Loading video...

Video Failed to Load

Go Home

AI research is getting f...cking illegal 15 GitHub projects for turning a question into sources, evidence, citations, and a finished report 01 GPT Researcher ▸ → recursive deep research 02 STORM ▸ SEARCH DEEPER 03 Perplexica ▸ 04 Open Deep Research ▸ 05 DeerFlow ▸ READ THE WEB 06...

Lummox_eth's profile picture

Lummox

7,234 subscribers

33,660 views • 1 day ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

10 Comments

Gipp 🦅's profile picture
Gipp 🦅1 day ago

I would also like to be a researcher

Karpacho's profile picture
Karpacho1 day ago

Will check all the repos right now

Mura's profile picture
Mura1 day ago

that's kinda helpfull

monokern's profile picture
monokern1 day ago

good share bro

Grootex's profile picture
Grootex1 day ago

Makes sense to use every repos from the post New banger

Dekos's profile picture
Dekos1 day ago

I should check this out.

beamnxw ./'s profile picture
beamnxw ./1 day ago

15 gems

BPP | Crypto Key Media |'s profile picture
BPP | Crypto Key Media |1 day ago

nah gpt researcher and storm are already my go to picks fr

magsimich's profile picture
magsimich22 hours ago

That research stack is worth saving

ALEXYZ's profile picture
ALEXYZ1 day ago

source backed research at your fingertips

Related Videos

this is pure f*cking treasure 15 GitHub projects with 1.21M combined stars that can form a real agent stack specs. memory. web data. documents. context. sandboxes. monitoring. video 01 hermes-agent ▸ 02 OpenSpec ▸ 03 caveman ▸ 04 Scrapling ▸ 05 Docling ▸ 06 PageIndex ▸ 07 mem0 ▸ 08 headroom ▸ 09 Daytona ▸ 10 TrendRadar ▸ 11 Fabric ▸ 12 spec-kit ▸ 13 hyperframes ▸ 14 OpenMontage ▸ 15 AI Engineering Hub ▸ the loop: define the job → collect the evidence → parse the docs → save the memory → compress the context → run the code safely → watch what changes → ship the output the entire stack is open source save this to build your own business with the help of an AI employee ⭣
0:24

this is pure f*cking treasure 15 GitHub projects with 1.21M combined stars that can form a real agent stack specs. memory. web data. documents. context. sandboxes. monitoring. video 01 hermes-agent ▸ 02 OpenSpec ▸ 03 caveman ▸ 04 Scrapling ▸ 05 Docling ▸ 06 PageIndex ▸ 07 mem0 ▸ 08 headroom ▸ 09 Daytona ▸ 10 TrendRadar ▸ 11 Fabric ▸ 12 spec-kit ▸ 13 hyperframes ▸ 14 OpenMontage ▸ 15 AI Engineering Hub ▸ the loop: define the job → collect the evidence → parse the docs → save the memory → compress the context → run the code safely → watch what changes → ship the output the entire stack is open source save this to build your own business with the help of an AI employee ⭣

beamnxw ./

151,844 views • 12 days ago

Competitor tracking is one of those tasks that's easy to skip because it's slow. I tested automating it with Qoder. The goal was simple: every week, research what changed across competitors and produce a report I could actually review. Qoder planned the research, checked public updates, ran tasks in parallel, and compiled everything into a structured Markdown report with sources and caveats where evidence was limited. The workflow went from manual to: schedule → research → verify → analyze → report. I also ran Qwen3.8-Flash on it, which is showing 0.0x Credits through September 30. Qoder has a 14-day Pro trial with 300 Credits. Sign up before downloading through this link and you get another 300 — 600 Credits total: The interesting part isn't just the research. It's having an AI agent turn a recurring task into a finished artifact automatically.
0:30

Competitor tracking is one of those tasks that's easy to skip because it's slow. I tested automating it with Qoder. The goal was simple: every week, research what changed across competitors and produce a report I could actually review. Qoder planned the research, checked public updates, ran tasks in parallel, and compiled everything into a structured Markdown report with sources and caveats where evidence was limited. The workflow went from manual to: schedule → research → verify → analyze → report. I also ran Qwen3.8-Flash on it, which is showing 0.0x Credits through September 30. Qoder has a 14-day Pro trial with 300 Credits. Sign up before downloading through this link and you get another 300 — 600 Credits total: The interesting part isn't just the research. It's having an AI agent turn a recurring task into a finished artifact automatically.

Shruti

142,126 views • 6 days ago

this is pure f*cking treasure 15 GitHub projects with 852K combined stars that build a real agent stack research, remember, run, learn, show up in a product and get shipped 01 DeerFlow ▸ 02 RAGFlow ▸ 03 Quivr ▸ 04 MemPalace ▸ 05 Folo ▸ 06 OpenBB ▸ 07 MindsHub ▸ 08 Agno ▸ 09 Oh My OpenAgent ▸ 10 Goose ▸ 11 Continue ▸ 12 Unsloth ▸ 13 LlamaFactory ▸ 14 CopilotKit ▸ 15 Dokploy ▸ the loop: find the signal → turn it into context → keep what matters → hand the job to an agent → give it a place to run → adapt the model → put it in front of users → ship every repo here has a defined place in that loop save this to build your own business with the help of an AI employee ⭣
0:24

this is pure f*cking treasure 15 GitHub projects with 852K combined stars that build a real agent stack research, remember, run, learn, show up in a product and get shipped 01 DeerFlow ▸ 02 RAGFlow ▸ 03 Quivr ▸ 04 MemPalace ▸ 05 Folo ▸ 06 OpenBB ▸ 07 MindsHub ▸ 08 Agno ▸ 09 Oh My OpenAgent ▸ 10 Goose ▸ 11 Continue ▸ 12 Unsloth ▸ 13 LlamaFactory ▸ 14 CopilotKit ▸ 15 Dokploy ▸ the loop: find the signal → turn it into context → keep what matters → hand the job to an agent → give it a place to run → adapt the model → put it in front of users → ship every repo here has a defined place in that loop save this to build your own business with the help of an AI employee ⭣

beamnxw ./

26,555 views • 10 days ago

How GPT-5 thinks, with OpenAI VP of Research Jerry Tworek 00:00 - Intro 01:01 - What Reasoning Actually Means in AI 02:32 - Chain of Thought: Models Thinking in Words 05:25 - How Models Decide How Long to Think 07:24 - Evolution from o1 to o3 to GPT-5 11:00 - The Road to OpenAI: Growing up in Poland, Dropping out of School, Trading 20:32 - Working on Robotics and Rubik's Cube Solving 23:02 - A Day in the Life: Talking to Researchers 24:06 - How Research Priorities Are Determined 26:53 - OpenAI's Culture of Transparency 29:32 - Balancing Research with Shipping Fast 31:52 - Using OpenAI's Own Tools Daily 32:43 - Pre-Training Plus RL: The Modern AI Stack 35:10 - Reinforcement Learning 101: Training Dogs 40:17 - The Evolution of Deep Reinforcement Learning 42:09 - When GPT-4 Seemed Underwhelming at First 45:39 - How RLHF Made GPT-4 Actually Useful 48:02 - Unsupervised vs Supervised Learning 49:59 - GRPO and How DeepSeek Accelerated US Research 53:05 - What It Takes to Scale Reinforcement Learning 55:36 - Agentic AI and Long-Horizon Thinking 59:19 - Alignment as an RL Problem 1:01:11 - Winning ICPC World Finals Without Specific Training 1:05:53 - Applying RL Beyond Math and Coding 1:09:15 - The Path from Here to AGI 1:12:23 - Pure RL vs Language Models
1:16:04

How GPT-5 thinks, with OpenAI VP of Research Jerry Tworek 00:00 - Intro 01:01 - What Reasoning Actually Means in AI 02:32 - Chain of Thought: Models Thinking in Words 05:25 - How Models Decide How Long to Think 07:24 - Evolution from o1 to o3 to GPT-5 11:00 - The Road to OpenAI: Growing up in Poland, Dropping out of School, Trading 20:32 - Working on Robotics and Rubik's Cube Solving 23:02 - A Day in the Life: Talking to Researchers 24:06 - How Research Priorities Are Determined 26:53 - OpenAI's Culture of Transparency 29:32 - Balancing Research with Shipping Fast 31:52 - Using OpenAI's Own Tools Daily 32:43 - Pre-Training Plus RL: The Modern AI Stack 35:10 - Reinforcement Learning 101: Training Dogs 40:17 - The Evolution of Deep Reinforcement Learning 42:09 - When GPT-4 Seemed Underwhelming at First 45:39 - How RLHF Made GPT-4 Actually Useful 48:02 - Unsupervised vs Supervised Learning 49:59 - GRPO and How DeepSeek Accelerated US Research 53:05 - What It Takes to Scale Reinforcement Learning 55:36 - Agentic AI and Long-Horizon Thinking 59:19 - Alignment as an RL Problem 1:01:11 - Winning ICPC World Finals Without Specific Training 1:05:53 - Applying RL Beyond Math and Coding 1:09:15 - The Path from Here to AGI 1:12:23 - Pure RL vs Language Models

Matt Turck

451,229 views • 11 months ago

this is pure f*cking treasure 20 useful GitHub projects for a system that captures sources, connects ideas, remembers context, and helps agents act on it your second brain should get sharper after every session CAPTURE THE INPUT 01 Chubby Skills ▸ 02 OpenWiki ▸ 03 Agent Second Brain ▸ 04 DocMason ▸ 05 DocsAgent ▸ CONNECT THE IDEAS 06 claude-obsidian ▸ 07 SwarmVault ▸ 08 sage-wiki ▸ 09 Vault Curate ▸ 10 COG Second Brain ▸ REMEMBER WHAT MATTERS 11 Hindsight ▸ 12 memU ▸ 13 TencentDB Agent Memory ▸ 14 agentmemory ▸ 15 OpenViking ▸ PUT IT TO WORK 16 Open Second Brain ▸ 17 Second Brain Cloudflare ▸ 18 makerskills ▸ 19 Row-Bot ▸ 20 MateClaw ▸ the loop: capture the source → turn it into linked, checkable knowledge → recall the right context → act with it → write the correction back 3 builds I'd explore: creator: Chubby Skills → SwarmVault → Hindsight → makerskills researcher: DocsAgent → sage-wiki → memU → Row-Bot team: DocMason → COG Second Brain → TencentDB Agent Memory → MateClaw save this, then build a second brain for your business ⭣
0:40

this is pure f*cking treasure 20 useful GitHub projects for a system that captures sources, connects ideas, remembers context, and helps agents act on it your second brain should get sharper after every session CAPTURE THE INPUT 01 Chubby Skills ▸ 02 OpenWiki ▸ 03 Agent Second Brain ▸ 04 DocMason ▸ 05 DocsAgent ▸ CONNECT THE IDEAS 06 claude-obsidian ▸ 07 SwarmVault ▸ 08 sage-wiki ▸ 09 Vault Curate ▸ 10 COG Second Brain ▸ REMEMBER WHAT MATTERS 11 Hindsight ▸ 12 memU ▸ 13 TencentDB Agent Memory ▸ 14 agentmemory ▸ 15 OpenViking ▸ PUT IT TO WORK 16 Open Second Brain ▸ 17 Second Brain Cloudflare ▸ 18 makerskills ▸ 19 Row-Bot ▸ 20 MateClaw ▸ the loop: capture the source → turn it into linked, checkable knowledge → recall the right context → act with it → write the correction back 3 builds I'd explore: creator: Chubby Skills → SwarmVault → Hindsight → makerskills researcher: DocsAgent → sage-wiki → memU → Row-Bot team: DocMason → COG Second Brain → TencentDB Agent Memory → MateClaw save this, then build a second brain for your business ⭣

beamnxw ./

133,321 views • 3 days ago

Most AI research demos show you a polished answer. This one showed me the disagreement that happened before the answer. I gave Ling-3.0-flash Ant Ling a deliberately difficult question: Do four-day workweeks actually increase productivity, or do they simply compress the same workload into fewer days? Instead of asking for a quick summary, I asked it to coordinate five specialist roles: a scientist, a data analyst, a cross-validator, an archivist, and a research writer. Each role had a separate responsibility. The scientist defined the competing hypotheses. The analyst extracted comparable findings. The archivist tracked the sources. The writer could only use approved claims. And the cross-validator had one job: challenge anything that sounded more confident than the evidence allowed. That last role changed the result. The team reviewed 12 sources and challenged six major claims. Three claims were narrowed. One was rejected entirely. Even a widely repeated claim about a 40% productivity increase did not survive the evidence check. That is the part I wanted to see from an AI research workflow. Not just more information, but visible resistance to weak evidence. The final output included: - a direct executive answer - a structured research paper - a source and evidence table - a disagreement log - a six-slide executive deck - a quality-control summary The conclusion was also more useful than a simple yes or no: reduced working hours may maintain productivity and improve wellbeing under certain conditions, while compressing the same workload into fewer days can increase fatigue and intensity. The evidence did not support a universal productivity claim. What impressed me was not that Ling-3.0-flash generated a long response. Plenty of models can do that. It was the way the model maintained multiple roles, evidence standards, objections, citations, and deliverables across one extended workflow, while preserving uncertainty instead of smoothing it away. That makes Ling-3.0-flash especially interesting for work where execution matters as much as reasoning: research, search, coding, document processing, tool use, repeated checks, and other multi-step agent workflows. The strongest AI systems will not use the largest model for every task. They will combine deep planning with fast, cost-efficient execution. Ling-3.0-flash is built for that execution layer. Ling-3.0-flash is now available on OpenRouter and free to use through August 3, 2026. Try it in your coding, search, research, and tool-use workflows. Then show us what you build. Try Ling-3.0-flash: Documentation:
0:33

Most AI research demos show you a polished answer. This one showed me the disagreement that happened before the answer. I gave Ling-3.0-flash Ant Ling a deliberately difficult question: Do four-day workweeks actually increase productivity, or do they simply compress the same workload into fewer days? Instead of asking for a quick summary, I asked it to coordinate five specialist roles: a scientist, a data analyst, a cross-validator, an archivist, and a research writer. Each role had a separate responsibility. The scientist defined the competing hypotheses. The analyst extracted comparable findings. The archivist tracked the sources. The writer could only use approved claims. And the cross-validator had one job: challenge anything that sounded more confident than the evidence allowed. That last role changed the result. The team reviewed 12 sources and challenged six major claims. Three claims were narrowed. One was rejected entirely. Even a widely repeated claim about a 40% productivity increase did not survive the evidence check. That is the part I wanted to see from an AI research workflow. Not just more information, but visible resistance to weak evidence. The final output included: - a direct executive answer - a structured research paper - a source and evidence table - a disagreement log - a six-slide executive deck - a quality-control summary The conclusion was also more useful than a simple yes or no: reduced working hours may maintain productivity and improve wellbeing under certain conditions, while compressing the same workload into fewer days can increase fatigue and intensity. The evidence did not support a universal productivity claim. What impressed me was not that Ling-3.0-flash generated a long response. Plenty of models can do that. It was the way the model maintained multiple roles, evidence standards, objections, citations, and deliverables across one extended workflow, while preserving uncertainty instead of smoothing it away. That makes Ling-3.0-flash especially interesting for work where execution matters as much as reasoning: research, search, coding, document processing, tool use, repeated checks, and other multi-step agent workflows. The strongest AI systems will not use the largest model for every task. They will combine deep planning with fast, cost-efficient execution. Ling-3.0-flash is built for that execution layer. Ling-3.0-flash is now available on OpenRouter and free to use through August 3, 2026. Try it in your coding, search, research, and tool-use workflows. Then show us what you build. Try Ling-3.0-flash: Documentation:

Rachel🥥

73,264 views • 2 months ago

🚨 THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read what’s actually on the page, that access is almost useless. We looked at Firecrawl as the web layer for AI agents and the numbers are hard to ignore. The setup is simple: Give it a URL, search query, or website. Firecrawl handles the ugly part — crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: → 173,000+ GitHub stars → Search, scrape and interact with the web at scale → Supports web pages, PDFs, DOCX and other content → Structured data extraction for AI workflows → MCP support for connecting it directly to AI agents The workflow looks like this: Search → Scrape → Crawl → Extract → Feed the agent Three things stand out: 1. Scraping becomes an infrastructure layer Instead of maintaining your own pile of HTTP clients, parsers, browser automation and retry logic, you can treat web access as an API. 2. Agents get more than raw HTML The goal isn't just downloading a webpage. It's turning messy web content into clean context that an LLM can reason over. 3. The same layer works across different agent workflows Research agents. RAG pipelines. AI search. Competitive intelligence. Web-data extraction. The interesting shift: AI agents don't just need better models. They need better access to the information those models are supposed to reason about. Firecrawl is building that layer. Save this repo.
0:28

🚨 THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read what’s actually on the page, that access is almost useless. We looked at Firecrawl as the web layer for AI agents and the numbers are hard to ignore. The setup is simple: Give it a URL, search query, or website. Firecrawl handles the ugly part — crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: → 173,000+ GitHub stars → Search, scrape and interact with the web at scale → Supports web pages, PDFs, DOCX and other content → Structured data extraction for AI workflows → MCP support for connecting it directly to AI agents The workflow looks like this: Search → Scrape → Crawl → Extract → Feed the agent Three things stand out: 1. Scraping becomes an infrastructure layer Instead of maintaining your own pile of HTTP clients, parsers, browser automation and retry logic, you can treat web access as an API. 2. Agents get more than raw HTML The goal isn't just downloading a webpage. It's turning messy web content into clean context that an LLM can reason over. 3. The same layer works across different agent workflows Research agents. RAG pipelines. AI search. Competitive intelligence. Web-data extraction. The interesting shift: AI agents don't just need better models. They need better access to the information those models are supposed to reason about. Firecrawl is building that layer. Save this repo.

Vikas gupta

18,053 views • 24 days ago

Use this FREE tool to generate the first draft of ANY type of literature review. Meet AnswerThis — a tool that makes literature review faster and easier. Here’s how it works. 1. Visit and log in. 2. Select the 𝐿𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑅𝑒𝑣𝑖𝑒𝑤 option from the menu. 3. From the prompt helper, select 𝑊𝑟𝑖𝑡𝑒 𝑎 𝑙𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑟𝑒𝑣𝑖𝑒𝑤 𝑜𝑛. 4. Enter your research topic in the blank text field ➝ For example, Vulnerabilities in Big Data Systems 5. Click 𝐶𝑟𝑒𝑎𝑡𝑒 to generate the initial search prompt. 6. Press Enter to see research filter options. 7. Choose your response type based on your needs. ➝ Structured Literature Review: Citation-rich and detailed. ➝ Dynamic Research Assistant: To explore research gaps. ➝ AI Only: Fast, but unreliable with no citations. 8. Set the minimum number of citations for the review. ➝ Choose at least 10 for comprehensive results. 9. Decide whether to enable 𝑇𝑢𝑟𝑏𝑜 𝑀𝑜𝑑𝑒 for faster results. ➝ Disabling it gives you more comprehensive answers. 10. Select the sources for search results. ➝ Choose both web and databases for thorough results. 11. Specify the date range to get recent papers. 12. Enable 𝑑𝑜𝑢𝑏𝑙𝑒-𝑐ℎ𝑒𝑐𝑘 𝑐𝑖𝑡𝑎𝑡𝑖𝑜𝑛𝑠 for accurate results. 13. Once filters are set, click 𝑆𝑢𝑏𝑚𝑖𝑡 𝑆𝑒𝑎𝑟𝑐ℎ to proceed. 14. After a while, your literature review will be generated. ➝ Sources and citations will be listed on the right. 15. Review the results and assess the paper sources carefully. 16. Add relevant papers to your library for easy access later. 17. Export citations in formats like BibTeX or CSV as needed. 18. You can also download the review as a Word or PDF file. Treat this literature review as an initial draft. Refine it and build your review on the top of it. Ready to make literature review effortless? Try AnswerThis ( today and see the difference!
0:57

Use this FREE tool to generate the first draft of ANY type of literature review. Meet AnswerThis — a tool that makes literature review faster and easier. Here’s how it works. 1. Visit and log in. 2. Select the 𝐿𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑅𝑒𝑣𝑖𝑒𝑤 option from the menu. 3. From the prompt helper, select 𝑊𝑟𝑖𝑡𝑒 𝑎 𝑙𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑟𝑒𝑣𝑖𝑒𝑤 𝑜𝑛. 4. Enter your research topic in the blank text field ➝ For example, Vulnerabilities in Big Data Systems 5. Click 𝐶𝑟𝑒𝑎𝑡𝑒 to generate the initial search prompt. 6. Press Enter to see research filter options. 7. Choose your response type based on your needs. ➝ Structured Literature Review: Citation-rich and detailed. ➝ Dynamic Research Assistant: To explore research gaps. ➝ AI Only: Fast, but unreliable with no citations. 8. Set the minimum number of citations for the review. ➝ Choose at least 10 for comprehensive results. 9. Decide whether to enable 𝑇𝑢𝑟𝑏𝑜 𝑀𝑜𝑑𝑒 for faster results. ➝ Disabling it gives you more comprehensive answers. 10. Select the sources for search results. ➝ Choose both web and databases for thorough results. 11. Specify the date range to get recent papers. 12. Enable 𝑑𝑜𝑢𝑏𝑙𝑒-𝑐ℎ𝑒𝑐𝑘 𝑐𝑖𝑡𝑎𝑡𝑖𝑜𝑛𝑠 for accurate results. 13. Once filters are set, click 𝑆𝑢𝑏𝑚𝑖𝑡 𝑆𝑒𝑎𝑟𝑐ℎ to proceed. 14. After a while, your literature review will be generated. ➝ Sources and citations will be listed on the right. 15. Review the results and assess the paper sources carefully. 16. Add relevant papers to your library for easy access later. 17. Export citations in formats like BibTeX or CSV as needed. 18. You can also download the review as a Word or PDF file. Treat this literature review as an initial draft. Refine it and build your review on the top of it. Ready to make literature review effortless? Try AnswerThis ( today and see the difference!

Faheem Ullah

12,694 views • 8 months ago

PhD Students – Use this tool to generate the first draft of ANY type of literature review in 10 minutes. Meet AnswerThis — a tool that makes literature review faster and easier. Here’s how it works. 1. Visit and log in. 2. Select the 𝐿𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑅𝑒𝑣𝑖𝑒𝑤 option from the menu. 3. From the prompt helper, select 𝑊𝑟𝑖𝑡𝑒 𝑎 𝑙𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑟𝑒𝑣𝑖𝑒𝑤 𝑜𝑛. 4. Enter your research topic in the blank text field ➝ For example, Vulnerabilities in Big Data Systems 5. Click 𝐶𝑟𝑒𝑎𝑡𝑒 to generate the initial search prompt. 6. Press Enter to see research filter options. 7. Choose your response type based on your needs. ➝ Structured Literature Review: Citation-rich and detailed. ➝ Dynamic Research Assistant: To explore research gaps. ➝ AI Only: Fast, but unreliable with no citations. 8. Set the minimum number of citations for the review. ➝ Choose at least 10 for comprehensive results. 9. Decide whether to enable 𝑇𝑢𝑟𝑏𝑜 𝑀𝑜𝑑𝑒 for faster results. ➝ Disabling it gives you more comprehensive answers. 10. Select the sources for search results. ➝ Choose both web and databases for thorough results. 11. Specify the date range to get recent papers. 12. Enable 𝑑𝑜𝑢𝑏𝑙𝑒-𝑐ℎ𝑒𝑐𝑘 𝑐𝑖𝑡𝑎𝑡𝑖𝑜𝑛𝑠 for accurate results. 13. Once filters are set, click 𝑆𝑢𝑏𝑚𝑖𝑡 𝑆𝑒𝑎𝑟𝑐ℎ to proceed. 14. After a while, your literature review will be generated. ➝ Sources and citations will be listed on the right. 15. Review the results and assess the paper sources carefully. 16. Add relevant papers to your library for easy access later. 17. Export citations in formats like BibTeX or CSV as needed. 18. You can also download the review as a Word or PDF file. Treat this literature review as an initial draft. Refine it and build your review on the top of it.
0:52

PhD Students – Use this tool to generate the first draft of ANY type of literature review in 10 minutes. Meet AnswerThis — a tool that makes literature review faster and easier. Here’s how it works. 1. Visit and log in. 2. Select the 𝐿𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑅𝑒𝑣𝑖𝑒𝑤 option from the menu. 3. From the prompt helper, select 𝑊𝑟𝑖𝑡𝑒 𝑎 𝑙𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑟𝑒𝑣𝑖𝑒𝑤 𝑜𝑛. 4. Enter your research topic in the blank text field ➝ For example, Vulnerabilities in Big Data Systems 5. Click 𝐶𝑟𝑒𝑎𝑡𝑒 to generate the initial search prompt. 6. Press Enter to see research filter options. 7. Choose your response type based on your needs. ➝ Structured Literature Review: Citation-rich and detailed. ➝ Dynamic Research Assistant: To explore research gaps. ➝ AI Only: Fast, but unreliable with no citations. 8. Set the minimum number of citations for the review. ➝ Choose at least 10 for comprehensive results. 9. Decide whether to enable 𝑇𝑢𝑟𝑏𝑜 𝑀𝑜𝑑𝑒 for faster results. ➝ Disabling it gives you more comprehensive answers. 10. Select the sources for search results. ➝ Choose both web and databases for thorough results. 11. Specify the date range to get recent papers. 12. Enable 𝑑𝑜𝑢𝑏𝑙𝑒-𝑐ℎ𝑒𝑐𝑘 𝑐𝑖𝑡𝑎𝑡𝑖𝑜𝑛𝑠 for accurate results. 13. Once filters are set, click 𝑆𝑢𝑏𝑚𝑖𝑡 𝑆𝑒𝑎𝑟𝑐ℎ to proceed. 14. After a while, your literature review will be generated. ➝ Sources and citations will be listed on the right. 15. Review the results and assess the paper sources carefully. 16. Add relevant papers to your library for easy access later. 17. Export citations in formats like BibTeX or CSV as needed. 18. You can also download the review as a Word or PDF file. Treat this literature review as an initial draft. Refine it and build your review on the top of it.

Faheem Ullah

14,071 views • 11 months ago

How to read a research paper 10x faster? PhD Students are often under time pressure. Many research papers but little time to read. Meet Bohrium – a tool that can 10x your paper reading. 𝐇𝐨𝐰 𝐜𝐚𝐧 𝐁𝐨𝐡𝐫𝐢𝐮𝐦 𝐡𝐞𝐥𝐩 𝐲𝐨𝐮 𝐫𝐞𝐚𝐝 𝐬𝐦𝐚𝐫𝐭𝐞𝐫? 1. Go to and log in. 2. Click on 𝑁𝑒𝑤 𝐶ℎ𝑎𝑡 and then on 𝐿𝑖𝑡𝑇𝑎𝑙𝑘 3. Upload the paper you want to read 4. Click on 𝑆𝑢𝑚𝑚𝑎𝑟𝑖𝑧𝑒 from the list. 5. Bohirum will summarize the paper for you. 6. This will help you understand the gist of the paper. 7. Now click on 𝐸𝑥𝑡𝑟𝑎𝑐𝑡 𝐹𝑖𝑛𝑑𝑖𝑛𝑔𝑠 8. Bohrium will extract key findings from the paper. 9. Go through each of the key finding. 10. Bohrium links each finding to respective part 11. This way you can see the links to the paper. 12. In the similar manner, you can also ↳ Extract information about research methods ↳ Academic concepts used in the paper 13. Bohrium can also help you in your writing 14. For example, you can use it to create diagrams 15. You can use Bohrium to create ✓ Graphical abstract ✓ Mechanism diagram ✓ Flowchart ✓ Concept cover 𝐖𝐡𝐚𝐭 𝐢𝐬 𝐬𝐩𝐞𝐜𝐢𝐚𝐥 𝐚𝐛𝐨𝐮𝐭 𝐁𝐨𝐡𝐫𝐢𝐮𝐦? → You can upload and chat with multiple papers together → Instead of only summarizing, it helps you in deep understanding → It links key findings to exact sections of the paper → It works like research-focused but free NotebookLLM Try it today:
1:10

How to read a research paper 10x faster? PhD Students are often under time pressure. Many research papers but little time to read. Meet Bohrium – a tool that can 10x your paper reading. 𝐇𝐨𝐰 𝐜𝐚𝐧 𝐁𝐨𝐡𝐫𝐢𝐮𝐦 𝐡𝐞𝐥𝐩 𝐲𝐨𝐮 𝐫𝐞𝐚𝐝 𝐬𝐦𝐚𝐫𝐭𝐞𝐫? 1. Go to and log in. 2. Click on 𝑁𝑒𝑤 𝐶ℎ𝑎𝑡 and then on 𝐿𝑖𝑡𝑇𝑎𝑙𝑘 3. Upload the paper you want to read 4. Click on 𝑆𝑢𝑚𝑚𝑎𝑟𝑖𝑧𝑒 from the list. 5. Bohirum will summarize the paper for you. 6. This will help you understand the gist of the paper. 7. Now click on 𝐸𝑥𝑡𝑟𝑎𝑐𝑡 𝐹𝑖𝑛𝑑𝑖𝑛𝑔𝑠 8. Bohrium will extract key findings from the paper. 9. Go through each of the key finding. 10. Bohrium links each finding to respective part 11. This way you can see the links to the paper. 12. In the similar manner, you can also ↳ Extract information about research methods ↳ Academic concepts used in the paper 13. Bohrium can also help you in your writing 14. For example, you can use it to create diagrams 15. You can use Bohrium to create ✓ Graphical abstract ✓ Mechanism diagram ✓ Flowchart ✓ Concept cover 𝐖𝐡𝐚𝐭 𝐢𝐬 𝐬𝐩𝐞𝐜𝐢𝐚𝐥 𝐚𝐛𝐨𝐮𝐭 𝐁𝐨𝐡𝐫𝐢𝐮𝐦? → You can upload and chat with multiple papers together → Instead of only summarizing, it helps you in deep understanding → It links key findings to exact sections of the paper → It works like research-focused but free NotebookLLM Try it today:

Faheem Ullah

27,133 views • 9 months ago

Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal instead. The results are wild. Here is the full workflow nobody is talking about: The Setup → Claude Code connects to NotebookLM via a command line interface → Claude searches YouTube, finds relevant videos, uploads them as sources automatically → NotebookLM processes up to 300 sources simultaneously and returns cited, grounded answers → Everything syncs back into your Obsidian vault with passage-level citations you can click to verify Why This Changes Research Forever → No more 20 browser tabs you never close → No more copy-pasting outputs into random notes → No more hallucinated answers with no sources to back them up → 60% of citations verified as strong matches in accuracy audits - answers are grounded in real data What Claude Can Do From the Terminal → Search YouTube for relevant videos on any topic and rank by relevance → Create a new NotebookLM notebook and add 20 sources in parallel automatically → Ask questions and export cited answers directly into Obsidian with wikilinks → Set custom personas per notebook - concise, no filler, no preamble → Generate audio overviews and save them as MP3 files into your vault → Build mind maps, flashcard decks, and research dashboards from your sources → Search arXiv for academic papers and feed them directly into NotebookLM → Upload competitor blog posts, podcast episodes, PDFs, and your own vault notes The Obsidian Output → Every answer arrives with clickable citations that link to the exact passage in the source video or article → Graph view shows connections between all 20 sources and the topics they share → Q&A log tracks every question asked and the grounded response received → Source dashboard shows citation frequency, topics extracted, and which questions each source answered Use Cases Worth Building Today → Academic research with arXiv papers, full citation traceability → Competitor analysis from their YouTube channels and blog posts → Company knowledge base for onboarding, new employees ask NotebookLM instead of interrupting teammates → Podcast research, feed 4-hour Lex Fridman episodes and ask what's new in AI this week → Personal second brain, 300 daily notes uploaded and queryable in one notebook Before this system existed you needed 20 tabs, hours of manual reading, and no guarantee the answers were real. Now you type one prompt in the terminal and Claude does all of it for you. The research stack of 2026 is not a browser. It is a terminal connected to everything
32:50

Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal instead. The results are wild. Here is the full workflow nobody is talking about: The Setup → Claude Code connects to NotebookLM via a command line interface → Claude searches YouTube, finds relevant videos, uploads them as sources automatically → NotebookLM processes up to 300 sources simultaneously and returns cited, grounded answers → Everything syncs back into your Obsidian vault with passage-level citations you can click to verify Why This Changes Research Forever → No more 20 browser tabs you never close → No more copy-pasting outputs into random notes → No more hallucinated answers with no sources to back them up → 60% of citations verified as strong matches in accuracy audits - answers are grounded in real data What Claude Can Do From the Terminal → Search YouTube for relevant videos on any topic and rank by relevance → Create a new NotebookLM notebook and add 20 sources in parallel automatically → Ask questions and export cited answers directly into Obsidian with wikilinks → Set custom personas per notebook - concise, no filler, no preamble → Generate audio overviews and save them as MP3 files into your vault → Build mind maps, flashcard decks, and research dashboards from your sources → Search arXiv for academic papers and feed them directly into NotebookLM → Upload competitor blog posts, podcast episodes, PDFs, and your own vault notes The Obsidian Output → Every answer arrives with clickable citations that link to the exact passage in the source video or article → Graph view shows connections between all 20 sources and the topics they share → Q&A log tracks every question asked and the grounded response received → Source dashboard shows citation frequency, topics extracted, and which questions each source answered Use Cases Worth Building Today → Academic research with arXiv papers, full citation traceability → Competitor analysis from their YouTube channels and blog posts → Company knowledge base for onboarding, new employees ask NotebookLM instead of interrupting teammates → Podcast research, feed 4-hour Lex Fridman episodes and ask what's new in AI this week → Personal second brain, 300 daily notes uploaded and queryable in one notebook Before this system existed you needed 20 tabs, hours of manual reading, and no guarantee the answers were real. Now you type one prompt in the terminal and Claude does all of it for you. The research stack of 2026 is not a browser. It is a terminal connected to everything

Dami-Defi

252,693 views • 4 months ago

AI memory is getting f...cking illegal 10 open-source GitHub projects that stop agents from starting from zero EVERY new session 01 Mem0 ▸ → 66K+ stars 02 Hindsight ▸ → retain → recall → reflect 03 memU ▸ TURN MEMORY INTO KNOWLEDGE 04 Cognee ▸ → documents + code + conversations → knowledge graph 05 Graphiti ▸ → remembers how facts change over time 06 OpenViking ▸ MAKE THE AGENT STATEFUL 07 Letta ▸ → memory + identity across sessions 08 Letta Code ▸ REMEMBER ACROSS THE STACK 09 OpenMemory ▸ 10 Agent Memory Benchmark ▸ the loop: experience → remember → connect → retrieve → act → update 3 builds I'd actually test: coding: Hindsight → Cognee → Letta Code personal agent: Mem0 → Graphiti → Letta company brain: Cognee → Graphiti → Hindsight and this is where the sh...t gets interesting: bigger context isn't the same as memory a model can hold 1M tokens and still meet you for the first time every morning these projects change that save this before your agent forgets it ⭣
0:36

AI memory is getting f...cking illegal 10 open-source GitHub projects that stop agents from starting from zero EVERY new session 01 Mem0 ▸ → 66K+ stars 02 Hindsight ▸ → retain → recall → reflect 03 memU ▸ TURN MEMORY INTO KNOWLEDGE 04 Cognee ▸ → documents + code + conversations → knowledge graph 05 Graphiti ▸ → remembers how facts change over time 06 OpenViking ▸ MAKE THE AGENT STATEFUL 07 Letta ▸ → memory + identity across sessions 08 Letta Code ▸ REMEMBER ACROSS THE STACK 09 OpenMemory ▸ 10 Agent Memory Benchmark ▸ the loop: experience → remember → connect → retrieve → act → update 3 builds I'd actually test: coding: Hindsight → Cognee → Letta Code personal agent: Mem0 → Graphiti → Letta company brain: Cognee → Graphiti → Hindsight and this is where the sh...t gets interesting: bigger context isn't the same as memory a model can hold 1M tokens and still meet you for the first time every morning these projects change that save this before your agent forgets it ⭣

Lummox

313,146 views • 2 days ago

When Mudith Jayasekara and I met Gabe Pereyra, we were expecting just another vanilla intro call and instead had the best yarn about research, the state of LLMs, and where intelligence is actually heading. It's rare to meet a founder this deep in the weeds who's also building for one of the most important verticals in this new age of intelligence So it was awesome to sit down with Gabe for an extended discussion on what it take to build agents that can reliably complete work over hours, days, or even longer? We talked about why agents today struggle with search and long context windows and how techniques like KV-cache compaction, synthetic data, and continual learning could help. 0:00 Introduction 0:36 Getting legal agents to review the whole data room 2:08 Data rooms larger than any context window 5:28 How far open-source models can go 7:58 Where specialist models fit in legal AI 10:59 Training legal models when client data is off-limits 13:06 Teaching a model how a law firm works 13:59 What belongs in context vs. model weights 15:36 From firm-wide AI to a model for every lawyer 18:37 What training adds beyond retrieving the right cases 20:26 Why context windows have plateaued 24:01 How models could learn continuously on the job 26:12 Can AI recursively improve AI research? 27:07 Research agents can run experiments but not choose them 30:00 Why open-ended research is hard to train 33:47 Why deployment, not intelligence, is the bottleneck 35:08 The cost of frontier intelligence 36:59 Different neolabs, different paths to intelligence 39:26 Using open datasets to compare research methods 41:13 Conclusion
41:50

When Mudith Jayasekara and I met Gabe Pereyra, we were expecting just another vanilla intro call and instead had the best yarn about research, the state of LLMs, and where intelligence is actually heading. It's rare to meet a founder this deep in the weeds who's also building for one of the most important verticals in this new age of intelligence So it was awesome to sit down with Gabe for an extended discussion on what it take to build agents that can reliably complete work over hours, days, or even longer? We talked about why agents today struggle with search and long context windows and how techniques like KV-cache compaction, synthetic data, and continual learning could help. 0:00 Introduction 0:36 Getting legal agents to review the whole data room 2:08 Data rooms larger than any context window 5:28 How far open-source models can go 7:58 Where specialist models fit in legal AI 10:59 Training legal models when client data is off-limits 13:06 Teaching a model how a law firm works 13:59 What belongs in context vs. model weights 15:36 From firm-wide AI to a model for every lawyer 18:37 What training adds beyond retrieving the right cases 20:26 Why context windows have plateaued 24:01 How models could learn continuously on the job 26:12 Can AI recursively improve AI research? 27:07 Research agents can run experiments but not choose them 30:00 Why open-ended research is hard to train 33:47 Why deployment, not intelligence, is the bottleneck 35:08 The cost of frontier intelligence 36:59 Different neolabs, different paths to intelligence 39:26 Using open datasets to compare research methods 41:13 Conclusion

Charlie O'Neill

92,869 views • 2 months ago

15 AI tools researched, ranked, and turned into X-ready content in ~2 minutes. I gave Viktor one job: Find the best new AI tools for our audience, research them, rank the top 3, and turn the research into X-ready content. In about 2 minutes, Viktor ran 24 targeted searches, researched 15 tools, cross-checked pricing, scored the options, built the comparison, and produced the final post. My first attempt didn't work. The workflow stalled before Viktor could connect the research and content steps. Then I adjusted the task, and that's when things clicked. What surprised me wasn't that he could research. It was how much of the workflow he could actually handle. Research. Compare. Prioritize. Create. Instead of jumping between tabs, collecting information, comparing tools, and turning research into content manually, Viktor handled the workflow in one place. That's the part I think people miss about AI employees. The value isn't another chatbot that gives you an answer. It's having an AI teammate that can take on real work and fit into the way your team already operates. Viktor works inside Slack and Microsoft Teams and connects to 3,200+ tools. A copilot helps you work. An AI employee works when you don't. I think this is where AI employees get genuinely interesting: the question isn't whether they can answer you, but whether you can trust them with actual work. Hire Viktor for your team. $100 in credits included, no card. Full link in first comment. #AIemployee #AITeams Paid Partnership
0:30

15 AI tools researched, ranked, and turned into X-ready content in ~2 minutes. I gave Viktor one job: Find the best new AI tools for our audience, research them, rank the top 3, and turn the research into X-ready content. In about 2 minutes, Viktor ran 24 targeted searches, researched 15 tools, cross-checked pricing, scored the options, built the comparison, and produced the final post. My first attempt didn't work. The workflow stalled before Viktor could connect the research and content steps. Then I adjusted the task, and that's when things clicked. What surprised me wasn't that he could research. It was how much of the workflow he could actually handle. Research. Compare. Prioritize. Create. Instead of jumping between tabs, collecting information, comparing tools, and turning research into content manually, Viktor handled the workflow in one place. That's the part I think people miss about AI employees. The value isn't another chatbot that gives you an answer. It's having an AI teammate that can take on real work and fit into the way your team already operates. Viktor works inside Slack and Microsoft Teams and connects to 3,200+ tools. A copilot helps you work. An AI employee works when you don't. I think this is where AI employees get genuinely interesting: the question isn't whether they can answer you, but whether you can trust them with actual work. Hire Viktor for your team. $100 in credits included, no card. Full link in first comment. #AIemployee #AITeams Paid Partnership

Marry Evan

30,072 views • 25 days ago

NEW: Harvey Co-Founder + Head of Applied Research on the *Token Reckoning* Valued at $11B, Harvey is on a mission to win the entire legal category, competing head-on against the trillion-dollar labs Coding agents hit Karpathy's "agents work now" inflection in late 2025. Harvey Co-Founder Gabe Pereyra (fmr Google Brain, DeepMind & Meta) argues legal is hitting its version of that curve right now. With both Gabe + Head of Applied Research Niko, we cover: - Open-sourcing LAB (legal agent benchmark): 1,200+ tasks across 24 practice areas, 75,000+ rubric criteria - Who's leading the leaderboard - Harvey is the largest embeddings consumer for some of the labs - Why every law firm has to be multi-model: conflict risk - The billable hour is coming back, this time for AI tokens FYI: Harvey Labs is the internal research group pushing the frontier of legal AI. Run by Niko (fmr multi-agent RL at Google Brain) & Julio Pereyra (fmr clerk + Big Law attorney), it partners with the labs, research community, & academia to bring frontier agent research into Harvey. 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) Gabe Pereyra (Co-Founder) & Niko Grupen (Head of Applied Research) (00:50) Inside Harvey's legal agent Benchmark (05:10) What happens after Benchmarking? (06:37) Why Harvey open sourced its research (09:21) Training models without client data (10:32) Google Brain vs. DeepMind (12:34) From Researcher to Founder (15:15) The Rise of the Inference Layer (18:38) The Agentic Shift (21:16) Harvey's 13 trillion tokens (23:48) AI's Biggest cost misconception (28:37) How Top AI founders learn (31:52) Learnings from Jensen Huang (34:14) How Harvey finds talent (35:41) Niko on Harvey's breakthroughs (36:38) Building a legal dataset from scratch (38:32) How to read AI Benchmarks (39:51) Niko's research playbook (40:51) The Opportunity beyond Benchmarks (41:45) Why Agent Harnesses matter (43:04) The Rise of Organizational AI
44:52

NEW: Harvey Co-Founder + Head of Applied Research on the *Token Reckoning* Valued at $11B, Harvey is on a mission to win the entire legal category, competing head-on against the trillion-dollar labs Coding agents hit Karpathy's "agents work now" inflection in late 2025. Harvey Co-Founder Gabe Pereyra (fmr Google Brain, DeepMind & Meta) argues legal is hitting its version of that curve right now. With both Gabe + Head of Applied Research Niko, we cover: - Open-sourcing LAB (legal agent benchmark): 1,200+ tasks across 24 practice areas, 75,000+ rubric criteria - Who's leading the leaderboard - Harvey is the largest embeddings consumer for some of the labs - Why every law firm has to be multi-model: conflict risk - The billable hour is coming back, this time for AI tokens FYI: Harvey Labs is the internal research group pushing the frontier of legal AI. Run by Niko (fmr multi-agent RL at Google Brain) & Julio Pereyra (fmr clerk + Big Law attorney), it partners with the labs, research community, & academia to bring frontier agent research into Harvey. 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) Gabe Pereyra (Co-Founder) & Niko Grupen (Head of Applied Research) (00:50) Inside Harvey's legal agent Benchmark (05:10) What happens after Benchmarking? (06:37) Why Harvey open sourced its research (09:21) Training models without client data (10:32) Google Brain vs. DeepMind (12:34) From Researcher to Founder (15:15) The Rise of the Inference Layer (18:38) The Agentic Shift (21:16) Harvey's 13 trillion tokens (23:48) AI's Biggest cost misconception (28:37) How Top AI founders learn (31:52) Learnings from Jensen Huang (34:14) How Harvey finds talent (35:41) Niko on Harvey's breakthroughs (36:38) Building a legal dataset from scratch (38:32) How to read AI Benchmarks (39:51) Niko's research playbook (40:51) The Opportunity beyond Benchmarks (41:45) Why Agent Harnesses matter (43:04) The Rise of Organizational AI

Molly O’Shea

86,280 views • 3 months ago

Building a very useful app in 20 minutes that has - Deep Research (Perplexity) - Claude 3.7 Sonnet - YT Transcript API (SupaData) Without writing a single line of code With the latest Cursor update with web search and Claude 3.7 Sonnet, Vibe Coding got even more vibey. Timestamps: 00:00 Getting Started 00:57 Ideating with excalidraw 02:29 Opening Cursor Starting From Template 05:25 Perplexity Deep Research API and Claude API set up 10:18 OHHH NO AN ERROR! WHATEVER WILL I DO? 11:17 PERPLEXITY AND CLAUDE WORKED! 12:02 IMPROVING DESIGN 13:04 ADDING YOUTUBE TRANSCRIPT API 15:21 Redesign Concept with v0 17:07 This is what we created 19:42 Want to dive deeper into vibe coding?
20:20

Building a very useful app in 20 minutes that has - Deep Research (Perplexity) - Claude 3.7 Sonnet - YT Transcript API (SupaData) Without writing a single line of code With the latest Cursor update with web search and Claude 3.7 Sonnet, Vibe Coding got even more vibey. Timestamps: 00:00 Getting Started 00:57 Ideating with excalidraw 02:29 Opening Cursor Starting From Template 05:25 Perplexity Deep Research API and Claude API set up 10:18 OHHH NO AN ERROR! WHATEVER WILL I DO? 11:17 PERPLEXITY AND CLAUDE WORKED! 12:02 IMPROVING DESIGN 13:04 ADDING YOUTUBE TRANSCRIPT API 15:21 Redesign Concept with v0 17:07 This is what we created 19:42 Want to dive deeper into vibe coding?

Riley Brown

84,875 views • 1 year ago

Anne-Laure Le Cunff (Anne-Laure Le Cunff) might be the most productive person I’ve ever met. She’s simultaneously running a successful business, writing a book being published by a major publisher, and getting a PhD in neuroscience. She says it’s only possible because of ChatGPT. It saves her time on the administrative tasks required to run her business. It helps her create better outlines so that she can write pieces more efficiently. It even breaks down complex research papers so that she can incorporate them into her PhD work. We spent an hour and a half exploring in-detail every part of her ChatGPT workflow—and we even used it live to help her fine-tune her meditation practice. We get into: - How @ChatGPTapp saves her time running her business - Tips to break down research papers into digestible insights - How she leverages ChatGPT to revamp her YouTube thumbnails - Using ChatGPT to write original articles - Doing deep online research using ChatGPT - How to use ChatGPT to generate advice tailored for your needs - How to surface useful insights from your journal using ChatGPT This is a must-watch for curious, creative people who want to get more done. Watch below! ---- Timestamps: Introduction 01:10 How to use ChatGPT to save time running a business 02:11 Tips to breakdown research papers with ChatGPT 05:17 How to use ChatGPT to generate explanations tailored for you 09:38 Leveraging ChatGPT to find hidden gems on the internet (like recipes for obscure cheese) 19:51 How to create awesome YouTube thumbnails with ChatGPT 33:47 Incorporating ChatGPT into your writing process 51:13 Rapid fire questions from X 56:52 Surfacing useful insights from Anne-Laure’s meditation journal 1:13:01 The case for journaling in the age of AI 1:29:04
1:28:37

Anne-Laure Le Cunff (Anne-Laure Le Cunff) might be the most productive person I’ve ever met. She’s simultaneously running a successful business, writing a book being published by a major publisher, and getting a PhD in neuroscience. She says it’s only possible because of ChatGPT. It saves her time on the administrative tasks required to run her business. It helps her create better outlines so that she can write pieces more efficiently. It even breaks down complex research papers so that she can incorporate them into her PhD work. We spent an hour and a half exploring in-detail every part of her ChatGPT workflow—and we even used it live to help her fine-tune her meditation practice. We get into: - How @ChatGPTapp saves her time running her business - Tips to break down research papers into digestible insights - How she leverages ChatGPT to revamp her YouTube thumbnails - Using ChatGPT to write original articles - Doing deep online research using ChatGPT - How to use ChatGPT to generate advice tailored for your needs - How to surface useful insights from your journal using ChatGPT This is a must-watch for curious, creative people who want to get more done. Watch below! ---- Timestamps: Introduction 01:10 How to use ChatGPT to save time running a business 02:11 Tips to breakdown research papers with ChatGPT 05:17 How to use ChatGPT to generate explanations tailored for you 09:38 Leveraging ChatGPT to find hidden gems on the internet (like recipes for obscure cheese) 19:51 How to create awesome YouTube thumbnails with ChatGPT 33:47 Incorporating ChatGPT into your writing process 51:13 Rapid fire questions from X 56:52 Surfacing useful insights from Anne-Laure’s meditation journal 1:13:01 The case for journaling in the age of AI 1:29:04

Dan Shipper

72,667 views • 2 years ago

this is pure f*cking treasure these 20 plugins have 8.78M combined downloads and form a real Claude Code stack build → think → operate → control → ship BUILD 01 agents-ai-agents ▸ 02 agents-data-ai ▸ 03 agents-design-experience ▸ 04 agents-development-architecture ▸ 05 agents-infrastructure-operations ▸ INTELLIGENCE 06 agents-language-specialists ▸ 07 agents-quality-security ▸ 08 agents-research ▸ 09 agents-sales-marketing ▸ 10 agents-documentation ▸ OPERATE 11 commands-automation-workflow ▸ 12 commands-ci-deployment ▸ 13 commands-code-analysis-testing ▸ 14 commands-context-loading-priming ▸ 15 commands-monitoring-observability ▸ CONTROL 16 commands-performance-optimization ▸ 17 commands-project-task-management ▸ 18 commands-security-audit ▸ 19 commands-workflow-orchestration ▸ 20 mcp-servers-docker ▸ the loop: idea → architecture → implementation → checks → release save this, then read the article below
0:20

this is pure f*cking treasure these 20 plugins have 8.78M combined downloads and form a real Claude Code stack build → think → operate → control → ship BUILD 01 agents-ai-agents ▸ 02 agents-data-ai ▸ 03 agents-design-experience ▸ 04 agents-development-architecture ▸ 05 agents-infrastructure-operations ▸ INTELLIGENCE 06 agents-language-specialists ▸ 07 agents-quality-security ▸ 08 agents-research ▸ 09 agents-sales-marketing ▸ 10 agents-documentation ▸ OPERATE 11 commands-automation-workflow ▸ 12 commands-ci-deployment ▸ 13 commands-code-analysis-testing ▸ 14 commands-context-loading-priming ▸ 15 commands-monitoring-observability ▸ CONTROL 16 commands-performance-optimization ▸ 17 commands-project-task-management ▸ 18 commands-security-audit ▸ 19 commands-workflow-orchestration ▸ 20 mcp-servers-docker ▸ the loop: idea → architecture → implementation → checks → release save this, then read the article below

beamnxw ./

34,441 views • 7 days ago

this is pure f*cking treasure 30 best MCP servers, mapped across 10 categories for building your agent's toolbox search. code. browser automation. files. databases. memory. agents. productivity. research. finance 01 SEARCH & INTERNET Brave Search MCP Server ▸ Google Maps MCP Server ▸ World Monitor MCP ▸ 02 PROGRAMMING Sentry MCP Server ▸ Context7 MCP ▸ GitHub MCP Server ▸ 03 BROWSER & AUTOMATION Fetch MCP Server ▸ Chrome DevTools MCP ▸ Playwright MCP Server ▸ 04 FILES & DOCUMENTS Filesystem MCP Server ▸ Google Drive server ▸ MCP server for Obsidian ▸ 05 DATABASES PostgreSQL ▸ SQLite MCP Server ▸ MCP Toolbox for Databases ▸ 06 MEMORY & RAG Knowledge Graph Memory Server ▸ Graphiti MCP Server ▸ cognee-mcp ▸ 07 AI AGENTS Taskmaster ▸ BlenderMCP ▸ Talk to Figma MCP ▸ 08 WORK & PRODUCTIVITY Google Workspace MCP Server ▸ Todoist AI MCP Server ▸ Thunderbird MCP ▸ 09 RESEARCH & ANALYTICS Phoenix MCP ▸ Zotero MCP ▸ NotebookLM MCP Server ▸ 10 BUSINESS & FINANCE Finance Toolkit ▸ Financial Datasets MCP Server ▸ Stripe MCP Server ▸ the stack covers the full agent loop: find information ⮕ write and inspect code ⮕ operate the browser ⮕ read files ⮕ query data ⮕ remember context ⮕ delegate work ⮕ run operations ⮕ analyze evidence ⮕ handle payments some reference servers above live in archived repositories, so check maintenance and permissions before production use save this, then select your gpt-6 astra use case ⭣
0:30

this is pure f*cking treasure 30 best MCP servers, mapped across 10 categories for building your agent's toolbox search. code. browser automation. files. databases. memory. agents. productivity. research. finance 01 SEARCH & INTERNET Brave Search MCP Server ▸ Google Maps MCP Server ▸ World Monitor MCP ▸ 02 PROGRAMMING Sentry MCP Server ▸ Context7 MCP ▸ GitHub MCP Server ▸ 03 BROWSER & AUTOMATION Fetch MCP Server ▸ Chrome DevTools MCP ▸ Playwright MCP Server ▸ 04 FILES & DOCUMENTS Filesystem MCP Server ▸ Google Drive server ▸ MCP server for Obsidian ▸ 05 DATABASES PostgreSQL ▸ SQLite MCP Server ▸ MCP Toolbox for Databases ▸ 06 MEMORY & RAG Knowledge Graph Memory Server ▸ Graphiti MCP Server ▸ cognee-mcp ▸ 07 AI AGENTS Taskmaster ▸ BlenderMCP ▸ Talk to Figma MCP ▸ 08 WORK & PRODUCTIVITY Google Workspace MCP Server ▸ Todoist AI MCP Server ▸ Thunderbird MCP ▸ 09 RESEARCH & ANALYTICS Phoenix MCP ▸ Zotero MCP ▸ NotebookLM MCP Server ▸ 10 BUSINESS & FINANCE Finance Toolkit ▸ Financial Datasets MCP Server ▸ Stripe MCP Server ▸ the stack covers the full agent loop: find information ⮕ write and inspect code ⮕ operate the browser ⮕ read files ⮕ query data ⮕ remember context ⮕ delegate work ⮕ run operations ⮕ analyze evidence ⮕ handle payments some reference servers above live in archived repositories, so check maintenance and permissions before production use save this, then select your gpt-6 astra use case ⭣

beamnxw ./

68,561 views • 14 days ago

Sonnet 4.5 & the AI Plateau Myth — epic conversation with Sholto Douglas of Anthropic 0:00 - Intro 1:09 - What's Behind The Rapid Pace of AI Releases at Anthropic 2:49 - Opus, Sonnet, and Haiku Model Tiers 4:14 - Sholto's Story: From Australian Fencer to AI Researcher 12:01 - The YouTube Effect: Mastery Through Observation 16:16 - Breaking Into AI Research Without Traditional Academic Signals 18:29 - DeepMind, Gemini, and Building Inference Stacks 23:05 - Why Anthropic? Culture and Mission Differences Amongst AI Research Labs 25:08 - What Is "Taste" in AI Research? 31:46 - This Week's Big Launch: Sonnet 4.5, Best Coding Model in the World 36:40 - From 7 Hours to 30 Hours: The Long-Running AI Agent Breakthrough 38:41 - How AI Agents Self-Correct and Maintain Coherence 43:13 - The Role of Memory in Extended Coding Sessions 47:42 - Pre-Training vs. RL: Textbooks vs. Worked Problems 52:11 - Test-Time Compute & Reinforcement Learning 55:55 - Why RL Finally Started Working on LLMs in 2024 59:38 - The Path to AGI 1:02:05 - Are We Hitting a Plateau in AI? So Many Low Hanging Fruits 1:03:41 - Beyond Coding: GDPVal & Impact Economic Sectors 1:05:47 - Preparing for 10-100x Individual Leverage & The Upcoming Robotics Explosion
1:10:03

Sonnet 4.5 & the AI Plateau Myth — epic conversation with Sholto Douglas of Anthropic 0:00 - Intro 1:09 - What's Behind The Rapid Pace of AI Releases at Anthropic 2:49 - Opus, Sonnet, and Haiku Model Tiers 4:14 - Sholto's Story: From Australian Fencer to AI Researcher 12:01 - The YouTube Effect: Mastery Through Observation 16:16 - Breaking Into AI Research Without Traditional Academic Signals 18:29 - DeepMind, Gemini, and Building Inference Stacks 23:05 - Why Anthropic? Culture and Mission Differences Amongst AI Research Labs 25:08 - What Is "Taste" in AI Research? 31:46 - This Week's Big Launch: Sonnet 4.5, Best Coding Model in the World 36:40 - From 7 Hours to 30 Hours: The Long-Running AI Agent Breakthrough 38:41 - How AI Agents Self-Correct and Maintain Coherence 43:13 - The Role of Memory in Extended Coding Sessions 47:42 - Pre-Training vs. RL: Textbooks vs. Worked Problems 52:11 - Test-Time Compute & Reinforcement Learning 55:55 - Why RL Finally Started Working on LLMs in 2024 59:38 - The Path to AGI 1:02:05 - Are We Hitting a Plateau in AI? So Many Low Hanging Fruits 1:03:41 - Beyond Coding: GDPVal & Impact Economic Sectors 1:05:47 - Preparing for 10-100x Individual Leverage & The Upcoming Robotics Explosion

Matt Turck

93,678 views • 1 year ago