Загрузка видео...

Не удалось загрузить видео

На главную

update: i gave chatgpt full access to the taskmaster github repo and asked it to produce a thorough investigation of the product, the code and architecture, and to pay special attention to LLM-powered test generation, which I particularly care about right now it responded with an 8-page Mackenzie consultant-level...

EyalToledano's profile picture

Eyal Toledano

17,958 subscribers

12,633 просмотров • 1 год назад •via X (Twitter)

ФинансыНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Dawood Khan
Dawood Khan1 год назад

The amount of effort you put in improving this product is remarkable ❤️

Фото профиля Eyal Toledano
Eyal Toledano1 год назад

I appreciate you!

Фото профиля Manticore Search
Manticore Search1 год назад

🚀 Star Manticore Search on #GitHub today and join our quest for the ultimate search solution!

Фото профиля Jake Sacino
Jake Sacino1 год назад

Had the same experience. PDF export is nice. Just wish you could explore a codebase without forking it.

Фото профиля Eyal Toledano
Eyal Toledano1 год назад

It’s my codebase so i don’t mind 😂

Фото профиля John Curtis
John Curtis1 год назад

Hey do you mind sharing how it planned to reduce the tool count?

Фото профиля Eyal Toledano
Eyal Toledano1 год назад

p much in the way I was gonna do it i have many tools that can be consolidated into a higher order tool ie add-task, remove-task, update, update-taskc update-subtask can all be part of the task_management tool That tool would take in an argument for which sub tool to run

Фото профиля d0gs0n4c1d
d0gs0n4c1d1 год назад

wow this is really interesting stuff and the 8 pages from chatgpt sounds cool too! jokes aside, imo there would be a lot of potential in train a sortof dedicated “debugger_model”, (ideally from a foundation model)and then just giving to it taskmaster as a tool. 👀

Фото профиля Antonio Correa
Antonio Correa1 год назад

Bravo!👏🏻

Фото профиля Eyal Toledano
Eyal Toledano1 год назад

🤜🤛

Фото профиля Carlos
Carlos1 год назад

Wow

Похожие видео

ChatGPT Deep Research is one of the most useful AI agents out there. I use it for complex tasks, so it's one of the top AI products I get value from. I finally got to record how I use it and how to best leverage OpenAI's Deep Research. Enjoy! (bookmark it)
57:41

ChatGPT Deep Research is one of the most useful AI agents out there. I use it for complex tasks, so it's one of the top AI products I get value from. I finally got to record how I use it and how to best leverage OpenAI's Deep Research. Enjoy! (bookmark it)

elvis

65,442 просмотров • 1 год назад

Perplexity Comet is so good, just give it a task and let comet cook. I gave it access to my GitHub repo and asked it to set up a webhook to listen for push events, and it actually did it. It pulled the webhook URL from another tab, configured it correctly, selected the right event, and it worked perfectly.
1:06

Perplexity Comet is so good, just give it a task and let comet cook. I gave it access to my GitHub repo and asked it to set up a webhook to listen for push events, and it actually did it. It pulled the webhook URL from another tab, configured it correctly, selected the right event, and it worked perfectly.

AshutoshShrivastava

103,682 просмотров • 7 месяцев назад

I added Sentry to my app because it was a requirement for the recent Build Competition by Lovable. To be honest, I had no idea what Sentry did or how to use it. I simply asked Lovable to add it and provided the DSN value assigned by Sentry. Today I opened the Sentry dashboard and it blew my mind: 1) It can show you how your users interact with your app! 2) When your users hit an unexpected error, you get a copy of what triggered it and some information to help solve the error. There are a bunch of other features that I haven't discovered yet. Has anyone else discovered how useful Sentry is?
0:26

I added Sentry to my app because it was a requirement for the recent Build Competition by Lovable. To be honest, I had no idea what Sentry did or how to use it. I simply asked Lovable to add it and provided the DSN value assigned by Sentry. Today I opened the Sentry dashboard and it blew my mind: 1) It can show you how your users interact with your app! 2) When your users hit an unexpected error, you get a copy of what triggered it and some information to help solve the error. There are a bunch of other features that I haven't discovered yet. Has anyone else discovered how useful Sentry is?

Tristan Rhodes

21,549 просмотров • 1 год назад

This might be the best "AI Engineer" I've tried so far. ​ I'm an old school developer who started 30 years ago. I feel very uncomfortable letting AI take control of my code, but for the sake of science, I spent two hours building an application that took me weeks to build a couple of years ago. ​ I used Pythagora, a brand new tool backed by Y Combinator. They just released to the public. ​ Keep in mind that I use AI every day to write code, but Pythagora is something different: it's a tool that leads, and uses you—the human—as the copilot. ​ I go into more details in the video, but here is the TLDR; ​ 1. Holy molly! We've made a ton of progress on this front! This is way better than Devin when I tested it a few months back. ​ 2. Love the approach of generating a plan with sub-tasks before writing any code. ​ 3. The tools never tries to do too much: it tackles every small task one at a time, and gives you instructions so you test everything. ​ 4. It does exactly what you'd do when it gets stuck: writes a bunch of logs and uses those to correct itself. Pretty neat! ​ 5. It's fast. It runs locally. It's an extension to Visual Studio Code. ​ I'm impressed, but I don't think this tool is for me. ​ I'm not the type of developer who's ready to relinquish control. I felt I had no connection with the code because I didn't write it. It was not my code. ​ I know many people who don't care about this. I know many people who will get tremendous value out of Pythagora. I hope they keep pushing the limits, providing feedback, and helping this get to a point where old folks like me feel more comfortable using it. ​ Don't take my word for it. The best thing you can do is to give it a try and see how you feel using it. ​ Thanks to the team who built this, for all of the explanations and support, and especially, for sitting and listening to my dumb questions for 2 hours while I tested this.
8:37

This might be the best "AI Engineer" I've tried so far. ​ I'm an old school developer who started 30 years ago. I feel very uncomfortable letting AI take control of my code, but for the sake of science, I spent two hours building an application that took me weeks to build a couple of years ago. ​ I used Pythagora, a brand new tool backed by Y Combinator. They just released to the public. ​ Keep in mind that I use AI every day to write code, but Pythagora is something different: it's a tool that leads, and uses you—the human—as the copilot. ​ I go into more details in the video, but here is the TLDR; ​ 1. Holy molly! We've made a ton of progress on this front! This is way better than Devin when I tested it a few months back. ​ 2. Love the approach of generating a plan with sub-tasks before writing any code. ​ 3. The tools never tries to do too much: it tackles every small task one at a time, and gives you instructions so you test everything. ​ 4. It does exactly what you'd do when it gets stuck: writes a bunch of logs and uses those to correct itself. Pretty neat! ​ 5. It's fast. It runs locally. It's an extension to Visual Studio Code. ​ I'm impressed, but I don't think this tool is for me. ​ I'm not the type of developer who's ready to relinquish control. I felt I had no connection with the code because I didn't write it. It was not my code. ​ I know many people who don't care about this. I know many people who will get tremendous value out of Pythagora. I hope they keep pushing the limits, providing feedback, and helping this get to a point where old folks like me feel more comfortable using it. ​ Don't take my word for it. The best thing you can do is to give it a try and see how you feel using it. ​ Thanks to the team who built this, for all of the explanations and support, and especially, for sitting and listening to my dumb questions for 2 hours while I tested this.

Santiago

211,985 просмотров • 1 год назад

Testing the next feature coming from Runway and it’s wild. You’ll soon be able to create just by chatting. One of the most impressive things I’ve seen is that it can now do stuff that even ChatGPT can’t. In this test, I asked it to add fur to objects that normally don’t have any...and boom, it generated a whole series of fuzzy creations. Then I gave it a character reference and asked for him to be playing the piano. It made mistakes at first, but kept correcting itself until it nailed the shot. Finally, I asked for a video based on the image... and it delivered again. The ability to iterate and evolve your vision in real-time is just incredible. Still makes mistakes and it can be much improved, but a massive shoutout to the team at Runway , this is next level.
1:00

Testing the next feature coming from Runway and it’s wild. You’ll soon be able to create just by chatting. One of the most impressive things I’ve seen is that it can now do stuff that even ChatGPT can’t. In this test, I asked it to add fur to objects that normally don’t have any...and boom, it generated a whole series of fuzzy creations. Then I gave it a character reference and asked for him to be playing the piano. It made mistakes at first, but kept correcting itself until it nailed the shot. Finally, I asked for a video based on the image... and it delivered again. The ability to iterate and evolve your vision in real-time is just incredible. Still makes mistakes and it can be much improved, but a massive shoutout to the team at Runway , this is next level.

@alexgnewmedia

21,183 просмотров • 1 год назад

An LLM with native access to find and run agents is a huge thing! This large language model (called ASI:One and developed by Fetch.ai) can do this natively when you show it a problem: • Reason about the problem • Identify live agents and tools that can help solve it • Dynamically invoke these agents and tools Honestly, this is pretty nuts! You don't need to set up anything beforehand. You don't need to write any code. Here is the best part: ASI:One has access to any agent published on Agentverse, an open directory of agents! This gives the model access to *millions* of tools it can execute dynamically when solving a task. Here is a simple example (the one in the attached video): • I went to Google Maps • I copied the latitude and longitude of a location • I asked ASI:One about relevant places around that location • ASI:One went to the marketplace • It identified and called the Google Places agent • It returned a list of museums, restaurants, and landmarks near my location Pretty awesome! You can try this now by going to You don't need to pay or register to test it out. If you want to get ideas of what's possible, check Agentverse, the agent marketplace: The model will have access to all of those tools. This is pretty awesome and opens up a whole new world of possibilities! Thanks to the team for partnering with me on this post!
4:59

An LLM with native access to find and run agents is a huge thing! This large language model (called ASI:One and developed by Fetch.ai) can do this natively when you show it a problem: • Reason about the problem • Identify live agents and tools that can help solve it • Dynamically invoke these agents and tools Honestly, this is pretty nuts! You don't need to set up anything beforehand. You don't need to write any code. Here is the best part: ASI:One has access to any agent published on Agentverse, an open directory of agents! This gives the model access to *millions* of tools it can execute dynamically when solving a task. Here is a simple example (the one in the attached video): • I went to Google Maps • I copied the latitude and longitude of a location • I asked ASI:One about relevant places around that location • ASI:One went to the marketplace • It identified and called the Google Places agent • It returned a list of museums, restaurants, and landmarks near my location Pretty awesome! You can try this now by going to You don't need to pay or register to test it out. If you want to get ideas of what's possible, check Agentverse, the agent marketplace: The model will have access to all of those tools. This is pretty awesome and opens up a whole new world of possibilities! Thanks to the team for partnering with me on this post!

Santiago

43,784 просмотров • 1 год назад

I asked my clawdbot to send a letter to me in the mail… and it actually did it. I gave it a crypto wallet and some USDC to make purchases with, and clawdbot went and read the agent documentation on postalform. It figured out how to draft an order with a PDF of the letter it wrote to me – then it used Stripe’s Purl cli and paid for the order using Stripe's new Machine Payments protocol. This is a huge step forward for real-world agentic task completion and commerce
0:51

I asked my clawdbot to send a letter to me in the mail… and it actually did it. I gave it a crypto wallet and some USDC to make purchases with, and clawdbot went and read the agent documentation on postalform. It figured out how to draft an order with a PDF of the letter it wrote to me – then it used Stripe’s Purl cli and paid for the order using Stripe's new Machine Payments protocol. This is a huge step forward for real-world agentic task completion and commerce

Gabriel Garrett

36,119 просмотров • 4 месяцев назад

Task Master CLI will makes Cursor 10x better at building projects. I created a full video demo of how it works. For those that don't want to watch. Here's what happens: 1️⃣ Install npm i task-master-ai CLI 2️⃣ Give it a description of your project. It will generate a PRD 3️⃣ It will then convert the PRD into tasks (10 detailed .txt files and a .json that acts as a local db to task track status) 4️⃣ Ask it to do a task. It will do the task and mark it off as done. Each task can also be broken down into small tasks using "expand" command. Following these steps it will build out an entire project. This is the future of dev and how tools like Manus work. But you can run it locally and follow step by step to make sure you're happy with what's happening. Seems a fitting to be posting about Task Master the day before Passover starts. Good job by Eyal Toledano who built this project.
12:18

Task Master CLI will makes Cursor 10x better at building projects. I created a full video demo of how it works. For those that don't want to watch. Here's what happens: 1️⃣ Install npm i task-master-ai CLI 2️⃣ Give it a description of your project. It will generate a PRD 3️⃣ It will then convert the PRD into tasks (10 detailed .txt files and a .json that acts as a local db to task track status) 4️⃣ Ask it to do a task. It will do the task and mark it off as done. Each task can also be broken down into small tasks using "expand" command. Following these steps it will build out an entire project. This is the future of dev and how tools like Manus work. But you can run it locally and follow step by step to make sure you're happy with what's happening. Seems a fitting to be posting about Task Master the day before Passover starts. Good job by Eyal Toledano who built this project.

Elie Steinbock

36,636 просмотров • 1 год назад

I asked ChatGPT to turn everything it knows about me into a portfolio. Then I connected it to Gamma and it built an entire deck in less than 3 minutes. I did not design anything, I did not write anything special. ChatGPT already had the context, Gamma used the context to build something real. Here's exactly how I did it 👇 Open ChatGPT → Go to Settings → Click on Apps → Search for Gamma → Click on `refrence memories and chat` → Connect. That's it. Once connected, start a new chat and give ChatGPT a prompt about yourself. I typed: "Turn my past projects and interests into a portfolio" ChatGPT pulled everything it already knows about me and Gamma turned it into a full structured deck in minutes 🧵
5:11

I asked ChatGPT to turn everything it knows about me into a portfolio. Then I connected it to Gamma and it built an entire deck in less than 3 minutes. I did not design anything, I did not write anything special. ChatGPT already had the context, Gamma used the context to build something real. Here's exactly how I did it 👇 Open ChatGPT → Go to Settings → Click on Apps → Search for Gamma → Click on `refrence memories and chat` → Connect. That's it. Once connected, start a new chat and give ChatGPT a prompt about yourself. I typed: "Turn my past projects and interests into a portfolio" ChatGPT pulled everything it already knows about me and Gamma turned it into a full structured deck in minutes 🧵

Oluwatimileyin✨🦋

390,207 просмотров • 1 месяц назад

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next
1:30

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

@levelsio

640,316 просмотров • 4 месяцев назад

Cameron Young is playing with a golf ball that would allegedly be compliant with the new roll back rules that will come into effect in a few years time. He was asked about it ahead of the PGA Championship and he says every player in the game is sacrificing distance for control, and he put it in play at the Wyndham last year which he won. “I think I put it in play the same reason that everybody else plays the ball that they play. I hit it during a ball test, one of the Titleist facilities probably close to two years ago and didn't know anything about it and just kind of say, hey, what's that one? Because I liked the flight. “Then as things progressed, I was able to test it last year at Wyndham, able to put that in play, and it's been there since. “Obviously there is no conforming list. I wasn't aware that it would have -- I suppose I read something that said it passed that test, but I wasn't aware of that until very recently. “So at no point was that a consideration. It was just really me trying to optimize my golf, and it's the ball that seems to work the best for me.” He then was asked whether he lost distance with it compared to other balls he’s tested: “Not particularly. I don't think any of us are out really here playing the ball that goes the farthest. I think you'd struggle to find a single person that's doing that. We're all sacrificing a certain amount of things that we feel are worth it, control with irons, control with wedges. For me, that's the biggest thing is being able to control spin, and this is the ball that does the best for me.” Finally he can as asked whether this ball goes further than the one he was using: “No, I hit very similar, yeah. It's much more -- the driver is kind of the easiest thing to deal with, I feel like. For me to get it where it needed to be, I had to just add a little bit of spin, and it kind of comes out at a perfectly playable range. “For me, the biggest thing, like I said, is the irons. This ball is easier to control with the irons. It doesn't spin as much, and it just allows me to be better with my distance control just because it's more consistent.” The golf ball rollback has been a hugely controversial subject but Cameron Young is currently using one that’s compliant and he is playing the best golf of his career. This gives the best idea yet on what impact, or lack of it, the new rules will actually have on the sport. PGA Championship
2:43

Cameron Young is playing with a golf ball that would allegedly be compliant with the new roll back rules that will come into effect in a few years time. He was asked about it ahead of the PGA Championship and he says every player in the game is sacrificing distance for control, and he put it in play at the Wyndham last year which he won. “I think I put it in play the same reason that everybody else plays the ball that they play. I hit it during a ball test, one of the Titleist facilities probably close to two years ago and didn't know anything about it and just kind of say, hey, what's that one? Because I liked the flight. “Then as things progressed, I was able to test it last year at Wyndham, able to put that in play, and it's been there since. “Obviously there is no conforming list. I wasn't aware that it would have -- I suppose I read something that said it passed that test, but I wasn't aware of that until very recently. “So at no point was that a consideration. It was just really me trying to optimize my golf, and it's the ball that seems to work the best for me.” He then was asked whether he lost distance with it compared to other balls he’s tested: “Not particularly. I don't think any of us are out really here playing the ball that goes the farthest. I think you'd struggle to find a single person that's doing that. We're all sacrificing a certain amount of things that we feel are worth it, control with irons, control with wedges. For me, that's the biggest thing is being able to control spin, and this is the ball that does the best for me.” Finally he can as asked whether this ball goes further than the one he was using: “No, I hit very similar, yeah. It's much more -- the driver is kind of the easiest thing to deal with, I feel like. For me to get it where it needed to be, I had to just add a little bit of spin, and it kind of comes out at a perfectly playable range. “For me, the biggest thing, like I said, is the irons. This ball is easier to control with the irons. It doesn't spin as much, and it just allows me to be better with my distance control just because it's more consistent.” The golf ball rollback has been a hugely controversial subject but Cameron Young is currently using one that’s compliant and he is playing the best golf of his career. This gives the best idea yet on what impact, or lack of it, the new rules will actually have on the sport. PGA Championship

Flushing It

311,472 просмотров • 1 месяц назад

I’m so fucking nervous to do this And yes I know you are out of the country But I’m trying so hard and putting my best efforts forward because I really want to catch your attention And I really want you to see my heart and all the love for you I’m carrying in it and how I’m ready to open it and share it with you I’m willing to be this open & vulnerable So yes I’m going to reuse my words because this is how I feel Dear Megan TINA SNOW You are absolutely everything to me I have never wanted a chance with someone so bad I have never felt so deep for someone like I feel for you My heart has never craved to love someone so badly like it craves to love you I sometimes find myself getting so emotional when I think about you because I so badly want to gain your attention Sometimes I wish I could to take my heart out of my chest and just pour everything out for you to see how deep my thoughts and feelings really go for you I’m constantly praying about I’m constantly talking to God about it and about you I do understand that this is not an ideal way to go about saying any of this But I feel this is the only way except the DM’s which is all I have I been feeling you for a good minute but was always scared to directly say anything to you because I didn’t want to come off looking like a psychopath and I always catch a lot of negativity from people that would attack me for just being honest on how I was feeling for you But now I don’t don’t care to much about it because I’m not bothering or hurting anybody I’m only speaking to you And so I just had to speak what’s been on my heart and mind Megan I promise I can be that true love you are looking for That true love you can fully trust and find real peace and happiness in I want the job of catering to you in every way that matters Mentally, emotionally, spiritually and physically I dream of waking up with you and praying with you and for you and giving you real words of encouragement and wisdom I dream to be the warm embrace you need to hold you on those bad days That will speak joy back into your day I dream to be the one you come to when you need a listening ear and really need attention and really need to know you are being heard and seen I dream to be the one to kiss all your tears and pain away when you’re struggling mentally and emotionally To be a strong praying partner when you struggle spiritually to express yourself To be the one that gives you that extra push when you are struggling physically I want to be your safe haven when you need to just let go and be vulnerable I want to be the one holding your hand through all the good and bad times standing strong beside you and never letting my presence waver I want to give you real intimacy that’s not always on a sexual level I want to be your lover that can give your body everything it needs when you desire it You really mean so much to me Megan that I will give up everything I have just for you You will always be my top priority I will make it my daily mission to make sure you are taken care of before anything else moves I really do care about you Megan I will make a fool of myself all for you because it would be worth it to me to do knowing it all got me your attention and a chance to talk to you I’m down so bad I really just want one chance to talk to you So please my love could you come talk to me in dm I promise you won’t regret it and it won’t be a waste of your time You have me wide open Please give me chance I love you 💕 Praying to talk to you soon Thank you for listening 🥹💋
3:47

Sensitive content

I’m so fucking nervous to do this And yes I know you are out of the country But I’m trying so hard and putting my best efforts forward because I really want to catch your attention And I really want you to see my heart and all the love for you I’m carrying in it and how I’m ready to open it and share it with you I’m willing to be this open & vulnerable So yes I’m going to reuse my words because this is how I feel Dear Megan TINA SNOW You are absolutely everything to me I have never wanted a chance with someone so bad I have never felt so deep for someone like I feel for you My heart has never craved to love someone so badly like it craves to love you I sometimes find myself getting so emotional when I think about you because I so badly want to gain your attention Sometimes I wish I could to take my heart out of my chest and just pour everything out for you to see how deep my thoughts and feelings really go for you I’m constantly praying about I’m constantly talking to God about it and about you I do understand that this is not an ideal way to go about saying any of this But I feel this is the only way except the DM’s which is all I have I been feeling you for a good minute but was always scared to directly say anything to you because I didn’t want to come off looking like a psychopath and I always catch a lot of negativity from people that would attack me for just being honest on how I was feeling for you But now I don’t don’t care to much about it because I’m not bothering or hurting anybody I’m only speaking to you And so I just had to speak what’s been on my heart and mind Megan I promise I can be that true love you are looking for That true love you can fully trust and find real peace and happiness in I want the job of catering to you in every way that matters Mentally, emotionally, spiritually and physically I dream of waking up with you and praying with you and for you and giving you real words of encouragement and wisdom I dream to be the warm embrace you need to hold you on those bad days That will speak joy back into your day I dream to be the one you come to when you need a listening ear and really need attention and really need to know you are being heard and seen I dream to be the one to kiss all your tears and pain away when you’re struggling mentally and emotionally To be a strong praying partner when you struggle spiritually to express yourself To be the one that gives you that extra push when you are struggling physically I want to be your safe haven when you need to just let go and be vulnerable I want to be the one holding your hand through all the good and bad times standing strong beside you and never letting my presence waver I want to give you real intimacy that’s not always on a sexual level I want to be your lover that can give your body everything it needs when you desire it You really mean so much to me Megan that I will give up everything I have just for you You will always be my top priority I will make it my daily mission to make sure you are taken care of before anything else moves I really do care about you Megan I will make a fool of myself all for you because it would be worth it to me to do knowing it all got me your attention and a chance to talk to you I’m down so bad I really just want one chance to talk to you So please my love could you come talk to me in dm I promise you won’t regret it and it won’t be a waste of your time You have me wide open Please give me chance I love you 💕 Praying to talk to you soon Thank you for listening 🥹💋

Patrice Davis Megan's My Queen!💙💙

115,735 просмотров • 1 год назад

🦊 i finished wrapping up first my solo recently and as words from people around me started influencing me, it really stressed me out and it really started swaying my identity as a person…i was really burnt out for 3 months 🦊 i used to be someone that told people everything when i was going through a hard time like “i’m going through a tough time right now” but i don’t know when it started, but i couldn’t get myself to tell people around me anymore 👤 i wonder why? was it out of consideration for them? 🦊 that could be why…and i also felt like i needed to learn how to overcome things myself 🦊 i didn’t say anything to anyone and was going through it myself…then i thought about namjoon hyung so i went to him and asked him a lot of questions and one of the things he said to me was that he hopes i face the things that make me uncomfortable 🦊 i had conflicts with soobin and we had awkward phases but i wanted to erase all of these things one by one and i feel like there were also a lot of things that i had been misunderstanding, coming to think of it now…so i went up to soobin first and said “hey, let’s go get a drink”
1:18

🦊 i finished wrapping up first my solo recently and as words from people around me started influencing me, it really stressed me out and it really started swaying my identity as a person…i was really burnt out for 3 months 🦊 i used to be someone that told people everything when i was going through a hard time like “i’m going through a tough time right now” but i don’t know when it started, but i couldn’t get myself to tell people around me anymore 👤 i wonder why? was it out of consideration for them? 🦊 that could be why…and i also felt like i needed to learn how to overcome things myself 🦊 i didn’t say anything to anyone and was going through it myself…then i thought about namjoon hyung so i went to him and asked him a lot of questions and one of the things he said to me was that he hopes i face the things that make me uncomfortable 🦊 i had conflicts with soobin and we had awkward phases but i wanted to erase all of these things one by one and i feel like there were also a lot of things that i had been misunderstanding, coming to think of it now…so i went up to soobin first and said “hey, let’s go get a drink”

💬

1,060,407 просмотров • 2 месяцев назад

“When I think about everything you’ve accomplished over the last 10 years and the fact that when I was thinking about becoming a father, I didn’t know whether you would live long enough to have a relationship with my kids. And now here they are, almost 8, 5, and 3, and you’re the best grandmother that these kids could ever ask for. It is really an amazing thing to watch. It is one of the great blessings of becoming a father, is that I’ve been able to see these kids develop the love and the affection for you and to see it in return. And that’s just an incredible blessing.” JD Vance
0:55

“When I think about everything you’ve accomplished over the last 10 years and the fact that when I was thinking about becoming a father, I didn’t know whether you would live long enough to have a relationship with my kids. And now here they are, almost 8, 5, and 3, and you’re the best grandmother that these kids could ever ask for. It is really an amazing thing to watch. It is one of the great blessings of becoming a father, is that I’ve been able to see these kids develop the love and the affection for you and to see it in return. And that’s just an incredible blessing.” JD Vance

ZitoSalena

20,253 просмотров • 1 год назад

TLDR for those who don’t want to watch the video. (I get it) I just had to vent about the fact that I always have to fight Wrath, over and over and over again. Dudes my best friend, and it never, and I mean EVER feel good having to fight him at any circumstances… I already see the replies here, and every other discussion surrounding me… and it’s predictable… I should just adapt to the fact that I have to deal with that often, or I should stop Johning because that’s how I come across… etc… I pay attention to all of it, and there are people who say it constructively, but it comes to a point. I’m tired of having to fight him… and paying thousands of dollars having to fight my best friend overseas. Please understand my frustration.
2:07

TLDR for those who don’t want to watch the video. (I get it) I just had to vent about the fact that I always have to fight Wrath, over and over and over again. Dudes my best friend, and it never, and I mean EVER feel good having to fight him at any circumstances… I already see the replies here, and every other discussion surrounding me… and it’s predictable… I should just adapt to the fact that I have to deal with that often, or I should stop Johning because that’s how I come across… etc… I pay attention to all of it, and there are people who say it constructively, but it comes to a point. I’m tired of having to fight him… and paying thousands of dollars having to fight my best friend overseas. Please understand my frustration.

DTN 🧨| Jahzz0

119,105 просмотров • 1 месяц назад

It’s hard to believe that 3 years ago, none of this was possible. Now, it’s pretty much going to change everything. Last month, Fish Audio reached out to me to try their voice AI software. They just launched their new S1 model today, and I was curious about the state of AI and voice (and everything else), so I gave it a spin. I liked it enough that when I was asked about a partnership, I said yes. I’m free to talk about what I like and don’t like about the software, and I’m going to share with you a few voices I cloned as well as some of the workflow. It was much easier than I thought. To give you an example, here is a private (research only) voice I cloned as a test. I grabbed a clip of Rutger Hauer’s famous speech from Blade Runner and uploaded it to the voice cloner on the Fish Audio Website as a private voice (no one else can use it, as it is for research only). I didn’t think it would work. The audio sample is very short. But Fish Audio was able to clone the voice extremely well and very fast. I didn’t have to upload any more than that to produce these results. I used Grok to write the new dialog, and I added the rain and background effects and the result is pretty impressive. It only took just a few minutes once I had the audio uploaded for everything from cloning to generating multiple takes. I’ll give some tips and pointers on how to get the best results at the conclusion of this thread and show you some surprising things it can do. (con’t) #Promotion
0:37

It’s hard to believe that 3 years ago, none of this was possible. Now, it’s pretty much going to change everything. Last month, Fish Audio reached out to me to try their voice AI software. They just launched their new S1 model today, and I was curious about the state of AI and voice (and everything else), so I gave it a spin. I liked it enough that when I was asked about a partnership, I said yes. I’m free to talk about what I like and don’t like about the software, and I’m going to share with you a few voices I cloned as well as some of the workflow. It was much easier than I thought. To give you an example, here is a private (research only) voice I cloned as a test. I grabbed a clip of Rutger Hauer’s famous speech from Blade Runner and uploaded it to the voice cloner on the Fish Audio Website as a private voice (no one else can use it, as it is for research only). I didn’t think it would work. The audio sample is very short. But Fish Audio was able to clone the voice extremely well and very fast. I didn’t have to upload any more than that to produce these results. I used Grok to write the new dialog, and I added the rain and background effects and the result is pretty impressive. It only took just a few minutes once I had the audio uploaded for everything from cloning to generating multiple takes. I’ll give some tips and pointers on how to get the best results at the conclusion of this thread and show you some surprising things it can do. (con’t) #Promotion

Grummz

69,859 просмотров • 1 год назад

🔥 Battle for the top reasoning LLM intensifies! The QwQ-32B-Preview is a very good reasoning LLM. Full video of my tests here: Summary of my findings and thoughts: It was able to solve a couple of hard math problems so it looks very promising for maths. It didn’t do so well on my coding task (generating bash script). By the results reported on the LiveCodeBench it has room for improvement. One thing that’s become very clear to me is that the reasoning capabilities of these LLMs are significantly closing the gap between the open and closed-sourced models. The competition is now going to be on a different level and it's going to be focused on which model produces the most efficient, optimized, accurate, and fastest reasoning steps beyond just accurate responses. That's what developers will care about. Traditional benchmarks are not going to be good enough for this. On that note, it's getting harder to assess these models, especially the consistency, efficiency, and quality of reasoning steps. After experimenting with this model, I realized that the reasoning paths are not fully optimized and there is a lot more optimization that needs to happen before these models are used in production settings. There might be a need to build some type of native and efficient self-assessment or self-reflection capability that prevents these reasoning LLMs to go in loops or produce unnecessary lengthy sequences. I also noticed that this model, at least from the HF demo, doesn’t separate the reasoning from the response. I think that actually hurts the performance of the model. On the other hand, o1 and R1 do that really well. In addition to that, I believe the training on reasoning is hurting the performance of the LLM in other areas such as helpfulness (check the code example in the video). Something that’s necessary at the moment is validating or evaluating the quality of the reasoning chains and figuring out a better strategy to optimize them. Current methods are probably not sufficient to solve this problem but that's where innovation will comes next. I recognize that this is a first effort so kudos to the Qwen team on this release. These issues highlight the importance of transparency with reasoning LLMs. We need to know how it was trained and with exact data or optimization strategy. Understanding that will enable researchers and developers to build better intuition and improve the reasoning capabilities and components at a faster rate. There is an opportunity for someone or a company to build a truly open-reasoning LLM. The race is on! I will continue to track the state-of-the-art in reasoning LLMs and report my takes and observations here. Stay tuned for more.
2:26

🔥 Battle for the top reasoning LLM intensifies! The QwQ-32B-Preview is a very good reasoning LLM. Full video of my tests here: Summary of my findings and thoughts: It was able to solve a couple of hard math problems so it looks very promising for maths. It didn’t do so well on my coding task (generating bash script). By the results reported on the LiveCodeBench it has room for improvement. One thing that’s become very clear to me is that the reasoning capabilities of these LLMs are significantly closing the gap between the open and closed-sourced models. The competition is now going to be on a different level and it's going to be focused on which model produces the most efficient, optimized, accurate, and fastest reasoning steps beyond just accurate responses. That's what developers will care about. Traditional benchmarks are not going to be good enough for this. On that note, it's getting harder to assess these models, especially the consistency, efficiency, and quality of reasoning steps. After experimenting with this model, I realized that the reasoning paths are not fully optimized and there is a lot more optimization that needs to happen before these models are used in production settings. There might be a need to build some type of native and efficient self-assessment or self-reflection capability that prevents these reasoning LLMs to go in loops or produce unnecessary lengthy sequences. I also noticed that this model, at least from the HF demo, doesn’t separate the reasoning from the response. I think that actually hurts the performance of the model. On the other hand, o1 and R1 do that really well. In addition to that, I believe the training on reasoning is hurting the performance of the LLM in other areas such as helpfulness (check the code example in the video). Something that’s necessary at the moment is validating or evaluating the quality of the reasoning chains and figuring out a better strategy to optimize them. Current methods are probably not sufficient to solve this problem but that's where innovation will comes next. I recognize that this is a first effort so kudos to the Qwen team on this release. These issues highlight the importance of transparency with reasoning LLMs. We need to know how it was trained and with exact data or optimization strategy. Understanding that will enable researchers and developers to build better intuition and improve the reasoning capabilities and components at a faster rate. There is an opportunity for someone or a company to build a truly open-reasoning LLM. The race is on! I will continue to track the state-of-the-art in reasoning LLMs and report my takes and observations here. Stay tuned for more.

elvis

14,740 просмотров • 1 год назад

I connected my WHOOP data to to use it as my health tracker. Yesterday, I asked it to generate a UI for all my data... ...and it generated a complete SaaS app now that connects with WHOOP and (soon) Apple Health 🤯 I only talked to it through telegram. Didn't even look at the code 😅
1:13

I connected my WHOOP data to to use it as my health tracker. Yesterday, I asked it to generate a UI for all my data... ...and it generated a complete SaaS app now that connects with WHOOP and (soon) Apple Health 🤯 I only talked to it through telegram. Didn't even look at the code 😅

Bhanu Teja P

47,668 просмотров • 4 месяцев назад