Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

LlamaCoder just got a lot better with "high quality" mode! It uses two chained LLM calls (1st call to make a plan, 2nd call to code) to create much better apps.

nutlope's profile picture

Hassan

99,468 subscribers

39,440 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

12 Yorum

Hassan profil fotoğrafı
Hassan1 yıl önce

This is the first of many improvements I'm making! If you want to see the PR including the prompts I used for this new coding agent, take a look here:

Reown profil fotoğrafı
Reown1 yıl önce

AppKit is the full-stack toolkit to build onchain app UX 🪄 ✅ Social, Email, and Wallet Login ✅ Embedded Wallets ✅ Crypto Swaps ✅ On-ramp Integrate with just 20 lines of code across 10+ languages for all EVM chains and Solana. Onboard millions of users for free today.

AK profil fotoğrafı
AK1 yıl önce

nice, also try out gemini-2.0-flash-thinking for making apps here in a similar way:

Hassan profil fotoğrafı
Hassan1 yıl önce

nice, does pretty well!

Tiger Abrodi profil fotoğrafı
Tiger Abrodi1 yıl önce

Reminds me a bit how perplexity works?

Hassan profil fotoğrafı
Hassan1 yıl önce

Directionally yes! I suspect Perplexity is doing a lot more than 2 calls in the background. The secret sauce to these LLMs is breaking down the problem and doing a lot of LLM calls, then aggregating them :)

SimpleCove profil fotoğrafı
SimpleCove1 yıl önce

You guys are killing it! I just discovered your services yesterday and will be reaching out for a call to discuss a few questions I have about inference scaling for multiple customers.

Hassan profil fotoğrafı
Hassan1 yıl önce

Thank you, great to hear!

Jon Kurtis ⚡ profil fotoğrafı
Jon Kurtis ⚡1 yıl önce

When deepseek v3?

Hassan profil fotoğrafı
Hassan1 yıl önce

Soon! Working on it

CoinCollector profil fotoğrafı
CoinCollector1 yıl önce

Tried it, really helps the quality, good job

Hassan profil fotoğrafı
Hassan1 yıl önce

Great to hear!

Benzer Videolar

This leaked 2nd Ye verse on Back To Me is wayyyy better than the one we got. Someone has to use AI to make a High Quality version of it ASAP⁉️⁉️
1:09

This leaked 2nd Ye verse on Back To Me is wayyyy better than the one we got. Someone has to use AI to make a High Quality version of it ASAP⁉️⁉️

yzystatus

102,984 görüntüleme • 2 yıl önce

Plan Mode is the most slept-on feature in Claude Code – and we just made it a lot better. It dramatically improves your one-shot success rate. Fewer iterations, less hand-holding, better final results. Shift + Tab twice to try it.
0:31

Plan Mode is the most slept-on feature in Claude Code – and we just made it a lot better. It dramatically improves your one-shot success rate. Fewer iterations, less hand-holding, better final results. Shift + Tab twice to try it.

Sid

168,716 görüntüleme • 9 ay önce

Im going to have a hard time being convinced there are a whole lot more 2nd basemen who are better than nico hoerner. ur really going to have to make a compelling argument theres much better out there. talk abt a guy who is just taking it to another level
0:31

Im going to have a hard time being convinced there are a whole lot more 2nd basemen who are better than nico hoerner. ur really going to have to make a compelling argument theres much better out there. talk abt a guy who is just taking it to another level

DOM

75,894 görüntüleme • 3 yıl önce

Paul Reed on last play of regulation: "He got tripped. They didn’t call it. Referees don’t call a lot of calls, so it’s not like that’s the make-or-break call to win or lose the game. “It was just another play that the refs missed. They miss a lot of calls, so it’s nothing new."
0:26

Paul Reed on last play of regulation: "He got tripped. They didn’t call it. Referees don’t call a lot of calls, so it’s not like that’s the make-or-break call to win or lose the game. “It was just another play that the refs missed. They miss a lot of calls, so it’s nothing new."

97.1 The Ticket:

80,631 görüntüleme • 3 ay önce

Better Call Saul is a masterclass in storytelling—flawless from beginning to end, with zero drop in quality.
1:58

Better Call Saul is a masterclass in storytelling—flawless from beginning to end, with zero drop in quality.

cinesthetic.

692,036 görüntüleme • 1 yıl önce

GitHub Copilot cloud agent just got a lot more flexible ✨ You can now it use it to research, plan, and make code changes without needing to open a pull request first.
0:49

GitHub Copilot cloud agent just got a lot more flexible ✨ You can now it use it to research, plan, and make code changes without needing to open a pull request first.

GitHub

44,977 görüntüleme • 5 ay önce

We just shipped a demo of how to flip the model-cost equation: Plan with the smartest model. Implement with a cheap one. Review with three in parallel. 3.5x cheaper. Better code quality.
3:29

We just shipped a demo of how to flip the model-cost equation: Plan with the smartest model. Implement with a cheap one. Review with three in parallel. 3.5x cheaper. Better code quality.

zencoderai

13,101,118 görüntüleme • 4 ay önce

Muslims react to Christian bagpipes. I think it sounds MUCH BETTER than the call to prayer!
1:04

Muslims react to Christian bagpipes. I think it sounds MUCH BETTER than the call to prayer!

AmericanPapaBear™

67,974 görüntüleme • 6 ay önce

"When I got that call to be a part of this organization, I was just thrilled." Two-way player CJ Huntley said he had two workouts with Phoenix Suns. "Second workout was even better." #Suns
2:02

"When I got that call to be a part of this organization, I was just thrilled." Two-way player CJ Huntley said he had two workouts with Phoenix Suns. "Second workout was even better." #Suns

Duane Rankin

10,672 görüntüleme • 1 yıl önce

“We like to call it science at digital speed.” 🚀 Our CEO @DemisHassabis speaks to Bloomberg TV about how AI could help medical researchers make fast breakthroughs, potentially create better quality jobs and lead to society-changing progress. ⬇️
0:51

“We like to call it science at digital speed.” 🚀 Our CEO @DemisHassabis speaks to Bloomberg TV about how AI could help medical researchers make fast breakthroughs, potentially create better quality jobs and lead to society-changing progress. ⬇️

Google DeepMind

85,850 görüntüleme • 3 yıl önce

Texas A&M HC Mike Elko - Building a Defensive Call Sheet - "We're probably really limited on 1st/2nd down. We really force ourselves to come down to some simplified concept how we're trying to attack them on 1st/2nd down." 1st/2nd Down = 6 Core Calls - Split Safety - Single High - 2 or 3 ways to Fire Zone/Man Pressure - Shot play defense - "We're going to limit ourselves to 6 core calls on 1st/2nd down because we want to be a little more expansive on 3rd down (10-14 calls)." - "Because we've become very situationally branded, to have it be effective we've forced ourselves to shrink what we do on 1st/2nd down." - "Everything we do should have a purpose for the offense we're playing."
3:17

Texas A&M HC Mike Elko - Building a Defensive Call Sheet - "We're probably really limited on 1st/2nd down. We really force ourselves to come down to some simplified concept how we're trying to attack them on 1st/2nd down." 1st/2nd Down = 6 Core Calls - Split Safety - Single High - 2 or 3 ways to Fire Zone/Man Pressure - Shot play defense - "We're going to limit ourselves to 6 core calls on 1st/2nd down because we want to be a little more expansive on 3rd down (10-14 calls)." - "Because we've become very situationally branded, to have it be effective we've forced ourselves to shrink what we do on 1st/2nd down." - "Everything we do should have a purpose for the offense we're playing."

James Light

38,337 görüntüleme • 2 ay önce

Texas A&M HC Mike Elko - Building a Defensive Call Sheet - "We're probably really limited on 1st/2nd down. We really force ourselves to come down to some simplified concept how we're trying to attack them on 1st/2nd down." 1st/2nd Down = 6 Core Calls - Split Safety - Single High - 2 or 3 ways to Fire Zone/Man Pressure - Shot play defense - "We're going to limit ourselves to 6 core calls on 1st/2nd down because we want to be a little more expansive on 3rd down (10-14 calls)." - "Because we've become very situationally branded, to have it be effective we've forced ourselves to shrink what we do on 1st/2nd down." - "Everything we do should have a purpose for the offense we're playing."
3:17

Texas A&M HC Mike Elko - Building a Defensive Call Sheet - "We're probably really limited on 1st/2nd down. We really force ourselves to come down to some simplified concept how we're trying to attack them on 1st/2nd down." 1st/2nd Down = 6 Core Calls - Split Safety - Single High - 2 or 3 ways to Fire Zone/Man Pressure - Shot play defense - "We're going to limit ourselves to 6 core calls on 1st/2nd down because we want to be a little more expansive on 3rd down (10-14 calls)." - "Because we've become very situationally branded, to have it be effective we've forced ourselves to shrink what we do on 1st/2nd down." - "Everything we do should have a purpose for the offense we're playing."

James Light

63,672 görüntüleme • 7 ay önce

Aydan on why Apex Legends is a better game than Call of Duty Warzone: “it’s just a better game.. coming from a guy who played this(Warzone) for 5 years.. i used to think it’s slow, but that’s what a BR should be.. the quality of the fights are much better..” 🗣️
1:46

Aydan on why Apex Legends is a better game than Call of Duty Warzone: “it’s just a better game.. coming from a guy who played this(Warzone) for 5 years.. i used to think it’s slow, but that’s what a BR should be.. the quality of the fights are much better..” 🗣️

jake newtron 🚀

591,549 görüntüleme • 7 ay önce

i'm a little sick of chatgpt giving me obviously broken code i've found a "micro agent" approach to LLM code generation can work much better the LLM first generates a *test*, and then enters a loop where it generates and iterates on the code until the tests pass source below
0:23

i'm a little sick of chatgpt giving me obviously broken code i've found a "micro agent" approach to LLM code generation can work much better the LLM first generates a *test*, and then enters a loop where it generates and iterates on the code until the tests pass source below

Steve (Builder.io)

544,212 görüntüleme • 2 yıl önce

Trump: We didn't make money. We had deficits with everybody and I call that a loss. A lot of people say oh, it doesn't matter, it does matter a lot. To me I call it a loss.
0:24

Trump: We didn't make money. We had deficits with everybody and I call that a loss. A lot of people say oh, it doesn't matter, it does matter a lot. To me I call it a loss.

Acyn

25,277 görüntüleme • 7 ay önce

Lets build `Auto-RAG` where we let the LLM pull the data it needs from different sources. 🔎 The user asks a question. 🤔 LLM decides whether to search its knowledge, memory, internet or make an API call. ✍️ LLM answers with the context. Code:
8:45

Lets build `Auto-RAG` where we let the LLM pull the data it needs from different sources. 🔎 The user asks a question. 🤔 LLM decides whether to search its knowledge, memory, internet or make an API call. ✍️ LLM answers with the context. Code:

Ashpreet Bedi

174,580 görüntüleme • 2 yıl önce

I'm reiterating - I think a better interface for LLMs on desktop is an interactive notebook, not chat. I'm trying to build a better intuition for PCA and strongly feel an interactive notebook where I'm chatting with LLM + also modifying code/plotting figures is a much better interaction. Bonus points if you make notebook cells branchable (so if you get an error, you can ask LLM to fix it without adding that rotten context to the main branch of learning). Please steal this idea. Make an AI-powered, interactive, branching notebook.
0:21

I'm reiterating - I think a better interface for LLMs on desktop is an interactive notebook, not chat. I'm trying to build a better intuition for PCA and strongly feel an interactive notebook where I'm chatting with LLM + also modifying code/plotting figures is a much better interaction. Bonus points if you make notebook cells branchable (so if you get an error, you can ask LLM to fix it without adding that rotten context to the main branch of learning). Please steal this idea. Make an AI-powered, interactive, branching notebook.

Paras Chopra

58,232 görüntüleme • 1 yıl önce

Yeah… Niggas knew better than to even call his name out for a Verzuz… 🥵🥵🥵🥵 ‘Heim ain’t the one or the two to be flexed with! 😡🔥🔥🔥 His debut album got so much heat it’s ridiculous!
1:30

Yeah… Niggas knew better than to even call his name out for a Verzuz… 🥵🥵🥵🥵 ‘Heim ain’t the one or the two to be flexed with! 😡🔥🔥🔥 His debut album got so much heat it’s ridiculous!

JustJamie21

28,532 görüntüleme • 27 gün önce