Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

launching 5 things: 1. multi-repo context support 2. rebuilt web app for super large orgs 3. integrations with claude/codex/devin 4. .greptile/rules files 5. rebuilt learning so greptile maintains internal docs about your company

dakshgup's profile picture

Daksh Gupta

17,564 subscribers

22,918 Aufrufe • vor 2 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

You wanted shadcn — so we built the heinous infra to make it work. Introducing Agent Arena, starting with the best: Claude Code by Anthropic Codex 5 by OpenAI Cursor Agent by Cursor Devin by Cognition Gemini CLI by Google DeepMind Grok Code Fast 1 by xAI 1/ Your prompt launches a containerized agent inside a fresh GitHub repo 2/ The agent can install packages, make tool calls, and write multi-file code 3/ The repo is deployed to Vercel *by the agent*, clonable to your heart's desire
0:25

You wanted shadcn — so we built the heinous infra to make it work. Introducing Agent Arena, starting with the best: Claude Code by Anthropic Codex 5 by OpenAI Cursor Agent by Cursor Devin by Cognition Gemini CLI by Google DeepMind Grok Code Fast 1 by xAI 1/ Your prompt launches a containerized agent inside a fresh GitHub repo 2/ The agent can install packages, make tool calls, and write multi-file code 3/ The repo is deployed to Vercel *by the agent*, clonable to your heart's desire

Grace Li

168,980 Aufrufe • vor 9 Monaten

I made an AI agent that can fill out complicated forms from unstructured context 📝 For instance: automatically fill out your expense report 💳 by drag and dropping 5-10 receipt pictures/scans 🧾 Uses Claude Agent SDK + LlamaParse to parse unstructured docs + custom tools for form understanding. It now semantically understands each field, handles multi-turn conversations, and lets you drag up to 10 files. Deployed on Vercel/Render. App: Repo: LlamaCloud:
0:39

I made an AI agent that can fill out complicated forms from unstructured context 📝 For instance: automatically fill out your expense report 💳 by drag and dropping 5-10 receipt pictures/scans 🧾 Uses Claude Agent SDK + LlamaParse to parse unstructured docs + custom tools for form understanding. It now semantically understands each field, handles multi-turn conversations, and lets you drag up to 10 files. Deployed on Vercel/Render. App: Repo: LlamaCloud:

Jerry Liu

34,991 Aufrufe • vor 6 Monaten

You need to be learning with NotebookLM, trust me 1) AI podcast summaries 2) Multi-source synthesis - Ultimate Context Engineering 3) Team SOPs - Turn research into shareable operational guides 4) Multimodal learning - Read, listen, ask questions - your choice 5) Source-grounded - Every answer cites exactly where it came from In this 39 min video, you will learn everything about NotebookLM (even as a beginner)
39:24

You need to be learning with NotebookLM, trust me 1) AI podcast summaries 2) Multi-source synthesis - Ultimate Context Engineering 3) Team SOPs - Turn research into shareable operational guides 4) Multimodal learning - Read, listen, ask questions - your choice 5) Source-grounded - Every answer cites exactly where it came from In this 39 min video, you will learn everything about NotebookLM (even as a beginner)

David Ondrej

62,095 Aufrufe • vor 8 Monaten

WARP SPEED: EPISODE 4 - starring Daksh Gupta, CEO of Greptile Daksh Gupta The core difference between human productivity and every other species? Tools. On the margin, slightly better tools create long-term efficiencies that unlock time for more important things. Daksh, Soohoon Choi , and Vaishant Kameswaran built Greptile into one of the fastest-growing AI code review platforms in the world. $25M Series A led by Benchmark . YC-backed. 16 people. 500M+ lines of code reviewed this month alone for companies like Brex, Substack, and PostHog. The insight: AI coding tools are exploding. Cursor, Claude Code, Devin. Everyone's writing more code than ever. But the systems for validating that code before it ships? Breaking down. Greptile is the independent, centralized validation layer - AI that reviews pull requests, catches bugs, enforces standards. Daksh didn't plan to start a company. He was in senior year when he realized he'd lost his way. Remembered why he chose CS in the first place: to build things. He then convinced his college roommate - "the smartest person I know" - to move to San Francisco with barely enough angel money to survive. Now they're one of the most craft-obsessed teams in SF - using Linear, Claude Code, Cursor, and Warp to ship at warp speed. In this conversation: (0:00) - From losing his way in college to moving to San Francisco (1:24) - Applying to Y Combinator and building the foundations of Greptile (2:37) - Hiring more senior than typical: arbitraging ageism in Silicon Valley (3:40) - Building a company worthy of people who could go anywhere (4:14) - The new bottleneck: producing code is worthless without validating it (4:52) - The Greptile stack: Linear, Claude Code, Cursor, Warp (5:55) - "People talked about Warp with a passion you wouldn't expect for back-office software" (6:17) - The magic of heavy automation: "I'm never in it" (6:42) - Built for engineers, not HR people: "When you're used to confusing software, simple things are just delightful" (7:46) - Scaling from 15 to 50: "Whatever will go wrong, Warp will have functionality for it" (8:55) - Discovering Warp on Twitter: "Why are people so excited about payroll?" (9:35) - "It inspires you to build more intuitive things"
10:17

WARP SPEED: EPISODE 4 - starring Daksh Gupta, CEO of Greptile Daksh Gupta The core difference between human productivity and every other species? Tools. On the margin, slightly better tools create long-term efficiencies that unlock time for more important things. Daksh, Soohoon Choi , and Vaishant Kameswaran built Greptile into one of the fastest-growing AI code review platforms in the world. $25M Series A led by Benchmark . YC-backed. 16 people. 500M+ lines of code reviewed this month alone for companies like Brex, Substack, and PostHog. The insight: AI coding tools are exploding. Cursor, Claude Code, Devin. Everyone's writing more code than ever. But the systems for validating that code before it ships? Breaking down. Greptile is the independent, centralized validation layer - AI that reviews pull requests, catches bugs, enforces standards. Daksh didn't plan to start a company. He was in senior year when he realized he'd lost his way. Remembered why he chose CS in the first place: to build things. He then convinced his college roommate - "the smartest person I know" - to move to San Francisco with barely enough angel money to survive. Now they're one of the most craft-obsessed teams in SF - using Linear, Claude Code, Cursor, and Warp to ship at warp speed. In this conversation: (0:00) - From losing his way in college to moving to San Francisco (1:24) - Applying to Y Combinator and building the foundations of Greptile (2:37) - Hiring more senior than typical: arbitraging ageism in Silicon Valley (3:40) - Building a company worthy of people who could go anywhere (4:14) - The new bottleneck: producing code is worthless without validating it (4:52) - The Greptile stack: Linear, Claude Code, Cursor, Warp (5:55) - "People talked about Warp with a passion you wouldn't expect for back-office software" (6:17) - The magic of heavy automation: "I'm never in it" (6:42) - Built for engineers, not HR people: "When you're used to confusing software, simple things are just delightful" (7:46) - Scaling from 15 to 50: "Whatever will go wrong, Warp will have functionality for it" (8:55) - Discovering Warp on Twitter: "Why are people so excited about payroll?" (9:35) - "It inspires you to build more intuitive things"

Ayush S

27,984 Aufrufe • vor 8 Monaten

Codex CLI will have MULTI-AGENT support in 0.123.0 Here's how it will work: → 1. Add `multi_agent=true` in ~/codex/config.toml under [features] → 2. Toggle with `/experimental` → 3. Three built-in agents (default, explorer, worker) → 4. Define your own agents ``` [agents.researcher] description = "Research-focused role." config_file = "~/.codex/agents/researcher.toml" model = "gpt-5.3-codex" model_reasoning_effort = "high" web_search = "live" sandbox_mode = "read-only" developer_instructions = """ You are the researcher agent. - Gather evidence from primary sources. - Return links, findings, and uncertainty. - Do not edit files. """ ``` → 5. Run more agent threads per session (default: 6) ``` [agents] max_threads = 6 Notes: → OAI released 0.122.0 - but rolled it back! → I built it from source (so you don't have)
0:21

Codex CLI will have MULTI-AGENT support in 0.123.0 Here's how it will work: → 1. Add `multi_agent=true` in ~/codex/config.toml under [features] → 2. Toggle with `/experimental` → 3. Three built-in agents (default, explorer, worker) → 4. Define your own agents ``` [agents.researcher] description = "Research-focused role." config_file = "~/.codex/agents/researcher.toml" model = "gpt-5.3-codex" model_reasoning_effort = "high" web_search = "live" sandbox_mode = "read-only" developer_instructions = """ You are the researcher agent. - Gather evidence from primary sources. - Return links, findings, and uncertainty. - Do not edit files. """ ``` → 5. Run more agent threads per session (default: 6) ``` [agents] max_threads = 6 Notes: → OAI released 0.122.0 - but rolled it back! → I built it from source (so you don't have)

Chong-U

36,205 Aufrufe • vor 5 Monaten

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this
13:23

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

55,345 Aufrufe • vor 1 Monat

Day 3 of 5 building with Claude Fable 5 before it goes paid. Today: an audit of everything you have already made. 1. Fable 5 reads back through all your past Claude chats 2. It flags what worked, what you dropped, and where value is going to waste 3. It ranks the top 10 fixes by effort against impact 4. Then it hands you a concrete plan for the top 3 5. Run that plan on a cheaper model and save Fable 5 for the thinking Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 4 tomorrow.
0:52

Day 3 of 5 building with Claude Fable 5 before it goes paid. Today: an audit of everything you have already made. 1. Fable 5 reads back through all your past Claude chats 2. It flags what worked, what you dropped, and where value is going to waste 3. It ranks the top 10 fixes by effort against impact 4. Then it hands you a concrete plan for the top 3 5. Run that plan on a cheaper model and save Fable 5 for the thinking Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 4 tomorrow.

Charlie Hills

13,617 Aufrufe • vor 28 Tagen

Boris Cherny: "My job is to write loops." 5-day version you can copy for Claude Code Day 1: repo memory - write CLAUDE.md - include stack, test commands, code style, release rules, gotchas - add .claude/settings.json with the shell commands Claude can run Day 2: verification skill - pick 1 flow Claude keeps breaking - put the browser/API test in .claude/skills/ /scripts/ - make it return: pass/fail, failing step, screenshot/log path Day 3: commands Add these files: .claude/commands/babysit.md - checks your PRs - reads CI - handles obvious review nits - surfaces design questions .claude/commands/triage-issues.md - labels new issues - dedupes against existing ones - assigns owners .claude/commands/deploy-watch.md - checks the live app - reports regressions - avoids touching production Day 4: loops > /loop 5m /babysit > /loop 15m /triage-issues > /loop 5m /deploy-watch Day 5: overnight work - schedule /morning-report - schedule /deep-audit - write results to .claude/inbox/ - let your morning loop read from that folder The rule: every code-writing loop gets a separate verifier. Builder makes the change. Verifier runs the real app. You read the diff. Skip that and you wake up to 14 broken PRs with very confident summaries. Video: "Reflecting on a year of Claude Code" with Boris Cherny & Cat Wu
18:07

Boris Cherny: "My job is to write loops." 5-day version you can copy for Claude Code Day 1: repo memory - write CLAUDE.md - include stack, test commands, code style, release rules, gotchas - add .claude/settings.json with the shell commands Claude can run Day 2: verification skill - pick 1 flow Claude keeps breaking - put the browser/API test in .claude/skills/ /scripts/ - make it return: pass/fail, failing step, screenshot/log path Day 3: commands Add these files: .claude/commands/babysit.md - checks your PRs - reads CI - handles obvious review nits - surfaces design questions .claude/commands/triage-issues.md - labels new issues - dedupes against existing ones - assigns owners .claude/commands/deploy-watch.md - checks the live app - reports regressions - avoids touching production Day 4: loops > /loop 5m /babysit > /loop 15m /triage-issues > /loop 5m /deploy-watch Day 5: overnight work - schedule /morning-report - schedule /deep-audit - write results to .claude/inbox/ - let your morning loop read from that folder The rule: every code-writing loop gets a separate verifier. Builder makes the change. Verifier runs the real app. You read the diff. Skip that and you wake up to 14 broken PRs with very confident summaries. Video: "Reflecting on a year of Claude Code" with Boris Cherny & Cat Wu

Alpha Batcher

141,110 Aufrufe • vor 1 Monat

Fable 5 goes paid in 4 days. After that, usage credits only. Five things to do before the window closes. 1. Build a website. It's brilliant at front end design. 2. Build an internal tool instead of Slack or Notion. 3. Get it to review everything you've made in Claude since the ban. 4. Hand it your goals. Ask how to start your first business. 5. Ask how to run a local LLM. Stay unlocked from closed models. Comment FABLE for the guide.
0:52

Fable 5 goes paid in 4 days. After that, usage credits only. Five things to do before the window closes. 1. Build a website. It's brilliant at front end design. 2. Build an internal tool instead of Slack or Notion. 3. Get it to review everything you've made in Claude since the ban. 4. Hand it your goals. Ask how to start your first business. 5. Ask how to run a local LLM. Stay unlocked from closed models. Comment FABLE for the guide.

Charlie Hills

30,530 Aufrufe • vor 1 Monat

The Moonpay Desktop App is SO GOOD for trading It's powered by Nansen AI, Claude/Codex, and Moonpay so it's REALLY smart at doing onchain things like wallet tracking In ONE prompt it: 1. Found 400+ early buyers for the top 5 Pokemon Coins 2. Removed snipers + highlighted insiders that own multiple of the same coins 3. Created a desktop notification if >40% of all wallets buy a new coin Watch this video on how to do this in 5 mins (lmk if you want the wallet list too)
3:29

The Moonpay Desktop App is SO GOOD for trading It's powered by Nansen AI, Claude/Codex, and Moonpay so it's REALLY smart at doing onchain things like wallet tracking In ONE prompt it: 1. Found 400+ early buyers for the top 5 Pokemon Coins 2. Removed snipers + highlighted insiders that own multiple of the same coins 3. Created a desktop notification if >40% of all wallets buy a new coin Watch this video on how to do this in 5 mins (lmk if you want the wallet list too)

ashen

13,813 Aufrufe • vor 2 Monaten

Our on-set food support was successfully delivered at 11:30 AM today! Here is the full menu: - 🌻For Faye： 🥞Breakfast 1. RUIT SCONES WITH CLOTTED CREAM AND RASPBERRY JAM 2. APPLE TURNOVERS 3. PLAIN AU CHOCOLATE 4. NUTELLA CROISSANT 5. SALTANA BUTTER CROISSANT 🍲Mains 1. SPICY SPAGHETTI WITH BACON 2. ROAST CHICKEN WITH SAUCE TERIYAKY 🍱Side 1. CHEESY GYOZA 2. SHRIMP SPRING ROLLS 🍹Drink 1. SUMMER BLACK 2. PLUM LEMON SPRITE 3. PREMIUM MATCHA 4. ROSE BLACK TEA 5. SNOW QUEEN 🍨Dessert & Cake 1. BANANA CARAMEL WAFFLES 2. NEW YORK CHEESECAKE 3. CREAMY BLUEBERRY BLACK PIE 🍓 MIX FRUITS - 👨‍⚕️For Staff： 1. MIX FRUITS (MINI) *15 2. MIX FRUITS *15 3. PLUM LEMON SPRITE *10 4. FRUIT PUNCH *10 5. RASPBERRY LEMON TEA *10 - Congratulations to all the lucky fans who joined this project! Thank you so much for your trust and support🫶 Our support for Broken (of) Love last EP event is still ongoing. Please stay tuned for our upcoming updates 🌻💛 #FayePeraya #ฝ้ายพีรญา #BrokenOfLoveTheSeries
0:26

Our on-set food support was successfully delivered at 11:30 AM today! Here is the full menu: - 🌻For Faye： 🥞Breakfast 1. RUIT SCONES WITH CLOTTED CREAM AND RASPBERRY JAM 2. APPLE TURNOVERS 3. PLAIN AU CHOCOLATE 4. NUTELLA CROISSANT 5. SALTANA BUTTER CROISSANT 🍲Mains 1. SPICY SPAGHETTI WITH BACON 2. ROAST CHICKEN WITH SAUCE TERIYAKY 🍱Side 1. CHEESY GYOZA 2. SHRIMP SPRING ROLLS 🍹Drink 1. SUMMER BLACK 2. PLUM LEMON SPRITE 3. PREMIUM MATCHA 4. ROSE BLACK TEA 5. SNOW QUEEN 🍨Dessert & Cake 1. BANANA CARAMEL WAFFLES 2. NEW YORK CHEESECAKE 3. CREAMY BLUEBERRY BLACK PIE 🍓 MIX FRUITS - 👨‍⚕️For Staff： 1. MIX FRUITS (MINI) *15 2. MIX FRUITS *15 3. PLUM LEMON SPRITE *10 4. FRUIT PUNCH *10 5. RASPBERRY LEMON TEA *10 - Congratulations to all the lucky fans who joined this project! Thank you so much for your trust and support🫶 Our support for Broken (of) Love last EP event is still ongoing. Please stay tuned for our upcoming updates 🌻💛 #FayePeraya #ฝ้ายพีรญา #BrokenOfLoveTheSeries

FayeTrendHub_CN

17,722 Aufrufe • vor 3 Monaten

Here's my conversation with Dario Amodei, CEO of Anthropic, the company that created Claude, one of the best AI systems in the world. We talk about scaling, AI safety, regulation, and a lot of super technical details about the present and future of AI and humanity. It's a 5+ hour conversation in total. Amanda Askell and Chris Olah (Chris Olah) join us for an hour each to talk about Claude's character and mechanistic interpretability, respectively. This was a fascinating, wide-ranging, super-technical, and fun conversation! First 4 hours are here on X (4 hours is current limit), and is up on everywhere else in full. Links in comment. Timestamps: 0:00 - Introduction 3:14 - Scaling laws 12:20 - Limits of LLM scaling 20:45 - Competition with OpenAI, Google, xAI, Meta 26:08 - Claude 29:44 - Opus 3.5 34:30 - Sonnet 3.5 37:50 - Claude 4.0 42:02 - Criticism of Claude 54:49 - AI Safety Levels 1:05:37 - ASL-3 and ASL-4 1:09:40 - Computer use 1:19:35 - Government regulation of AI 1:38:24 - Hiring a great team 1:47:14 - Post-training 1:52:39 - Constitutional AI 1:58:05 - Machines of Loving Grace 2:17:11 - AGI timeline 2:29:46 - Programming 2:36:46 - Meaning of life 2:42:53 - Amanda Askell - Philosophy 2:45:21 - Programming advice for non-technical people 2:49:09 - Talking to Claude 3:05:41 - Prompt engineering 3:14:15 - Post-training 3:18:54 - Constitutional AI 3:23:48 - System prompts 3:29:54 - Is Claude getting dumber? 3:41:56 - Character training 3:42:56 - Nature of truth 3:47:32 - Optimal rate of failure 3:54:43 - AI consciousness 4:09:14 - AGI 4:17:52 - Chris Olah - Mechanistic Interpretability 4:22:44 - Features, Circuits, Universality 4:40:17 - Superposition 4:51:16 - Monosemanticity 4:58:08 - Scaling Monosemanticity 5:06:56 - Macroscopic behavior of neural networks 5:11:50 - Beauty of neural networks
3:58:08

Here's my conversation with Dario Amodei, CEO of Anthropic, the company that created Claude, one of the best AI systems in the world. We talk about scaling, AI safety, regulation, and a lot of super technical details about the present and future of AI and humanity. It's a 5+ hour conversation in total. Amanda Askell and Chris Olah (Chris Olah) join us for an hour each to talk about Claude's character and mechanistic interpretability, respectively. This was a fascinating, wide-ranging, super-technical, and fun conversation! First 4 hours are here on X (4 hours is current limit), and is up on everywhere else in full. Links in comment. Timestamps: 0:00 - Introduction 3:14 - Scaling laws 12:20 - Limits of LLM scaling 20:45 - Competition with OpenAI, Google, xAI, Meta 26:08 - Claude 29:44 - Opus 3.5 34:30 - Sonnet 3.5 37:50 - Claude 4.0 42:02 - Criticism of Claude 54:49 - AI Safety Levels 1:05:37 - ASL-3 and ASL-4 1:09:40 - Computer use 1:19:35 - Government regulation of AI 1:38:24 - Hiring a great team 1:47:14 - Post-training 1:52:39 - Constitutional AI 1:58:05 - Machines of Loving Grace 2:17:11 - AGI timeline 2:29:46 - Programming 2:36:46 - Meaning of life 2:42:53 - Amanda Askell - Philosophy 2:45:21 - Programming advice for non-technical people 2:49:09 - Talking to Claude 3:05:41 - Prompt engineering 3:14:15 - Post-training 3:18:54 - Constitutional AI 3:23:48 - System prompts 3:29:54 - Is Claude getting dumber? 3:41:56 - Character training 3:42:56 - Nature of truth 3:47:32 - Optimal rate of failure 3:54:43 - AI consciousness 4:09:14 - AGI 4:17:52 - Chris Olah - Mechanistic Interpretability 4:22:44 - Features, Circuits, Universality 4:40:17 - Superposition 4:51:16 - Monosemanticity 4:58:08 - Scaling Monosemanticity 5:06:56 - Macroscopic behavior of neural networks 5:11:50 - Beauty of neural networks

Lex Fridman

1,374,903 Aufrufe • vor 1 Jahr

THIS GUY BUILT AN AUTONOMOUS AI AGENT OUT OF CLAUDE CODE + OBSIDIAN and this is way more interesting than another “use AI to take notes” demo the trick is simple: Obsidian is not the writing app here. it becomes the agent’s memory, task board, and context folder. Claude Code is not just answering prompts. it reads the vault, edits files, follows instructions, and keeps moving through the work like a junior operator with a filesystem. the reusable setup looks like this: 1. create an Obsidian vault for one project 2. keep goals, rules, tasks, decisions, and references as markdown files 3. point Claude Code at the folder 4. give it a clear operating loop: read context → choose next task → execute → write back what changed 5. use the notes as persistent memory instead of re-explaining the project every chat that’s the part people miss. the “agent” is not magic. it’s the boring combination of: - local files - explicit rules - task state - write access - a model that can run through the repo/vault Obsidian makes the memory human-readable. Claude Code makes the memory executable. that combo is why the video worked: it turns a notes app into an operating surface for actual work. best use cases: - content systems - research vaults - coding projects - client ops docs - personal knowledge bases that need actions, not just storage the caveat: if your vault is messy, your agent becomes messy too. folders, naming, “done” criteria, and forbidden actions matter more than the prompt. but once the structure is clean, this is one of the easiest ways to build an agent that remembers what happened yesterday without paying for a full custom app.
10:19

THIS GUY BUILT AN AUTONOMOUS AI AGENT OUT OF CLAUDE CODE + OBSIDIAN and this is way more interesting than another “use AI to take notes” demo the trick is simple: Obsidian is not the writing app here. it becomes the agent’s memory, task board, and context folder. Claude Code is not just answering prompts. it reads the vault, edits files, follows instructions, and keeps moving through the work like a junior operator with a filesystem. the reusable setup looks like this: 1. create an Obsidian vault for one project 2. keep goals, rules, tasks, decisions, and references as markdown files 3. point Claude Code at the folder 4. give it a clear operating loop: read context → choose next task → execute → write back what changed 5. use the notes as persistent memory instead of re-explaining the project every chat that’s the part people miss. the “agent” is not magic. it’s the boring combination of: - local files - explicit rules - task state - write access - a model that can run through the repo/vault Obsidian makes the memory human-readable. Claude Code makes the memory executable. that combo is why the video worked: it turns a notes app into an operating surface for actual work. best use cases: - content systems - research vaults - coding projects - client ops docs - personal knowledge bases that need actions, not just storage the caveat: if your vault is messy, your agent becomes messy too. folders, naming, “done” criteria, and forbidden actions matter more than the prompt. but once the structure is clean, this is one of the easiest ways to build an agent that remembers what happened yesterday without paying for a full custom app.

kocer

30,403 Aufrufe • vor 1 Monat

Let me save you hours of testing frontends. If you're ever working on a front-end, instead of writing tests, and adding puppeteer slop to your repo 1. Get an llm to write you with whatever needs to be tested 2. Copy that, go to browser 3. Open localhost with your selected app 4. Use Claude Chrome Extension or Parchi 5. Send it the prompt 6. QA engineering, there you go. Use models results and pass it back to your coding agent to fix whatever is flagged.
0:42

Let me save you hours of testing frontends. If you're ever working on a front-end, instead of writing tests, and adding puppeteer slop to your repo 1. Get an llm to write you with whatever needs to be tested 2. Copy that, go to browser 3. Open localhost with your selected app 4. Use Claude Chrome Extension or Parchi 5. Send it the prompt 6. QA engineering, there you go. Use models results and pass it back to your coding agent to fix whatever is flagged.

0xSero

110,007 Aufrufe • vor 6 Monaten

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.
8:17

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The Startup Ideas Podcast (SIP) 🧃

13,598 Aufrufe • vor 1 Monat

THE 64 MINUTE OPENAI CODEX MASTERCLASS IS HERE if you've been meaning to learn Codex, this is the episode for you, we cover: 1/ Claude vs Codex (what's better?) 2/How to run Claude Code inside Codex (really cool) 3/Why GPT 5.5 changed everything for browser agents 4/How to create skills (reusable agents you build once and call by name forever) 5/How to connect Notion with surgical permissions (one database, not the whole workspace) 6/How to use Remotion inside Codex to create videos 7/ How to one-shot full mobile apps in Swift 8/The 4 projects to run on day one to get up to speed fast shoutout to Riley Brown for coming onto The Startup Ideas Podcast (SIP) 🧃 for the 5th time. every episode he delivers. this one is the Codex masterclass. if you've been meaning to learn Codex, this is the episode. 100% free i just want to see you build your ideas. watch
1:04:40

THE 64 MINUTE OPENAI CODEX MASTERCLASS IS HERE if you've been meaning to learn Codex, this is the episode for you, we cover: 1/ Claude vs Codex (what's better?) 2/How to run Claude Code inside Codex (really cool) 3/Why GPT 5.5 changed everything for browser agents 4/How to create skills (reusable agents you build once and call by name forever) 5/How to connect Notion with surgical permissions (one database, not the whole workspace) 6/How to use Remotion inside Codex to create videos 7/ How to one-shot full mobile apps in Swift 8/The 4 projects to run on day one to get up to speed fast shoutout to Riley Brown for coming onto The Startup Ideas Podcast (SIP) 🧃 for the 5th time. every episode he delivers. this one is the Codex masterclass. if you've been meaning to learn Codex, this is the episode. 100% free i just want to see you build your ideas. watch

GREG ISENBERG

199,366 Aufrufe • vor 3 Monaten

Your one-minute clock starts now. Prompt 1 to Grok: "Review the video in the post. Create a detailed project requirements document to exactly recreate the app in the video" - about 15 seconds of typing Prompt 2 to Claude Code: "Go into planning mode and create a detailed plan to implement the app described in the attached PRD" - about 15 seconds of typing. Although I did have to come back and type "1" to give it permission to execute the plan. Prompt 3 to Claude Code: "Push this to a public repo." - about 5 seconds of typing All coding about 60 seconds of my time. The longest part was trying to figure out how to screen capture a video with system audio. That flummoxed me for three to four minutes.
0:36

Your one-minute clock starts now. Prompt 1 to Grok: "Review the video in the post. Create a detailed project requirements document to exactly recreate the app in the video" - about 15 seconds of typing Prompt 2 to Claude Code: "Go into planning mode and create a detailed plan to implement the app described in the attached PRD" - about 15 seconds of typing. Although I did have to come back and type "1" to give it permission to execute the plan. Prompt 3 to Claude Code: "Push this to a public repo." - about 5 seconds of typing All coding about 60 seconds of my time. The longest part was trying to figure out how to screen capture a video with system audio. That flummoxed me for three to four minutes.

Wayne Culbreth

615,120 Aufrufe • vor 4 Monaten

Want a free private AI agent on your laptop? Here’s the simple setup. 👇 1. Install Hermes Agent from GitHub. 2. Install Ollama. 3. Download Gemma 4 26B. 4. Use Docker to keep everything contained. 5. Add Firecrawl so the agent can research the web. 6. Connect Telegram so you can chat with it from your phone. 7. Turn on context compression so it stays sharp. 8. Set the daily reset for 4 AM so it refreshes while you sleep. What you get at the end: → local AI agent → private workflow → web research built in → self improving skills → no monthly model rental That is a serious setup for anyone building with AI. Save this video, you’ll have the easiest beginner roadmap to follow later. Want the SOP? DM me. 💬
7:27

Want a free private AI agent on your laptop? Here’s the simple setup. 👇 1. Install Hermes Agent from GitHub. 2. Install Ollama. 3. Download Gemma 4 26B. 4. Use Docker to keep everything contained. 5. Add Firecrawl so the agent can research the web. 6. Connect Telegram so you can chat with it from your phone. 7. Turn on context compression so it stays sharp. 8. Set the daily reset for 4 AM so it refreshes while you sleep. What you get at the end: → local AI agent → private workflow → web research built in → self improving skills → no monthly model rental That is a serious setup for anyone building with AI. Save this video, you’ll have the easiest beginner roadmap to follow later. Want the SOP? DM me. 💬

Julian Goldie SEO

31,292 Aufrufe • vor 3 Monaten