 gün önce

@Bodhan_AI @ai4bharat Amazing work🙌🏼🙌🏼

Bhaskar Jha profil fotoğrafı
Bhaskar Jha10 gün önce

@Bodhan_AI @ai4bharat Awesome, Congratulations to everyone involved

Shenoy profil fotoğrafı
Shenoy10 gün önce

@Bodhan_AI @ai4bharat Super excited to try this.. I am working on something and I need good TTS for Indic Languages…

Surya A. Moitra profil fotoğrafı
Surya A. Moitra10 gün önce

@Bodhan_AI @ai4bharat waiting to try the Open Weights

Ravi Narayanan profil fotoğrafı
Ravi Narayanan10 gün önce

@Bodhan_AI @ai4bharat Wow excited to try this ..I hope it covers tamil + english tanglish also ryt

VENKAT ASHOK K profil fotoğrafı
VENKAT ASHOK K10 gün önce

@Bodhan_AI @ai4bharat Is the LLM open source?

Crio Songo profil fotoğrafı
Crio Songo10 gün önce

@Bodhan_AI @ai4bharat 4B参数就能做23种印度语言的统一语音模型，还能原生处理混编语言，这个方向选得挺准，期待上线看效果。

Shashank profil fotoğrafı
Shashank10 gün önce

@Bodhan_AI @ai4bharat Hello @MiteshKhapra its all fine but how i can gets my hands on these models i want to test it for my project thats i am hustling.

Harsh Khandelwal profil fotoğrafı
Harsh Khandelwal5 gün önce

@Bodhan_AI @ai4bharat Is it available now?

vesh profil fotoğrafı
vesh6 gün önce

@Bodhan_AI @ai4bharat How a company hyped and posted many things and misses the launch day, that too incubated by iit ? Atleast an announcement regarding delay should have been posted.

Debjit B. profil fotoğrafı
Debjit B.10 gün önce

@Bodhan_AI @ai4bharat Please share the link.

Mitesh Khapra profil fotoğrafı
Mitesh Khapra10 gün önce

@Bodhan_AI @ai4bharat Will be available on HF on 05.09.2026

vesh profil fotoğrafı
vesh10 gün önce

@Bodhan_AI @ai4bharat Any plans for sub 1b model for synthesis? For edge deployment sub 1b will be best

Hemanshu profil fotoğrafı
Hemanshu10 gün önce

@Bodhan_AI @ai4bharat Love it!

Manash profil fotoğrafı
Manash9 gün önce

@Bodhan_AI @ai4bharat Is the training data going to be open source???

Rithul profil fotoğrafı
Rithul10 gün önce

@Bodhan_AI @ai4bharat Hi, is the API available for public use, or is this currently only for research purposes?

Mitesh Khapra profil fotoğrafı
Mitesh Khapra10 gün önce

@Bodhan_AI @ai4bharat Will be available for public use on 05.09.2026

Rithul profil fotoğrafı
Rithul10 gün önce

@Bodhan_AI @ai4bharat will it be opensource?

Ashwin Sankar profil fotoğrafı
Ashwin Sankar10 gün önce

@MiteshKhapra @Bodhan_AI @ai4bharat It will be open-weights and will be released on @huggingface

Rithul profil fotoğrafı
Rithul10 gün önce

@MiteshKhapra @Bodhan_AI @ai4bharat @huggingface That's awsome!!

Shivam Gupta profil fotoğrafı
Shivam Gupta10 gün önce

@Bodhan_AI @ai4bharat 4B params is huge for a TTS.. no?

Benzer Videolar

Text (Indic-Translate). Speech (Indic-Transcribe). Now vision. IndicOCR, the new kid on the block. Built by AI4Bharat and BodhanAI Handwritten notes, degraded archives, 9+ scripts, all in a 0.8B model that holds its own against models 4-5x its size. Live 05.09.2026. Short video here 👇 full version in the reply.
0:41

Text (Indic-Translate). Speech (Indic-Transcribe). Now vision. IndicOCR, the new kid on the block. Built by AI4Bharat and BodhanAI Handwritten notes, degraded archives, 9+ scripts, all in a 0.8B model that holds its own against models 4-5x its size. Live 05.09.2026. Short video here 👇 full version in the reply.

Mitesh Khapra

192,291 görüntüleme • 17 gün önce

Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with Hugging Face, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality speech technology to India’s diverse linguistic community. Supporting 20 of the 22 scheduled Indian languages—and English in various accents (US, British, Indian)—it’s built to serve over a billion speakers and empower companies, developers, researchers, and communities. Why Indic Parler-TTS Stands Out: 1. Open and Accessible: Fully open-source with permissive licensing for unrestricted usage. 2. Wide Language Support: Includes a vast range of Indic languages, with rich diversity in voices. 3. High-Quality Audio: Produces natural, clear, and lifelike speech. 4. Adaptable and Fine-Tunable: Customize it to new languages, accents, or specific applications. 5. State-of-the-Art Performance: Proven through rigorous evaluation. 6. Versatile and Inclusive: Indic Parler-TTS offers 69 unique voices across 18 Indian languages, making it a perfect fit for diverse use cases like audiobooks, virtual assistants, and educational tools. Let's democratize speech technology together and make speech technology more inclusive and accessible for everyone. ▶️ Experience it now: Demo: Model page:
1:06

Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with Hugging Face, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality speech technology to India’s diverse linguistic community. Supporting 20 of the 22 scheduled Indian languages—and English in various accents (US, British, Indian)—it’s built to serve over a billion speakers and empower companies, developers, researchers, and communities. Why Indic Parler-TTS Stands Out: 1. Open and Accessible: Fully open-source with permissive licensing for unrestricted usage. 2. Wide Language Support: Includes a vast range of Indic languages, with rich diversity in voices. 3. High-Quality Audio: Produces natural, clear, and lifelike speech. 4. Adaptable and Fine-Tunable: Customize it to new languages, accents, or specific applications. 5. State-of-the-Art Performance: Proven through rigorous evaluation. 6. Versatile and Inclusive: Indic Parler-TTS offers 69 unique voices across 18 Indian languages, making it a perfect fit for diverse use cases like audiobooks, virtual assistants, and educational tools. Let's democratize speech technology together and make speech technology more inclusive and accessible for everyone. ▶️ Experience it now: Demo: Model page:

AI4Bharat

28,681 görüntüleme • 1 yıl önce

A very happy 80th Independence Day to India, from team Cartesia! 🇮🇳 Coming closer to home with Sonic 3.6, we're making every one of India's languages more natural, expressive, and accurate: - Hindi that flows the way you speak it - Hinglish that switches without missing a beat - Naturalness gains across all 9 existing Indic languages - Plus two new languages: Urdu and Odia Every voice in this video generated by Sonic.
0:49

A very happy 80th Independence Day to India, from team Cartesia! 🇮🇳 Coming closer to home with Sonic 3.6, we're making every one of India's languages more natural, expressive, and accurate: - Hindi that flows the way you speak it - Hinglish that switches without missing a beat - Naturalness gains across all 9 existing Indic languages - Plus two new languages: Urdu and Odia Every voice in this video generated by Sonic.

Cartesia

110,964 görüntüleme • 28 gün önce

India’s Sovereign Move - Sarvam Vision Cracks the Code across 22 Indian languages Sarvam Vision is an AI model from Sarvam AI that excels in optical character recognition (OCR) for 22 Indian languages, outperforming global models like Gemini and GPT-4o on Indic benchmarks. This achievement supports India's push for sovereign AI by digitizing real-world documents and archives in local scripts. ​ Sarvam Vision, a 3-billion-parameter model, handles "messy" scanned paperwork across languages like Hindi (95.91% accuracy), Bengali (92.61%), Tamil (93.42%), Marathi (93.13%), and even low-resource ones like Santali and Dogri (over 80%). ​ It structures data natively without relying on English translation layers, enabling applications in cultural recovery and document intelligence. ​ The model powers India's sovereign AI infrastructure under the IndiaAI Mission, where Sarvam was selected to build a national LLM. This launch fits Sarvam's broader stack, including prior models like Sarvam-Translate (also for 22 languages) and audio models for code-mixed speech. By focusing on Indic challenges ignored by Western AI, it unlocks centuries of knowledge in non-English archives. ​ Recent demos, like digitizing historical texts, highlight its real-world impact beyond benchmarks. Credit : AIM Network.
6:27

India’s Sovereign Move - Sarvam Vision Cracks the Code across 22 Indian languages Sarvam Vision is an AI model from Sarvam AI that excels in optical character recognition (OCR) for 22 Indian languages, outperforming global models like Gemini and GPT-4o on Indic benchmarks. This achievement supports India's push for sovereign AI by digitizing real-world documents and archives in local scripts. ​ Sarvam Vision, a 3-billion-parameter model, handles "messy" scanned paperwork across languages like Hindi (95.91% accuracy), Bengali (92.61%), Tamil (93.42%), Marathi (93.13%), and even low-resource ones like Santali and Dogri (over 80%). ​ It structures data natively without relying on English translation layers, enabling applications in cultural recovery and document intelligence. ​ The model powers India's sovereign AI infrastructure under the IndiaAI Mission, where Sarvam was selected to build a national LLM. This launch fits Sarvam's broader stack, including prior models like Sarvam-Translate (also for 22 languages) and audio models for code-mixed speech. By focusing on Indic challenges ignored by Western AI, it unlocks centuries of knowledge in non-English archives. ​ Recent demos, like digitizing historical texts, highlight its real-world impact beyond benchmarks. Credit : AIM Network.

Augadh

20,708 görüntüleme • 7 ay önce

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊
2:13

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊

Soniox

663,421 görüntüleme • 1 ay önce

DHRUVA SARJA - SANJAY DUTT - SHILPA SHETTY PAN-INDIA FILM: 'KD THE DEVIL' *HINDI* TEASER OUT NOW... This looks like a full-on massy entertainer... The teaser of PAN-#India film #KDTheDevil [#KDTeaser] is now LIVE. Starring #DhruvaSarja, #KDTheDevil also features #SanjayDutt, #ShilpaShetty, #NoraFatehi, and #RameshAravind. Produced by #KVNProductions and directed by #PremS, the film will release in #Kannada, #Hindi, #Tamil, #Telugu, and #Malayalam.
1:59

DHRUVA SARJA - SANJAY DUTT - SHILPA SHETTY PAN-INDIA FILM: 'KD THE DEVIL' *HINDI* TEASER OUT NOW... This looks like a full-on massy entertainer... The teaser of PAN-#India film #KDTheDevil [#KDTeaser] is now LIVE. Starring #DhruvaSarja, #KDTheDevil also features #SanjayDutt, #ShilpaShetty, #NoraFatehi, and #RameshAravind. Produced by #KVNProductions and directed by #PremS, the film will release in #Kannada, #Hindi, #Tamil, #Telugu, and #Malayalam.

taran adarsh

185,853 görüntüleme • 1 yıl önce

Text to Sound Effects is here. Our newest AI Audio model generates sound effects, short instrumental tracks, soundscapes, and a wide variety of character voices, all from a text prompt. Available now for all users. Everyone from content creators, video game developers, to film and television studios, uses sound effects to create rich and immersive content. Now, in addition to AI voiceovers, you can generate all of the sounds you need with just a prompt. Everything you hear in this video was generated by ElevenLabs sound and voice models. In this thread, we shared some additional clips that help show off the range of this new model.
1:08

Text to Sound Effects is here. Our newest AI Audio model generates sound effects, short instrumental tracks, soundscapes, and a wide variety of character voices, all from a text prompt. Available now for all users. Everyone from content creators, video game developers, to film and television studios, uses sound effects to create rich and immersive content. Now, in addition to AI voiceovers, you can generate all of the sounds you need with just a prompt. Everything you hear in this video was generated by ElevenLabs sound and voice models. In this thread, we shared some additional clips that help show off the range of this new model.

ElevenLabs

451,024 görüntüleme • 2 yıl önce

Listen, speak, handle interruptions, and call tools in one live conversation. 🎙️ Introducing NVIDIA-NemotronLabs-VoiceChat-11B, NVIDIA’s end-to-end full-duplex model for real-time voice agents. 🤖 🏆 It ranks #2 among open full-duplex models on both VoiceBench and Full-Duplex-Bench 1.0. ⚡ Natural turn-taking responds in ~448 ms, while barge-in lets users interrupt the model with ~480 ms latency. 🛠️ The first open full-duplex model with live tool calling. One unified system handles speech understanding, generation, transcription, and tool execution while keeping the conversation flowing. 🧠 Built with a Fast Conformer, Nemotron Nano v2, and a TTS decoder, trained on ~550K hours of real and synthetic speech. 📜 Research use only. OpenMDW 1.1.
1:24

Listen, speak, handle interruptions, and call tools in one live conversation. 🎙️ Introducing NVIDIA-NemotronLabs-VoiceChat-11B, NVIDIA’s end-to-end full-duplex model for real-time voice agents. 🤖 🏆 It ranks #2 among open full-duplex models on both VoiceBench and Full-Duplex-Bench 1.0. ⚡ Natural turn-taking responds in ~448 ms, while barge-in lets users interrupt the model with ~480 ms latency. 🛠️ The first open full-duplex model with live tool calling. One unified system handles speech understanding, generation, transcription, and tool execution while keeping the conversation flowing. 🧠 Built with a Fast Conformer, Nemotron Nano v2, and a TTS decoder, trained on ~550K hours of real and synthetic speech. 📜 Research use only. OpenMDW 1.1.

ModelScope

22,194 görüntüleme • 1 ay önce

I made a live-action series – 'Penumbra' – on invideo’s Agent One without the screenplay, pre-production plan or script locked going in. I started with a vague idea about two characters and built the episode scene by scene, pulling references on the fly and brainstorming with the agents the way I would with a real crew.Had around 20-25 agents working in parallel by the end of it. Took me ~10 days. ~$6,540. Full breakdown in the video and the thread.
14:19

I made a live-action series – 'Penumbra' – on invideo’s Agent One without the screenplay, pre-production plan or script locked going in. I started with a vague idea about two characters and built the episode scene by scene, pulling references on the fly and brainstorming with the agents the way I would with a real crew.Had around 20-25 agents working in parallel by the end of it. Took me ~10 days. ~$6,540. Full breakdown in the video and the thread.

Invideo

139,395 görüntüleme • 2 ay önce

HRITHIK ROSHAN - RYAN GOSLING CONNECT FOR 'PROJECT HAIL MARY' CONVERSATION... In a landmark moment, #HrithikRoshan and #Hollywood actor #RyanGosling come together for an exclusive virtual conversation on the much-anticipated biggie #ProjectHailMary. The conversation builds on the tremendous global momentum generated by #HrithikRoshan's association with #ProjectHailMary, following a collaboration video that captivated audiences worldwide. Bringing together two of the world's most influential stars, the conversation offers fans a rare and candid glimpse into their creative worlds. Starring #RyanGosling, the film is presented by Amazon MGM Studios and distributed by Sony Pictures Releasing International. #ProjectHailMary is set for a theatrical release in #India on 26 March 2026, in #English, #Hindi, #Tamil, and #Telugu.
4:50

HRITHIK ROSHAN - RYAN GOSLING CONNECT FOR 'PROJECT HAIL MARY' CONVERSATION... In a landmark moment, #HrithikRoshan and #Hollywood actor #RyanGosling come together for an exclusive virtual conversation on the much-anticipated biggie #ProjectHailMary. The conversation builds on the tremendous global momentum generated by #HrithikRoshan's association with #ProjectHailMary, following a collaboration video that captivated audiences worldwide. Bringing together two of the world's most influential stars, the conversation offers fans a rare and candid glimpse into their creative worlds. Starring #RyanGosling, the film is presented by Amazon MGM Studios and distributed by Sony Pictures Releasing International. #ProjectHailMary is set for a theatrical release in #India on 26 March 2026, in #English, #Hindi, #Tamil, and #Telugu.

taran adarsh

586,240 görüntüleme • 5 ay önce

hmmm. Ally Sammarco stated in a viral video, "Imagine you are at a bowling alley with a handgun and a perpetrator walks in with a militiray style weapon and a bullet proof vest. There's literally no way you are going to be able to defend yourself. Banning weapons of war on the street isn't about infringing on you, it's about protecting you." In this video I debunk her viral video. ALSO, right now exclusive to my Twitter subscribers, for our Store-wide holiday sale, all the shirts, drinkware and hoodies, including the Need Money For Guns and Need Money For Pew Pew designs are 20% OFF when you use the code: "NeedMoneyGun" while supplies last! Click Here➡️
6:03

hmmm. Ally Sammarco stated in a viral video, "Imagine you are at a bowling alley with a handgun and a perpetrator walks in with a militiray style weapon and a bullet proof vest. There's literally no way you are going to be able to defend yourself. Banning weapons of war on the street isn't about infringing on you, it's about protecting you." In this video I debunk her viral video. ALSO, right now exclusive to my Twitter subscribers, for our Store-wide holiday sale, all the shirts, drinkware and hoodies, including the Need Money For Guns and Need Money For Pew Pew designs are 20% OFF when you use the code: "NeedMoneyGun" while supplies last! Click Here➡️

Colion Noir

167,682 görüntüleme • 2 yıl önce

Tried something a little ambitious with Kling AI MCP — a full 1-minute J-pop-style music video featuring two consistent characters, Girl A and Girl B, from the MCP Elements library. 🎬🎶 Instead of generating a bunch of 5-second clips and stitching everything together, I built the entire minute in one workflow. The music, characters, and editing all came together in the same setup, so there was no need to jump between different tools. Honestly, this is one of the first times I’ve seen an MCP workflow handle music-video-length continuity this smoothly. #Kling
1:00

Tried something a little ambitious with Kling AI MCP — a full 1-minute J-pop-style music video featuring two consistent characters, Girl A and Girl B, from the MCP Elements library. 🎬🎶 Instead of generating a bunch of 5-second clips and stitching everything together, I built the entire minute in one workflow. The music, characters, and editing all came together in the same setup, so there was no need to jump between different tools. Honestly, this is one of the first times I’ve seen an MCP workflow handle music-video-length continuity this smoothly. #Kling

Bairan

90,068 görüntüleme • 1 gün önce

MICROSOFT OPEN SOURCED A 7B PARAMETER MODEL THAT TRANSCRIBES 60 MINUTES OF AUDIO IN A SINGLE PASS and it's completely free VIBEVOICE ASR no chunking, no context loss, full speaker diarization baked in not just speech to text..not a basic wrapper who spoke, when they spoke, exactly what they said..all in one shot and it handles the hard stuff too..50+ languages, custom hotwords, long form audio that breaks every other tool the model doesn't know what "context window" means apparently Available on macOS and Windows right now. Free to use. Free to fine tune. Free to build on.
5:45

MICROSOFT OPEN SOURCED A 7B PARAMETER MODEL THAT TRANSCRIBES 60 MINUTES OF AUDIO IN A SINGLE PASS and it's completely free VIBEVOICE ASR no chunking, no context loss, full speaker diarization baked in not just speech to text..not a basic wrapper who spoke, when they spoke, exactly what they said..all in one shot and it handles the hard stuff too..50+ languages, custom hotwords, long form audio that breaks every other tool the model doesn't know what "context window" means apparently Available on macOS and Windows right now. Free to use. Free to fine tune. Free to build on.

Rahul

1,375,300 görüntüleme • 4 ay önce

Seedance 2.5 is insane for marketing and UGC. I've already spent close to $6000 in generations and here's what I noticed: - Realism is on another level This entire vlog is generated. Freckles, flyaway hair, wind gusts, even the exposure shifts of a real phone camera. Nothing in this frame reads as AI. - Pay close attention to the video at 0:14 She flips the camera to show the valley and pans back to herself mid-sentence. Camera movement, lighting, and action like this all in a single pass were never possible before. - Voices finally sound human She talks to camera for the full 30 seconds. No robotic AI delivery, she breathes, pauses, and hits emotion like a real creator. - Up to 30 seconds in a single pass One take from start to finish. Characters don't drift and blocking works better than any other model. - Up to 50 inputs in one generation Feed your product, your creator, and your style references into a single run. UGC marketing will never be the same. Seedance 2.5 coming soon to Higgsfield.
0:30

Seedance 2.5 is insane for marketing and UGC. I've already spent close to $6000 in generations and here's what I noticed: - Realism is on another level This entire vlog is generated. Freckles, flyaway hair, wind gusts, even the exposure shifts of a real phone camera. Nothing in this frame reads as AI. - Pay close attention to the video at 0:14 She flips the camera to show the valley and pans back to herself mid-sentence. Camera movement, lighting, and action like this all in a single pass were never possible before. - Voices finally sound human She talks to camera for the full 30 seconds. No robotic AI delivery, she breathes, pauses, and hits emotion like a real creator. - Up to 30 seconds in a single pass One take from start to finish. Characters don't drift and blocking works better than any other model. - Up to 50 inputs in one generation Feed your product, your creator, and your style references into a single run. UGC marketing will never be the same. Seedance 2.5 coming soon to Higgsfield.

Adil Alimzhanov

11,569 görüntüleme • 1 ay önce

Claude Code is now a full video editor! Our new plugin opens a full built-in NLE right inside the Claude desktop app, where you and your agent can edit together, effortlessly. If you're already paying for Claude, you get this one for FREE. It's available now. Start using it in 1 minute, by pasting this prompt into any Claude Code chat: "Read to install and use the ChatCut plugin"
0:44

Claude Code is now a full video editor! Our new plugin opens a full built-in NLE right inside the Claude desktop app, where you and your agent can edit together, effortlessly. If you're already paying for Claude, you get this one for FREE. It's available now. Start using it in 1 minute, by pasting this prompt into any Claude Code chat: "Read to install and use the ChatCut plugin"

ChatCut

227,551 görüntüleme • 1 ay önce

The two authors of Pi share three design principles in this 3-minute video: → Coding doesn’t need a separate memory system Code is the ground truth, and it keeps changing. Maintaining a separate memory that describes the code creates one more thing to maintain and keep in sync. Models can usually infer a project’s structure and coding style after reading one or two files. If they need help navigating it, a folder list with short descriptions is enough. For a chat bot, the ground truth is the conversation log. They append questions and answers from Slack channels to JSONL, then query the history with jq. → Bash is all you need Models already know Bash and can combine commands and scripts themselves. They don’t use MCP for Sentry data. Instead, they built an on-demand Skill that handles authentication and pulls the data in a fixed format. → Load tool output into context only when needed When Sentry returns 52 items, the Skill puts only 3 into context and writes the rest to a JSON file. Once the model confirms the structure looks right, it reads the remaining items.
2:56

The two authors of Pi share three design principles in this 3-minute video: → Coding doesn’t need a separate memory system Code is the ground truth, and it keeps changing. Maintaining a separate memory that describes the code creates one more thing to maintain and keep in sync. Models can usually infer a project’s structure and coding style after reading one or two files. If they need help navigating it, a folder list with short descriptions is enough. For a chat bot, the ground truth is the conversation log. They append questions and answers from Slack channels to JSONL, then query the history with jq. → Bash is all you need Models already know Bash and can combine commands and scripts themselves. They don’t use MCP for Sentry data. Instead, they built an on-demand Skill that handles authentication and pulls the data in a fixed format. → Load tool output into context only when needed When Sentry returns 52 items, the Skill puts only 3 into context and writes the rest to a JSON file. Once the model confirms the structure looks right, it reads the remaining items.

Vox

166,060 görüntüleme • 24 gün önce