subtitlecat.com

All language subtitles for 02 - Agent AI reasoning approaches

Afrikaans

Akan

Albanian

Amharic

Arabic

Armenian

Azerbaijani

Basque

Belarusian

Bemba

Bengali

Bihari

Bosnian

Breton

Bulgarian

Cambodian

Catalan

Cebuano

Cherokee

Chichewa

Chinese (Simplified)

Chinese (Traditional)

Corsican

Croatian

Czech

Danish

Dutch

English

Esperanto

Estonian

Ewe

Faroese

Filipino

Finnish

French

Frisian

Galician

Georgian

German

Greek

Guarani

Gujarati

Haitian Creole

Hausa

Hawaiian

Hebrew

Hindi

Hmong

Hungarian

Icelandic

Igbo

Indonesian

Interlingua

Irish

Italian

Japanese

Javanese

Kannada

Kazakh

Kinyarwanda

Kirundi

Kongo

Korean

Krio (Sierra Leone)

Kurdish

Kurdish (Soranî)

Kyrgyz

Laothian

Latin

Latvian

Lingala

Lithuanian

Lozi

Luganda

Luo

Luxembourgish

Macedonian

Malagasy

Malay

Malayalam

Maltese

Maori

Marathi

Mauritian Creole

Moldavian

Mongolian

Myanmar (Burmese)

Montenegrin

Nepali

Nigerian Pidgin

Northern Sotho

Norwegian

Norwegian (Nynorsk)

Occitan

Oriya

Oromo

Pashto

Persian

Polish

Portuguese (Brazil) Download

Portuguese (Portugal)

Punjabi

Quechua

Romanian

Romansh

Runyakitara

Russian

Samoan

Scots Gaelic

Serbian

Serbo-Croatian

Sesotho

Setswana

Seychellois Creole

Shona

Sindhi

Sinhalese

Slovak

Slovenian

Somali

Spanish

Spanish (Latin American)

Sundanese

Swahili

Swedish

Tajik

Tamil

Tatar

Telugu

Thai

Tigrinya

Tonga

Tshiluba

Tumbuka

Turkish

Turkmen

Twi

Uighur

Ukrainian

Urdu

Uzbek

Vietnamese

Welsh

Wolof

Xhosa

Yiddish

Yoruba

Zulu

Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated: 1 00:00:00,005 --> 00:00:01,005 - [Instructor] We have learned 2 00:00:01,005 --> 00:00:04,004 that the reasoning power of large language models 3 00:00:04,004 --> 00:00:07,001 is the superpower of agent AI. 4 00:00:07,001 --> 00:00:09,002 This is an evolving field. 5 00:00:09,002 --> 00:00:14,004 Let us learn three basic approaches to reasoning. 6 00:00:14,004 --> 00:00:17,009 Remember, we can ask LLMs to chat with us 7 00:00:17,009 --> 00:00:20,007 or generate anything by prompting. 8 00:00:20,007 --> 00:00:24,001 Using a prompt with the LLM and automating this 9 00:00:24,001 --> 00:00:27,000 is a prompt-based approach. 10 00:00:27,000 --> 00:00:29,000 One of the prompt-based approaches 11 00:00:29,000 --> 00:00:32,006 is to create a set of predetermined prompts in the backend 12 00:00:32,006 --> 00:00:35,004 and let this talk to a LLM. 13 00:00:35,004 --> 00:00:38,001 We will learn some no-code agent AI tools 14 00:00:38,001 --> 00:00:41,007 that are built using predetermined prompts in the backend. 15 00:00:41,007 --> 00:00:45,008 We will even build an agent AI using one of these tools. 16 00:00:45,008 --> 00:00:47,007 Another prompt-based approach 17 00:00:47,007 --> 00:00:51,003 is to do a chain-of-thought prompting at every step 18 00:00:51,003 --> 00:00:55,000 of the step-by-step action plan by the agent AI. 19 00:00:55,000 --> 00:00:57,005 Another approach is called ReAct. 20 00:00:57,005 --> 00:01:01,004 ReAct approach means that the agent AI reasons 21 00:01:01,004 --> 00:01:03,002 and updates its context, 22 00:01:03,002 --> 00:01:04,006 and then makes a plan, 23 00:01:04,006 --> 00:01:08,008 and then takes action to solve the problem step by step. 24 00:01:08,008 --> 00:01:11,005 Contrary to that is ReWOO approach. 25 00:01:11,005 --> 00:01:13,003 With ReWOO approach, 26 00:01:13,003 --> 00:01:16,003 the agent makes a plan upfront, 27 00:01:16,003 --> 00:01:20,000 and then takes action to solve the problem step by step. 28 00:01:20,000 --> 00:01:22,002 Now, you have learned three approaches 29 00:01:22,002 --> 00:01:25,000 to building reasoning in agent AI. 2252