lukkiddd 🧮
@lukkidddBuilder at https://t.co/R9G3v1DQo3, X about LLM/Data/Software, mostly in Thai
Similar User
@JaesSmile
@joey_pakpoom
@latifou_yaya
@niki_avramov
@Kaanwela
@e_square_io
@iBookbiG
@aiaiCougar
@nongnamhom1
@Satoung
@MDRG_Inc
@tulathorn
@kirapao
@nn_namenode
😂 love the vibe Great talk about LLM Evaluation youtu.be/IIL2tE4n1Q0?si…
Oh wow!
Re: CaseText & eval driven development (EDD) for AI. EDD was always front and center pre-generative AI. Ex: nobody cares about your fraud/churn/forecasting model if it’s not accurate. This is missing with most LLM products. But the best practices and playbooks are there in…
Scaling LLM apps - OpenAI break out session Going from 1K > 10M users Making apps better, faster, and cheaper Accuracy * Start by optimizing for accuracy, use the most intelligent model you have * Build evals > Set Target > Optimize * People skip the "set target" but then it's…
Excited to share our latest research on Contextual Retrieval - a technique that reduces incorrect chunk retrieval rates by up to 67%. When combined with prompt caching, it may be one of the best techniques there is for implementing retrieval in RAG apps. Let me explain:
If you remember our Applied LLMs course, you'll love this. Today, we are making all these resources available for free to everyone! 📚 We did extra work to add learning tracks, resources, and notes to each lesson to maximize your learning. Link in next tweet
ช่วงตลอดเดือน July, August, September ใน GenAI Engineer Thailand discord เรามี knowledge sharing session (ภาษาไทย) กันตลอดนะค้าบ ใครสนใจฟัง ตามมาได้นะคร้าบ ของเดือนนี้มี คืนนี้ July 16th : 8-9pm วันศุกร์ July 19th: 8-9pm วันเสาร์หน้า July 27th: 8-9pm Discord Invite:…
โอ้โหว ว้าวซ่า จาก Gen3 runway มาเจอ video-to-audio จาก deepmind อีก
We're sharing progress on our video-to-audio (V2A) generative technology. 🎥 It can add sound to silent clips that match the acoustics of the scene, accompany on-screen action, and more. Here are 4 examples - turn your sound on. 🧵🔊 dpmd.ai/v2a
Runway Gen-3 ล้ำเกิ๊น
Introducing Gen-3 Alpha: Runway’s new base model for video generation. Gen-3 Alpha can create highly detailed videos with complex scene changes, a wide range of cinematic choices, and detailed art directions. runwayml.com/gen-3-alpha (1/10)
Deploy self host LLM อาจจะไม่ได้ถูกกว่า บทความนี้ลองคำนวนให้ดูฮะ ว่ามันมี cost อะไรที่แฝงอยู่บ้าง เทียบกับ Managed Service แต่ก็เช่นกันนะคับใช้ Managed Service ก็อาจจะมี hidden cost เหมือนกัน 🤔 philschmid.de/cost-generativ…
ล่าสุดพี่ ปาโก้ จาก PALO IT มาแชร์เรื่อง Introduction to @ollama ใครสนใจจิ้มไปอ่านสรุปกันได้ฮะ txt.lukkiddd.com/introduction-t…
เห็นพี่ @fony_lew เล่นแล้วอยากลองบ้าง (ใช้ twitter ไม่เป็น) @lukkiddd spends 856% more time coding than tweeting shiptalkers.dev/compare?name=l…
พรุ่งนี้ กลุ่ม GenAI Engineer Thailand เรามี knowledge sharing กันนะฮะ เรื่อง PDF-to-Text โดย @napatswift ตามมาจอยกันได้
งาน microsoft พูดเรื่อง LLMOps งาน AWS พูดเรื่อง GenAI development (RAG, vector database) งาน Google Cloud พูดเรื่อง Responsible AI
Quote ให้ครบ
LLMs are useful, but they are an off ramp on the road to human-level AI. If you are a PhD student, don't work on LLMs. Try to discover methods that would lift the limitations of LLMs.
love the product, but it wont work well for Thai Language, is there any we can help improve?
RAG over Excel Files 📊 A key blocker for building functional RAG over your excel spreadsheets is the data representation - if the data isn’t parsed well, this leads to the garbage in/garbage out problem. We’ve launched a huge update for LlamaParse to let you parse very complex…
interesting! reduce from $40 (1,470 THB) to $8 (~300THB)
Answering 93% of customer support questions autonomously Reducing the average time to resolve customer issues by 60% Improved customer service representatives’ productivity by 2X, providing more time for human interactions and spending less time finding the correct response for…
This is a good recap 🙌
With the rising popularity of RAG pipelines, you need an evaluation pipeline to measure the quality of your retrieval component. In my new blog, I give an overview of the most popular metrics in information retrieval systems. 🔗 Read more: weaviate.io/blog/retrieval…
United States Trends
- 1. Chargers 56,4 B posts
- 2. Dayton 4.284 posts
- 3. Quentin Johnston 5.929 posts
- 4. Ravens 68 B posts
- 5. Kerr 7.572 posts
- 6. Drake 354 B posts
- 7. #WWERaw 67,8 B posts
- 8. Canada 413 B posts
- 9. Lamar 181 B posts
- 10. Seth Trimble N/A
- 11. Herbert 19 B posts
- 12. Cadeau 9.372 posts
- 13. Kofi 16,3 B posts
- 14. Jalen Washington N/A
- 15. #BALvsLAC 9.346 posts
- 16. Maui 15,3 B posts
- 17. Derrick Henry 9.320 posts
- 18. Nets 14,4 B posts
- 19. Cory Alexander N/A
- 20. Ladd 4.853 posts
Who to follow
-
zamiled
@JaesSmile -
Joe Pakpoom
@joey_pakpoom -
Latifou Yaya
@latifou_yaya -
Nikolay Avramov
@niki_avramov -
Love, Kaan 🌎
@Kaanwela -
e-square.io
@e_square_io -
หนังสือ(โ -๊ )เล่มใหญ่
@iBookbiG -
คูก้า✨ still alive
@aiaiCougar -
นอหอ
@nongnamhom1 -
||| ＱＵＩＮＮ Σ
@Satoung -
MDRG
@MDRG_Inc -
Tulathorn S. ||| 🇹🇭
@tulathorn -
𝙋𝘼𝙊𝘾𝙊𝙈 𝕏 🏳️🌈
@kirapao -
NameNode
@nn_namenode
Something went wrong.
Something went wrong.