Загрузка видео...

Не удалось загрузить видео

На главную

The underrated Codex pattern: stop asking one thread to hold the whole universe. OpenAI's jason talks about thread managers, threads that talk to other threads, Slack context, hourly loops, and feedback IDs. The win is not just parallelism. It is better-scoped context. Join us in the Token Billionaires Lounge,...

MilksandMatcha's profile picture

Sarah Chieng

26,867 subscribers

83,077 просмотров • 1 месяц назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

The hard part of agent loops is not starting them! It’s knowing when to move up a layer, and when to come back down. swyx explains the operator skill behind useful loops: automate repeatable work, watch for failure, drop into the problem when reliability breaks, then climb back up once the system is sound. That flexibility (not token volume for its own sake) is the key to productive loops. Join us in the Token Billionaires Lounge, presented by Cerebras and AI Engineer
7:34

The hard part of agent loops is not starting them! It’s knowing when to move up a layer, and when to come back down. swyx explains the operator skill behind useful loops: automate repeatable work, watch for failure, drop into the problem when reliability breaks, then climb back up once the system is sound. That flexibility (not token volume for its own sake) is the key to productive loops. Join us in the Token Billionaires Lounge, presented by Cerebras and AI Engineer

Sarah Chieng

202,991 просмотров • 1 месяц назад

🧵 Slack sync Sync Slack threads to Linear issues so that the conversation in Slack is mirrored in a comment thread in Linear. Replies, screenshots, and files immediately sync and Linear posts updates to the thread when the issue is completed, canceled, or re-opened.
1:51

🧵 Slack sync Sync Slack threads to Linear issues so that the conversation in Slack is mirrored in a comment thread in Linear. Replies, screenshots, and files immediately sync and Linear posts updates to the thread when the issue is completed, canceled, or re-opened.

Linear

66,579 просмотров • 3 лет назад

I just built an AI ghostwriter that writes threads just like you (and doesn't sound like it was written by AI) just give it a headline + context and watch it: – learn your writing style, tone, vocabulary, and thread structure – write the entire thread just how you would write it – generate 5 viral hook variations to choose from reply "thread" and I'll DM you the walkthrough (must be following)
1:02

I just built an AI ghostwriter that writes threads just like you (and doesn't sound like it was written by AI) just give it a headline + context and watch it: – learn your writing style, tone, vocabulary, and thread structure – write the entire thread just how you would write it – generate 5 viral hook variations to choose from reply "thread" and I'll DM you the walkthrough (must be following)

Tyler

28,137 просмотров • 1 год назад

Level up your engineering team's collaboration with OpenAI's new Codex Slack integration. 🚀 Just tag Codex to answer questions, fix bugs, and explore new ideas, right from a team channel or thread. 💻 ✨ Learn more about the OpenAI Codex app in the Slack Marketplace.
0:35

Level up your engineering team's collaboration with OpenAI's new Codex Slack integration. 🚀 Just tag Codex to answer questions, fix bugs, and explore new ideas, right from a team channel or thread. 💻 ✨ Learn more about the OpenAI Codex app in the Slack Marketplace.

Slack

41,973 просмотров • 10 месяцев назад

I asked jason (DevEx at OpenAI): “What’s the craziest thing Codex did for you?” Here’s his answer: “I was on a bike ride when a coworker asked me to fix a launch video. So I connected remotely from my phone and asked Codex to use computer use to edit the video, export it, and post it back to Slack. Twenty minutes later, there was a new video in the Slack thread. Then I told Codex: ‘Every 30 minutes, check the thread for feedback and export V2, V3, V4.’ By the time I got home, the launch video was greenlit.” Codex had handled the revisions by repeatedly checking Slack for feedback. 📌 Watch the full episode here:
0:36

I asked jason (DevEx at OpenAI): “What’s the craziest thing Codex did for you?” Here’s his answer: “I was on a bike ride when a coworker asked me to fix a launch video. So I connected remotely from my phone and asked Codex to use computer use to edit the video, export it, and post it back to Slack. Twenty minutes later, there was a new video in the Slack thread. Then I told Codex: ‘Every 30 minutes, check the thread for feedback and export V2, V3, V4.’ By the time I got home, the launch video was greenlit.” Codex had handled the revisions by repeatedly checking Slack for feedback. 📌 Watch the full episode here:

Peter Yang

79,504 просмотров • 1 месяц назад

This n8n workflow turns ANY viral YouTube video into a banger X thread automatically. The AI agent is trained on threads that have gotten 16M+ views. All you need to do is drop a keyword, and you get viral-ready threads. Follow + comment "THREAD" and I'll dm the full workflow.
5:11

This n8n workflow turns ANY viral YouTube video into a banger X thread automatically. The AI agent is trained on threads that have gotten 16M+ views. All you need to do is drop a keyword, and you get viral-ready threads. Follow + comment "THREAD" and I'll dm the full workflow.

Tom

70,061 просмотров • 1 год назад

Your engineering team is about to snap. And your AI coding agent is making it worse. Introducing CodeRabbit Agent for Slack 🎉 A second brain for engineering teams. Because your tribal knowledge lives in Slack threads nobody can find. At CodeRabbit, we review millions of PRs every week and know how ace engineering teams operate on the planet. The same three things slow every team we see: - Context and decisions that live elsewhere. - Lack of a team-level durable knowledge base - And a trust layer that gives a safety net to your teams Built for Agentic SDLC workflows, CodeRabbit Agent for Slack solves all three problems in one shot while enabling teams to collaborate in real-time with the Agent. CodeRabbit Agent is Slack-native and builds your team’s operating context from every thread, every decision, every conversation your team has ever had. Make your team’s context compound!
1:37

Your engineering team is about to snap. And your AI coding agent is making it worse. Introducing CodeRabbit Agent for Slack 🎉 A second brain for engineering teams. Because your tribal knowledge lives in Slack threads nobody can find. At CodeRabbit, we review millions of PRs every week and know how ace engineering teams operate on the planet. The same three things slow every team we see: - Context and decisions that live elsewhere. - Lack of a team-level durable knowledge base - And a trust layer that gives a safety net to your teams Built for Agentic SDLC workflows, CodeRabbit Agent for Slack solves all three problems in one shot while enabling teams to collaborate in real-time with the Agent. CodeRabbit Agent is Slack-native and builds your team’s operating context from every thread, every decision, every conversation your team has ever had. Make your team’s context compound!

Harjot Gill

4,777,289 просмотров • 4 месяцев назад

This argument conveniently demands “full context” only when it is being used to defend him, while completely ignoring the context surrounding his repeated treatment of Nomy. If we are talking about context, then let’s talk about all of it. Tram didn’t simply wake up one day and become the “victim” of Nomy’s reaction. He has repeatedly provoked her. He explicitly said he would frustrate her and turn the house against her. That is not an innocent misunderstanding. That is an expressed intention to antagonise someone and isolate them socially. And this is not just about one argument. There has also been a repeated pattern of age-shaming and body-shaming Nomy. The “he only said ‘somewhere is smelling’” defence is also deliberately narrow. Context is not just about the exact wording of one sentence. Context includes the pattern of interactions that led to the confrontation, what had been said before it, and what each person had been doing throughout the situation. You cannot demand nuance for Tram while denying Nomy the same nuance. #BBNaija
0:33

This argument conveniently demands “full context” only when it is being used to defend him, while completely ignoring the context surrounding his repeated treatment of Nomy. If we are talking about context, then let’s talk about all of it. Tram didn’t simply wake up one day and become the “victim” of Nomy’s reaction. He has repeatedly provoked her. He explicitly said he would frustrate her and turn the house against her. That is not an innocent misunderstanding. That is an expressed intention to antagonise someone and isolate them socially. And this is not just about one argument. There has also been a repeated pattern of age-shaming and body-shaming Nomy. The “he only said ‘somewhere is smelling’” defence is also deliberately narrow. Context is not just about the exact wording of one sentence. Context includes the pattern of interactions that led to the confrontation, what had been said before it, and what each person had been doing throughout the situation. You cannot demand nuance for Tram while denying Nomy the same nuance. #BBNaija

NOMY #BBNaija

85,287 просмотров • 1 месяц назад

Most people use Claude Code like a chatbot. That is the mistake. The real power is not in better prompts. It is in controlling the session. /init gives the project memory. /memory keeps the rules alive. /clear removes old context. /compact saves the important parts. /context shows where the tokens go. /rewind fixes bad turns. /plan stops blind edits. /model matches the brain to the task. Claude Code gets 10x better when you stop letting the conversation run itself. Memory. Context. Boundaries. Rollback. Planning. That is the system. Stop asking Claude Code to “just do it”. Teach it what to remember, what to forget, and when to stop. Bookmark this before your next session turns into 40 messages of context debt.
0:33

Most people use Claude Code like a chatbot. That is the mistake. The real power is not in better prompts. It is in controlling the session. /init gives the project memory. /memory keeps the rules alive. /clear removes old context. /compact saves the important parts. /context shows where the tokens go. /rewind fixes bad turns. /plan stops blind edits. /model matches the brain to the task. Claude Code gets 10x better when you stop letting the conversation run itself. Memory. Context. Boundaries. Rollback. Planning. That is the system. Stop asking Claude Code to “just do it”. Teach it what to remember, what to forget, and when to stop. Bookmark this before your next session turns into 40 messages of context debt.

Fluixo

19,226 просмотров • 2 месяцев назад

OpenAI staff engineer Ryan Lopopolo banned his team from touching their editors. his thesis: code is free. context, guardrails, and feedback loops are the moat. I wrote 8,000 words on how to build that harness. this is the playbook.
46:20

OpenAI staff engineer Ryan Lopopolo banned his team from touching their editors. his thesis: code is free. context, guardrails, and feedback loops are the moat. I wrote 8,000 words on how to build that harness. this is the playbook.

Rohit

309,091 просмотров • 4 месяцев назад

TBPN asked me how Zapier keeps AI from drowning in data. Short answer: we built it a brain. Three layers: 1. Company-level source of truth (strategy, values, ICP). Curated by me and a handful of senior leaders 2. Team-level context that cascades down 3. Individual context, private to each person. Meeting transcripts, Slack threads, project docs, etc. So when anyone at Zapier talks to AI, they're not starting from scratch. They point the SDK at specific documents against the backdrop of that brain. Better inputs, better AI. Thanks to TBPN for having me on
1:14

TBPN asked me how Zapier keeps AI from drowning in data. Short answer: we built it a brain. Three layers: 1. Company-level source of truth (strategy, values, ICP). Curated by me and a handful of senior leaders 2. Team-level context that cascades down 3. Individual context, private to each person. Meeting transcripts, Slack threads, project docs, etc. So when anyone at Zapier talks to AI, they're not starting from scratch. They point the SDK at specific documents against the backdrop of that brain. Better inputs, better AI. Thanks to TBPN for having me on

Wade Foster

35,638 просмотров • 4 месяцев назад

Biggest lesson from OpenClaw is that a good teammate doesn't start from scratch everytime you check in. They remember what was decided, what's still open, and proactively help you. Today we launched heartbeats in Codex: automations that maintain context inside a single thread over time. Instead of each run starting fresh, Codex wakes up in the same conversation, with the history and context it needs already in place. You can also have it schedule its own next steps – just ask Codex. Think about the overhead that quietly accumulates every morning: scanning Slack channels, catching up on email, piecing together what moved overnight. With a heartbeat, you offload that once, and wake up to a brief already waiting in a pinned thread. If you want to try turning Codex into a chief of staff: connect Slack, Gmail, and Notion, and paste the following prompt into codex: Please check Matt Slack Gmail Notion and write me a morning brief every weekday at 9am in this thread. I want you to collapse all the chaos at work into a single note every morning over some coffee ☕️
0:29

Biggest lesson from OpenClaw is that a good teammate doesn't start from scratch everytime you check in. They remember what was decided, what's still open, and proactively help you. Today we launched heartbeats in Codex: automations that maintain context inside a single thread over time. Instead of each run starting fresh, Codex wakes up in the same conversation, with the history and context it needs already in place. You can also have it schedule its own next steps – just ask Codex. Think about the overhead that quietly accumulates every morning: scanning Slack channels, catching up on email, piecing together what moved overnight. With a heartbeat, you offload that once, and wake up to a brief already waiting in a pinned thread. If you want to try turning Codex into a chief of staff: connect Slack, Gmail, and Notion, and paste the following prompt into codex: Please check Matt Slack Gmail Notion and write me a morning brief every weekday at 9am in this thread. I want you to collapse all the chaos at work into a single note every morning over some coffee ☕️

pash

119,552 просмотров • 5 месяцев назад

"I used a billion tokens this week. I'm not even in the top 100 Codex users at OpenAI." We sat down with jason (creator of Instructor, now on OpenAI's Developer Experience team) to talk about how zero-latency inference is changing the way engineers work.
0:37

"I used a billion tokens this week. I'm not even in the top 100 Codex users at OpenAI." We sat down with jason (creator of Instructor, now on OpenAI's Developer Experience team) to talk about how zero-latency inference is changing the way engineers work.

Cerebras

93,023 просмотров • 5 месяцев назад

The Bible in its context is not a Christian book. The Bible in its nature is a catholic book which was edited and given to us in the context of what it is. - Joshua Maponga
2:32

The Bible in its context is not a Christian book. The Bible in its nature is a catholic book which was edited and given to us in the context of what it is. - Joshua Maponga

Typical African

12,986 просмотров • 5 месяцев назад

94% OF ENGINEERING ORGS USE AI. ONLY 6% SCALE IT The missing link is context and governance. That’s exactly what Atlassian is going after with its new agentic engineering stack: Code Context + governed agent loops in Atlassian Jira + DX measurement. The idea is simple: make agents a native part of your engineering system instead of a side quest in a terminal. > Code Context grounds them in your architecture > Governed loops take work from backlog to pull request > DX measures the impact And the data backs up the context thesis: DX found context-rich AI teams shipped ~64% more per developer 👊 A pretty strong signal that context is becoming one of the biggest leverage points in agentic engineering.
1:00

94% OF ENGINEERING ORGS USE AI. ONLY 6% SCALE IT The missing link is context and governance. That’s exactly what Atlassian is going after with its new agentic engineering stack: Code Context + governed agent loops in Atlassian Jira + DX measurement. The idea is simple: make agents a native part of your engineering system instead of a side quest in a terminal. > Code Context grounds them in your architecture > Governed loops take work from backlog to pull request > DX measures the impact And the data backs up the context thesis: DX found context-rich AI teams shipped ~64% more per developer 👊 A pretty strong signal that context is becoming one of the biggest leverage points in agentic engineering.

Charly Wargnier ♨️

29,622 просмотров • 3 дней назад

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.
0:34

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

SIBYL

86,148 просмотров • 3 месяцев назад

Prime Intellect engineer: "everyone's bragging about a million-token context. here's what they don't tell you. at 256k tokens GPT-5.5 scores 80% on retrieval. push it to a million and it drops to 36%. the model accepts the context, it just can't reason across it. people call it context rot." in a 20-minute talk he explains why bigger context windows won't save your agents. continual learning + training on your own traces + real environments - that's the fix. Watch the talk, then save!
19:43

Prime Intellect engineer: "everyone's bragging about a million-token context. here's what they don't tell you. at 256k tokens GPT-5.5 scores 80% on retrieval. push it to a million and it drops to 36%. the model accepts the context, it just can't reason across it. people call it context rot." in a 20-minute talk he explains why bigger context windows won't save your agents. continual learning + training on your own traces + real environments - that's the fix. Watch the talk, then save!

Carnage

749,152 просмотров • 2 месяцев назад

Context vs. Graphs, clearly explained! context engineering is great, but it has a ceiling: you can make one window perfect. there is still only one of it. every technique on that layer is rationing the same scarce thing. compact, retrieve less, delete, defer. all of it is deciding what to drop. Graph engineering fixes this by moving the decision up a layer: not what goes in the window, but how many windows there are and what each one is for. you need both. here's how it works: ↳ inside a window: context engineering. what loads, in what order, what gets compacted ↳ between windows: the graph. how many lanes, what each one is allowed to see, what comes back Prompts → Context → Harness → Loops → Graphs each lane gets a clean window, nothing in one competes with anything in another, and your main thread stops filling up. the trick is being selective about what comes back. a subagent reads six thousand tokens of files and hands you a four hundred token summary. that ratio is the whole point. send back the raw material instead and you have moved the problem, not solved it. one thing to know before you scale it. not everything survives compaction equally, and almost nobody knows the table. ↳ the project-root rules file and auto memory are re-injected from disk. they come back intact ↳ path-scoped rules and nested rules files live in message history. they get summarized away and do not return until a matching file is read again so a rule that genuinely must persist cannot be path-scoped. move it to the root and pay the always-loaded cost, or accept that it is advisory in any long session. and the one that eats whole nights: shared context makes parallel agents converge. four auditors on one window produce one opinion with three echoes. you paid four times for it. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓
0:53

Context vs. Graphs, clearly explained! context engineering is great, but it has a ceiling: you can make one window perfect. there is still only one of it. every technique on that layer is rationing the same scarce thing. compact, retrieve less, delete, defer. all of it is deciding what to drop. Graph engineering fixes this by moving the decision up a layer: not what goes in the window, but how many windows there are and what each one is for. you need both. here's how it works: ↳ inside a window: context engineering. what loads, in what order, what gets compacted ↳ between windows: the graph. how many lanes, what each one is allowed to see, what comes back Prompts → Context → Harness → Loops → Graphs each lane gets a clean window, nothing in one competes with anything in another, and your main thread stops filling up. the trick is being selective about what comes back. a subagent reads six thousand tokens of files and hands you a four hundred token summary. that ratio is the whole point. send back the raw material instead and you have moved the problem, not solved it. one thing to know before you scale it. not everything survives compaction equally, and almost nobody knows the table. ↳ the project-root rules file and auto memory are re-injected from disk. they come back intact ↳ path-scoped rules and nested rules files live in message history. they get summarized away and do not return until a matching file is read again so a rule that genuinely must persist cannot be path-scoped. move it to the root and pay the always-loaded cost, or accept that it is advisory in any long session. and the one that eats whole nights: shared context makes parallel agents converge. four auditors on one window produce one opinion with three echoes. you paid four times for it. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Hanako

36,970 просмотров • 22 дней назад