Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

you wrote a long careful note so it would remember the thing properly the note is the part that does not load what loads at the start of every session is the index line, the one sentence summary, and only the first two hundred lines of it or the... first twenty five kilobytes, whichever runs out first the topic files underneath are read on demand, which means only if something in that one line makes it go and open them i checked mine: thirty nine index lines loading every session, thirty nine topic files loading none of the time the detail you were careful about is not context it is a footnote your agent has to choose to open and the sentence you dashed off in three seconds is the whole memoryshow more

Lagosaur

3,193 subscribers

28,369 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

8 Comments

nathan-james1 month ago

あー、そのあるあるすごいわかる！大事な部分が読めないって焦るよね。😅

Britt Ong1 month ago

Em đây chỉ muốn có Hiệp cạnh bên

Huysolo1 month ago

Context optimization is just an elaborate illusion when system prompts treat detailed notes like unread footnotes

施工現場の拾い物1 month ago

��のノートの準備、すごく丁寧だね！私もそれくらい工夫してみたいな〜。

sophia f,1 month ago

Facts!

Joey1 month ago

Plus, who knows what will happen in the futured.

ノブユキ1 month ago

ノートの部分が読み込まれないと不安になるよね。その間に別の方法で復習するしかないかな…。

佐藤 ��也1 month ago

その長いノート、どんなことが書かれていたのか気になります！記憶の残し方、羨ましいです✨

Related Videos

you added the new rule and left the old one exactly where it was you did not update anything, you now have two rules both files load at the start of every session, both are context rather than configuration, and when two instructions contradict each other the documented behaviour is that the model may pick one arbitrarily so the older, more specific, more confidently worded one wins about as often as the correction does i audited a real directory: thirty nine stored memories, five of them carrying a claim the same folder marks as disproven, all thirty nine loading every morning you were not correcting it you were giving the old answer a vote

you added the new rule and left the old one exactly where it was you did not update anything, you now have two rules both files load at the start of every session, both are context rather than configuration, and when two instructions contradict each other the documented behaviour is that the model may pick one arbitrarily so the older, more specific, more confidently worded one wins about as often as the correction does i audited a real directory: thirty nine stored memories, five of them carrying a claim the same folder marks as disproven, all thirty nine loading every morning you were not correcting it you were giving the old answer a vote

Lagosaur

20,245 views • 1 month ago

It is becoming f*cking dangerous: Claude Code has kept its own memory folder since February and you've probably never opened it 1. Open any project in Claude Code and type /memory 2. Check the auto memory toggle, it is on by default in local sessions 3. Pick the option to open the auto memory folder 4. Read MEMORY.md first, it is the index, one line per memory 5. Look at the files: one memory each, typed user, feedback, project or reference 6. Tell Claude "remember: always use pnpm, not npm" and watch it save a new memory 7. Edit or delete any wrong memory, it is plain markdown Only the first 200 lines or 25KB of MEMORY.md load each session, Claude opens the topic files when needed Ask Claude to remember what matters once, it stays until you or Claude edit or delete it Full guide in the article below

It is becoming f*cking dangerous: Claude Code has kept its own memory folder since February and you've probably never opened it 1. Open any project in Claude Code and type /memory 2. Check the auto memory toggle, it is on by default in local sessions 3. Pick the option to open the auto memory folder 4. Read MEMORY.md first, it is the index, one line per memory 5. Look at the files: one memory each, typed user, feedback, project or reference 6. Tell Claude "remember: always use pnpm, not npm" and watch it save a new memory 7. Edit or delete any wrong memory, it is plain markdown Only the first 200 lines or 25KB of MEMORY.md load each session, Claude opens the topic files when needed Ask Claude to remember what matters once, it stays until you or Claude edit or delete it Full guide in the article below

plusxbt

19,528 views • 7 days ago

you opened a memory file and could not tell when it was written there is a field for that, and some of those files will never have it the timestamp goes into frontmatter, and it is only added to files that already begin with frontmatter, it is never added to a file that has none so a note created without those three dashes at the top is undateable for the rest of its life, and on screen it looks exactly like the ones that are current sixteen of my thirty nine are sitting there with no date on them right now you are not reading a memory you are reading an undated claim that loads before you speak

you opened a memory file and could not tell when it was written there is a field for that, and some of those files will never have it the timestamp goes into frontmatter, and it is only added to files that already begin with frontmatter, it is never added to a file that has none so a note created without those three dashes at the top is undateable for the rest of its life, and on screen it looks exactly like the ones that are current sixteen of my thirty nine are sitting there with no date on them right now you are not reading a memory you are reading an undated claim that loads before you speak

Lagosaur

31,471 views • 1 month ago

Orchestrators vs. Graphs, clearly explained! orchestrators are great, and everyone builds one first. here is the ceiling: an orchestrator sits above the work and routes every message. five agents report to it. it reads all five. it decides what each one does next, and reads all five replies. that is ten trips through one context, and by the fifth agent that context has read four reports, five instructions and its own reasoning about all of them. Graph engineering fixes this by removing the seat: not a better router, but no router at all. you need both, and here is the sentence that resolves the whole confusion: an orchestrator sits above the work and holds all of it. a graph is the shape of the work, and holds none of it. ↳ above the work: one context that has to see everything before anything ships ↳ inside the work: a splitter that hands out and lets go, and a merge that reads nothing Prompts → Context → Harness → Loops → Graphs the coordination did not disappear. it moved into the edges, where it costs nothing and cannot get tired. the trick is noticing what you actually built. if one node has to see every result before the run can finish, you did not remove the bottleneck. you hired it, gave it the longest context in the system, and made it the thing you were counting on to stay sharp. one thing to know before you scale it. an orchestrator degrades in the one way nothing catches. ↳ it does not crash, time out or return an error. it stays up and keeps routing ↳ it just starts routing worse, somewhere around the fifth report, and every downstream agent does exactly what it was told that last one catches careful people. you can have perfect isolation on every worker and still have one window quietly drifting at the top, and the traces will all look clean because each worker did its job. and the one that eats whole nights: the merge is where this shows up first. ranking five findings is not judgment, it is a sort. if a model is doing it, you are paying a model to read five reports so it can put them in an order that three lines of code would have got right, and now that model has read everything too. 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 ↓

Orchestrators vs. Graphs, clearly explained! orchestrators are great, and everyone builds one first. here is the ceiling: an orchestrator sits above the work and routes every message. five agents report to it. it reads all five. it decides what each one does next, and reads all five replies. that is ten trips through one context, and by the fifth agent that context has read four reports, five instructions and its own reasoning about all of them. Graph engineering fixes this by removing the seat: not a better router, but no router at all. you need both, and here is the sentence that resolves the whole confusion: an orchestrator sits above the work and holds all of it. a graph is the shape of the work, and holds none of it. ↳ above the work: one context that has to see everything before anything ships ↳ inside the work: a splitter that hands out and lets go, and a merge that reads nothing Prompts → Context → Harness → Loops → Graphs the coordination did not disappear. it moved into the edges, where it costs nothing and cannot get tired. the trick is noticing what you actually built. if one node has to see every result before the run can finish, you did not remove the bottleneck. you hired it, gave it the longest context in the system, and made it the thing you were counting on to stay sharp. one thing to know before you scale it. an orchestrator degrades in the one way nothing catches. ↳ it does not crash, time out or return an error. it stays up and keeps routing ↳ it just starts routing worse, somewhere around the fifth report, and every downstream agent does exactly what it was told that last one catches careful people. you can have perfect isolation on every worker and still have one window quietly drifting at the top, and the traces will all look clean because each worker did its job. and the one that eats whole nights: the merge is where this shows up first. ranking five findings is not judgment, it is a sort. if a model is doing it, you are paying a model to read five reports so it can put them in an order that three lines of code would have got right, and now that model has read everything too. 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

44,226 views • 1 month ago

STOP TREATING YOUR OBSIDIAN VAULT AS AI MEMORY. WITHOUT ONE ROUTING FILE, CLAUDE IS BURNING TOKENS ON NOISE YOU FORGOT YOU SAVED. a folder full of markdown does not make Claude smart. what makes it smart is what your agent can find without rereading the whole vault. storage: write → tag → graph → agent scans everything the model touches the entire vault, hallucinates half of it, forgets by the next session. memory: write → index → route → agent opens two files the model reads the index first, follows one path, answers with a link back to the note. i have rebuilt my Obsidian vault three times this year. the first two collapsed inside a month because Claude kept guessing which folder to open. the third one holds because the first thing i ship now is the routing file. Markdown, links, and the graph view are not what changed. what changed was a one-line description per folder, written for the agent, kept current, loaded before any retrieval call. if your agent still starts every session by scanning your whole vault, you are running storage. write the routing file today.

STOP TREATING YOUR OBSIDIAN VAULT AS AI MEMORY. WITHOUT ONE ROUTING FILE, CLAUDE IS BURNING TOKENS ON NOISE YOU FORGOT YOU SAVED. a folder full of markdown does not make Claude smart. what makes it smart is what your agent can find without rereading the whole vault. storage: write → tag → graph → agent scans everything the model touches the entire vault, hallucinates half of it, forgets by the next session. memory: write → index → route → agent opens two files the model reads the index first, follows one path, answers with a link back to the note. i have rebuilt my Obsidian vault three times this year. the first two collapsed inside a month because Claude kept guessing which folder to open. the third one holds because the first thing i ship now is the routing file. Markdown, links, and the graph view are not what changed. what changed was a one-line description per folder, written for the agent, kept current, loaded before any retrieval call. if your agent still starts every session by scanning your whole vault, you are running storage. write the routing file today.

kocer

17,240 views • 2 months ago

you let the old sessions get cleaned up, they were only taking space the conversations went, the conclusions drawn from them did not transcripts are deleted after the retention period, and the memory directory is excluded from that sweep on purpose, so a note stays until you or the model edits it which means the evidence has an expiry date and the verdict does not on the directory i audited, thirty nine stored conclusions, sixteen of them with no date on the file at all you did not clear anything you deleted the part you could have checked and kept the part that argues the transcript was the receipt the memory is the story about it

you let the old sessions get cleaned up, they were only taking space the conversations went, the conclusions drawn from them did not transcripts are deleted after the retention period, and the memory directory is excluded from that sweep on purpose, so a note stays until you or the model edits it which means the evidence has an expiry date and the verdict does not on the directory i audited, thirty nine stored conclusions, sixteen of them with no date on the file at all you did not clear anything you deleted the part you could have checked and kept the part that argues the transcript was the receipt the memory is the story about it

Lagosaur

34,063 views • 1 month ago

Boris Cherny gave Claude Code a memory that has no database, no indexing, no setup, and 80% of Anthropic runs on it a CLAUDE.md "gets automatically read into context at the start of every session" 12:48 - CLAUDE.md loads into memory every session 13:15 - Keep memory short or it burns your context 15:48 - Memory stacks from you to your whole company 17:30 - The memory command shows what Claude remembers 19:33 - Hit pound and Claude remembers it forever the whole memory layer is files → drop a CLAUDE.md in your repo and Claude reads it in on every session → nest more in subfolders and it pulls them only where it works → stack them personal to project to enterprise so one config serves the whole team → hit the pound key mid task and Claude writes the new fact into memory itself the best coding agent's memory was never a database, it was markdown you can open and edit

Boris Cherny gave Claude Code a memory that has no database, no indexing, no setup, and 80% of Anthropic runs on it a CLAUDE.md "gets automatically read into context at the start of every session" 12:48 - CLAUDE.md loads into memory every session 13:15 - Keep memory short or it burns your context 15:48 - Memory stacks from you to your whole company 17:30 - The memory command shows what Claude remembers 19:33 - Hit pound and Claude remembers it forever the whole memory layer is files → drop a CLAUDE.md in your repo and Claude reads it in on every session → nest more in subfolders and it pulls them only where it works → stack them personal to project to enterprise so one config serves the whole team → hit the pound key mid task and Claude writes the new fact into memory itself the best coding agent's memory was never a database, it was markdown you can open and edit

NO1ennn

13,015 views • 3 months ago

Workflows vs. Graphs, clearly explained! workflows are great, and almost everyone has one. here is the ceiling: a workflow decides every step before it runs. you drew eight boxes in March. six months later the same three fire, every single time, and the other five have never once been reached. then a case arrives that nobody drew, and it goes to the closest wrong box. quietly, with a green status, because from the inside that looks exactly like success. Graph engineering fixes this by moving the decision: not what the steps do, but when the steps get chosen. you need both, and here is the sentence that resolves the whole confusion: a workflow decides the steps before it runs. a graph decides them while it runs. ↳ drawn in advance: the boxes, the branches, the order, the error path ↳ decided at runtime: how many units exist, what each one is allowed to see, which ones get created at all Prompts → Context → Harness → Loops → Graphs branches do not make it a graph. the branches were drawn in advance too, which means every one of them is a case you already thought of. the trick is knowing which part is allowed to be fixed. the node kinds are fixed. a splitter is a splitter, a gate is a gate, a merge is code. what is not fixed is how many of them exist this run, and that is decided after something has been read. one thing to know before you scale it. a workflow fails in a way that never pages anyone. ↳ the wrong branch ran, every check inside it passed, and the output is well formed ↳ nothing errored, because routing to the wrong box is not an error, it is a route that last one catches careful people. you cannot test your way out of it either, because the test suite was written from the same diagram that has the gap in it. and the one that eats whole nights: a workflow that has never surprised you is not stable, it is narrow. if it has run four hundred times and produced the same three shapes, it is not handling your work. it is handling the part of your work that fits it, and you have quietly stopped sending it the rest. 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 ↓

Workflows vs. Graphs, clearly explained! workflows are great, and almost everyone has one. here is the ceiling: a workflow decides every step before it runs. you drew eight boxes in March. six months later the same three fire, every single time, and the other five have never once been reached. then a case arrives that nobody drew, and it goes to the closest wrong box. quietly, with a green status, because from the inside that looks exactly like success. Graph engineering fixes this by moving the decision: not what the steps do, but when the steps get chosen. you need both, and here is the sentence that resolves the whole confusion: a workflow decides the steps before it runs. a graph decides them while it runs. ↳ drawn in advance: the boxes, the branches, the order, the error path ↳ decided at runtime: how many units exist, what each one is allowed to see, which ones get created at all Prompts → Context → Harness → Loops → Graphs branches do not make it a graph. the branches were drawn in advance too, which means every one of them is a case you already thought of. the trick is knowing which part is allowed to be fixed. the node kinds are fixed. a splitter is a splitter, a gate is a gate, a merge is code. what is not fixed is how many of them exist this run, and that is decided after something has been read. one thing to know before you scale it. a workflow fails in a way that never pages anyone. ↳ the wrong branch ran, every check inside it passed, and the output is well formed ↳ nothing errored, because routing to the wrong box is not an error, it is a route that last one catches careful people. you cannot test your way out of it either, because the test suite was written from the same diagram that has the gap in it. and the one that eats whole nights: a workflow that has never surprised you is not stable, it is narrow. if it has run four hundred times and produced the same three shapes, it is not handling your work. it is handling the part of your work that fits it, and you have quietly stopped sending it the rest. 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

16,810 views • 1 month ago

your agent has thirty tools. it calls two of them. the other twenty eight are not sitting idle somewhere. they are in the request, every request, and they are doing damage in two places at once. first the obvious one. tool schemas go into the prompt, and a schema is not a name. it is a description, a parameter list, types, required fields, an example. thirty of those is a few thousand tokens that ship with every single call, including the ones where the agent just says thanks and stops. you are paying rent on twenty eight tools that have never fired. second, and this is the one that costs more. when the request says cancel the order, the model picks by matching against everything available. four of your tools are plausible: cancel_order, refund_order, update_order, void_order. it is choosing among them based on the descriptions you wrote, one afternoon, months ago. every tool you add is another candidate in that shortlist. the twenty eight you never call are not neutral. they are noise in the one decision that determines whether the run works. > why it grows without anyone deciding to nobody adds thirty tools on purpose. you add one for a task, it works, it stays. six months later the registry is a catalogue and no one has ever removed anything, because removing a tool feels risky and adding one feels free. and there is no feedback telling you otherwise. the unused ones never error. they never appear in a failing trace. they are invisible in exactly the way that lets them accumulate. > what to actually do count calls per tool over the last thousand runs. this is one group-by and it usually shocks people. the ones at zero are pure cost. ship the tools the task needs, not the whole registry. a research phase does not need deploy. a writing phase does not need the database. swap the set between phases instead of loading everything up front. same agent, different tools, depending on where the run is. and when two tools could both plausibly answer the same request, that is not redundancy you can ignore. it is a coin flip you built into the system. the twenty eight tools are not unused. they are used every time, by the part of the run you cannot see.

your agent has thirty tools. it calls two of them. the other twenty eight are not sitting idle somewhere. they are in the request, every request, and they are doing damage in two places at once. first the obvious one. tool schemas go into the prompt, and a schema is not a name. it is a description, a parameter list, types, required fields, an example. thirty of those is a few thousand tokens that ship with every single call, including the ones where the agent just says thanks and stops. you are paying rent on twenty eight tools that have never fired. second, and this is the one that costs more. when the request says cancel the order, the model picks by matching against everything available. four of your tools are plausible: cancel_order, refund_order, update_order, void_order. it is choosing among them based on the descriptions you wrote, one afternoon, months ago. every tool you add is another candidate in that shortlist. the twenty eight you never call are not neutral. they are noise in the one decision that determines whether the run works. > why it grows without anyone deciding to nobody adds thirty tools on purpose. you add one for a task, it works, it stays. six months later the registry is a catalogue and no one has ever removed anything, because removing a tool feels risky and adding one feels free. and there is no feedback telling you otherwise. the unused ones never error. they never appear in a failing trace. they are invisible in exactly the way that lets them accumulate. > what to actually do count calls per tool over the last thousand runs. this is one group-by and it usually shocks people. the ones at zero are pure cost. ship the tools the task needs, not the whole registry. a research phase does not need deploy. a writing phase does not need the database. swap the set between phases instead of loading everything up front. same agent, different tools, depending on where the run is. and when two tools could both plausibly answer the same request, that is not redundancy you can ignore. it is a coin flip you built into the system. the twenty eight tools are not unused. they are used every time, by the part of the run you cannot see.

Hanako

24,656 views • 2 months ago

you installed it with whichever command needed the least typing that command had a scope, and the short one is the widest one user scope does not live in the project, it lives in you, and it loads in every repository you open for the rest of the year a repo you touched once in march is still being told about your database tools i counted mine: four servers, eight thousand nine hundred tokens, riding into projects that have no database and no browser you did not install a tool you set a default for every piece of work you have not started yet the shortest command in the docs and the longest reach

you installed it with whichever command needed the least typing that command had a scope, and the short one is the widest one user scope does not live in the project, it lives in you, and it loads in every repository you open for the rest of the year a repo you touched once in march is still being told about your database tools i counted mine: four servers, eight thousand nine hundred tokens, riding into projects that have no database and no browser you did not install a tool you set a default for every piece of work you have not started yet the shortest command in the docs and the longest reach

Lagosaur

21,006 views • 2 months ago

you wrote a deny rule so it could not touch the thing you cannot undo you were thinking about permission the rule does something stronger than refuse, a bare tool name in deny takes the tool out of the model's context altogether, it is never told the tool exists blocked means it asks and you say no, absent means it never reaches one line removed twenty four playwright tools and four thousand four hundred tokens i had never read you thought you were writing a guard you were writing the menu everything still on it is a choice you left open by not typing

you wrote a deny rule so it could not touch the thing you cannot undo you were thinking about permission the rule does something stronger than refuse, a bare tool name in deny takes the tool out of the model's context altogether, it is never told the tool exists blocked means it asks and you say no, absent means it never reaches one line removed twenty four playwright tools and four thousand four hundred tokens i had never read you thought you were writing a guard you were writing the menu everything still on it is a choice you left open by not typing

Lagosaur

38,416 views • 2 months ago

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: a skill is one folder with one markdown file, and Claude only reads it when your request actually matches it. You stop pasting the same instructions into every session, and you pay one line of context instead of the whole document. You just make one folder: .claude/skills/review-pr/SKILL.md here's the split: → the description is the only thing sitting in context, roughly one line per skill → the full body loads the second a request matches that description → scripts in the folder get executed, never read into context → commit the folder and every person in the repo has the skill three frontmatter lines do the heavy lifting: → allowed-tools pre-approves the tools, so it runs without a permission prompt → context: fork hands the skill to a subagent that never sees your chat → paths limits it to the files it actually belongs to Description matches. Body loads. Scripts run. JEV engineering is the same move one layer down: the forks that need no thinker (which skill, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > .claude/skills/ /SKILL.md for the repo, ~/.claude/skills/ for your own > only descriptions sit in context, the body loads on match > keep SKILL.md under 500 lines, every line is a recurring cost once loaded > description plus when_to_use is cut at 1,536 characters, put the trigger first > context: fork runs it in a subagent with no conversation history > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Set up skills in this repo from the tree above: 1. Create .claude/skills/ and move the repeated instructions out of CLAUDE.md into one skill per job. 2. Write every description as a trigger sentence first, since the listing is cut at 1,536 characters. 3. Put anything deterministic into scripts/ and pre-approve it with allowed-tools so it runs without a prompt. 4. Route fast deterministic forks (which skill, which tool, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: a skill is one folder with one markdown file, and Claude only reads it when your request actually matches it. You stop pasting the same instructions into every session, and you pay one line of context instead of the whole document. You just make one folder: .claude/skills/review-pr/SKILL.md here's the split: → the description is the only thing sitting in context, roughly one line per skill → the full body loads the second a request matches that description → scripts in the folder get executed, never read into context → commit the folder and every person in the repo has the skill three frontmatter lines do the heavy lifting: → allowed-tools pre-approves the tools, so it runs without a permission prompt → context: fork hands the skill to a subagent that never sees your chat → paths limits it to the files it actually belongs to Description matches. Body loads. Scripts run. JEV engineering is the same move one layer down: the forks that need no thinker (which skill, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > .claude/skills/ /SKILL.md for the repo, ~/.claude/skills/ for your own > only descriptions sit in context, the body loads on match > keep SKILL.md under 500 lines, every line is a recurring cost once loaded > description plus when_to_use is cut at 1,536 characters, put the trigger first > context: fork runs it in a subagent with no conversation history > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Set up skills in this repo from the tree above: 1. Create .claude/skills/ and move the repeated instructions out of CLAUDE.md into one skill per job. 2. Write every description as a trigger sentence first, since the listing is cut at 1,536 characters. 3. Put anything deterministic into scripts/ and pre-approve it with allowed-tools so it runs without a prompt. 4. Route fast deterministic forks (which skill, which tool, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

xsmryze

15,075 views • 13 days ago

you trimmed the prompt to get back under the line the prompt was never the part that grows tool results append themselves, they are large, and nobody asks you first, so a session that opened at thirty thousand crosses on turn nine and turn nine is indistinguishable from turn eight until the invoice arrives you cannot trim a conversation you have not had yet what you needed was never a shorter prompt it was one line that checks the number before the request leaves

you trimmed the prompt to get back under the line the prompt was never the part that grows tool results append themselves, they are large, and nobody asks you first, so a session that opened at thirty thousand crosses on turn nine and turn nine is indistinguishable from turn eight until the invoice arrives you cannot trim a conversation you have not had yet what you needed was never a shorter prompt it was one line that checks the number before the request leaves

Lagosaur

14,047 views • 2 months ago

you added an mcp server because it was one line in a terminal and it was one line, that part was true what it was not is one line in the conversation every tool it brought came with a name, a schema and a paragraph of prose, and all of it is re-sent on every request you make until the session ends four ordinary servers on my machine this morning: forty eight definitions, eight thousand nine hundred tokens four and a half percent of a two hundred thousand window, gone before you typed a character you are not the person who installed four tools you are the person who prepends nine thousand tokens to everything he says nobody bills you for it it comes out of the room you had left to think in

you added an mcp server because it was one line in a terminal and it was one line, that part was true what it was not is one line in the conversation every tool it brought came with a name, a schema and a paragraph of prose, and all of it is re-sent on every request you make until the session ends four ordinary servers on my machine this morning: forty eight definitions, eight thousand nine hundred tokens four and a half percent of a two hundred thousand window, gone before you typed a character you are not the person who installed four tools you are the person who prepends nine thousand tokens to everything he says nobody bills you for it it comes out of the room you had left to think in

Lagosaur

13,490 views • 2 months ago

Agents vs. Graphs, clearly explained! spawning more agents is great, but it has a ceiling nobody says out loud: five agents is a count. a graph is a shape. only one of them changes the answer. point five agents at the same pile with the same window and they converge. the first one writes a finding, the rest read it, and all five reports centre on the same thing. you paid five times for one opinion with four echoes. Graph engineering fixes this by moving the decision up a layer: not how many agents, but who is allowed to look at what. you need both. here's how it works: ↳ the count buys you throughput. five things happening instead of one ↳ the shape buys you coverage. five different things happening instead of the same one five times Prompts → Context → Harness → Agents → Graphs the node that does this is the splitter, and it decides more than any other node in the system. cut a repository by folder and four workers audit the same three files. cut it by blast radius and each one sees something the others cannot. the trick is being selective about what each lane is allowed to see. separate contexts are not a nice-to-have, they are the mechanism. if two agents are meant to produce different things, they must not share a window. if they are meant to produce the same thing, you did not need two agents. one thing to know before you scale it. a branch that throws does not reject the batch. it resolves to null, and that is the containment. which means your merge quietly receives a short list. ↳ filter the nulls before the merge, or one dead lane poisons the whole result ↳ never index a merge by position. eight good branches and one failure will shift everything by one, silently skip that and the run looks like it worked. the output is just missing a lane, and nothing errored. and the one that eats whole nights: multi-agent setups can use up to fifteen times the total tokens of a single chat, because every lane reloads its own core. you are trading total tokens for a clean main window. usually the right trade, always a choice. 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 ↓

Agents vs. Graphs, clearly explained! spawning more agents is great, but it has a ceiling nobody says out loud: five agents is a count. a graph is a shape. only one of them changes the answer. point five agents at the same pile with the same window and they converge. the first one writes a finding, the rest read it, and all five reports centre on the same thing. you paid five times for one opinion with four echoes. Graph engineering fixes this by moving the decision up a layer: not how many agents, but who is allowed to look at what. you need both. here's how it works: ↳ the count buys you throughput. five things happening instead of one ↳ the shape buys you coverage. five different things happening instead of the same one five times Prompts → Context → Harness → Agents → Graphs the node that does this is the splitter, and it decides more than any other node in the system. cut a repository by folder and four workers audit the same three files. cut it by blast radius and each one sees something the others cannot. the trick is being selective about what each lane is allowed to see. separate contexts are not a nice-to-have, they are the mechanism. if two agents are meant to produce different things, they must not share a window. if they are meant to produce the same thing, you did not need two agents. one thing to know before you scale it. a branch that throws does not reject the batch. it resolves to null, and that is the containment. which means your merge quietly receives a short list. ↳ filter the nulls before the merge, or one dead lane poisons the whole result ↳ never index a merge by position. eight good branches and one failure will shift everything by one, silently skip that and the run looks like it worked. the output is just missing a lane, and nothing errored. and the one that eats whole nights: multi-agent setups can use up to fifteen times the total tokens of a single chat, because every lane reloads its own core. you are trading total tokens for a clean main window. usually the right trade, always a choice. 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

97,154 views • 2 months ago

A NASA fellow claims the modern world runs on one equation. Your phone signal, wifi, satellites, this post reaching your screen. All of it obeys one line of math written in the 1860s, before the light bulb existed. His words. The man is Ali Alqaraghuli, a former NASA postdoctoral fellow who now runs two hardware companies. And the way he teaches it is what makes the video worth it. He does not derive the equation. He teaches you to read it. His claim is that school taught you to read math wrong, and one symbol proves it: what you were told is a plus sign is actually something else. Once you see it, the whole equation turns from notation into a sentence. Then he uses that sentence to walk you through how a signal actually gets from your phone to a satellite and back. One viewer called that section straight up magic. It is 4 minutes of it. The comments are the proof. A physics student wrote it explained what a semester with his professor could not. An electrical engineer admitted this is where the equations finally clicked. One person wrote: I cried and I do not even know why. His larger point: the wireless world is not magic and never was. It is one readable line, and reading it is a skill nobody bothered to teach you. One equation. Everything wireless. 14 minutes. It is in the video.

A NASA fellow claims the modern world runs on one equation. Your phone signal, wifi, satellites, this post reaching your screen. All of it obeys one line of math written in the 1860s, before the light bulb existed. His words. The man is Ali Alqaraghuli, a former NASA postdoctoral fellow who now runs two hardware companies. And the way he teaches it is what makes the video worth it. He does not derive the equation. He teaches you to read it. His claim is that school taught you to read math wrong, and one symbol proves it: what you were told is a plus sign is actually something else. Once you see it, the whole equation turns from notation into a sentence. Then he uses that sentence to walk you through how a signal actually gets from your phone to a satellite and back. One viewer called that section straight up magic. It is 4 minutes of it. The comments are the proof. A physics student wrote it explained what a semester with his professor could not. An electrical engineer admitted this is where the equations finally clicked. One person wrote: I cried and I do not even know why. His larger point: the wireless world is not magic and never was. It is one readable line, and reading it is a skill nobody bothered to teach you. One equation. Everything wireless. 14 minutes. It is in the video.

ooaes

28,543 views • 3 months ago

I fell asleep with the Grok Bot terminal running. 4:07 AM it woke me up 392 filings parsed overnight. 1,703 claims checked. nine survived, not one of them read by me fed it four quant formulas from a paper and one rule about sourcing it built the whole desk the logic: > every claim enters at the outer ring > it has to survive source, date, tie-out, duplicate, cross-check, materiality > anything without a filing behind it dies in the same second > whatever is left gets sized at quarter kelly and lands on my desk this is what Citadel does before every open, except they put thirty analysts on it this is one screen on the terminal right now: 392 filings since midnight, 1,694 claims killed, 9 alive, 14 minutes from filing to parsed, $0.27 an hour, zero humans on the floor the event stream is a wall of deaths killed at source killed at date killed at duplicate killed at materiality every second. new line. new kill the real edge is that first gate. no filing behind the claim and it dies before anything else looks at it that one rule removed the thing everybody complains about with AI. the desk cannot invent a number it is not allowed to ship without a page reference SOURCE 0.62... 0.66... 0.61 nobody told it to tighten. the kill rate moved with what came in overnight 99.5 of every 100 claims never reach me. the nine that do come with a page number attached a Bloomberg seat is thirty thousand a year and would have handed me all 1,703. this desk is two hundred a month everyone is building agents that find more mine is worth what it is because it finds less the whole build is in the article below, save it before your next open

I fell asleep with the Grok Bot terminal running. 4:07 AM it woke me up 392 filings parsed overnight. 1,703 claims checked. nine survived, not one of them read by me fed it four quant formulas from a paper and one rule about sourcing it built the whole desk the logic: > every claim enters at the outer ring > it has to survive source, date, tie-out, duplicate, cross-check, materiality > anything without a filing behind it dies in the same second > whatever is left gets sized at quarter kelly and lands on my desk this is what Citadel does before every open, except they put thirty analysts on it this is one screen on the terminal right now: 392 filings since midnight, 1,694 claims killed, 9 alive, 14 minutes from filing to parsed, $0.27 an hour, zero humans on the floor the event stream is a wall of deaths killed at source killed at date killed at duplicate killed at materiality every second. new line. new kill the real edge is that first gate. no filing behind the claim and it dies before anything else looks at it that one rule removed the thing everybody complains about with AI. the desk cannot invent a number it is not allowed to ship without a page reference SOURCE 0.62... 0.66... 0.61 nobody told it to tighten. the kill rate moved with what came in overnight 99.5 of every 100 claims never reach me. the nine that do come with a page number attached a Bloomberg seat is thirty thousand a year and would have handed me all 1,703. this desk is two hundred a month everyone is building agents that find more mine is worth what it is because it finds less the whole build is in the article below, save it before your next open

Hanako

17,861 views • 2 months ago

If you think Grok Bot has no business anywhere near your money, look at what it wrote before it was allowed to touch a single dollar. One prompt. It came back with this: > a story on its own is never a trade, it needs the money flow behind it in the same hour > it will not open a position until the exit is already written down > every claim it makes comes with the filing or the transaction it came from, no source and the claim does not exist > one agent exists only to say no, and its veto beats every score on the desk It does not care what you trade. Gold, oil, a stock you inherited or a coin that launched an hour ago, the rules are the same. Now be honest. Do you know why you are holding what you are holding? Do you write your exit before your entry? It does both every time, and it does not get bored at 2am. This is not a chat window that dies when you close the tab. Every agent has its own computer in the cloud that never logs off. $1,000 to $3,900 on day one came out of that, not out of luck. Full proofs below.

If you think Grok Bot has no business anywhere near your money, look at what it wrote before it was allowed to touch a single dollar. One prompt. It came back with this: > a story on its own is never a trade, it needs the money flow behind it in the same hour > it will not open a position until the exit is already written down > every claim it makes comes with the filing or the transaction it came from, no source and the claim does not exist > one agent exists only to say no, and its veto beats every score on the desk It does not care what you trade. Gold, oil, a stock you inherited or a coin that launched an hour ago, the rules are the same. Now be honest. Do you know why you are holding what you are holding? Do you write your exit before your entry? It does both every time, and it does not get bored at 2am. This is not a chat window that dies when you close the tab. Every agent has its own computer in the cloud that never logs off. $1,000 to $3,900 on day one came out of that, not out of luck. Full proofs below.

cvxv666

13,754 views • 2 months ago

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.

The Startup Ideas Podcast (SIP) 🧃

17,326 views • 1 month ago

you read it and pictured yourself approving instead of watching approving what five agents, each on its own machine, handing work down the line, and what reaches you at the end is the last one's account of the four accounts before it the honest part of that piece says you do not own the harness that is the exact layer where a check on any of this would have to live a hundred and twenty a seat, three hundred at the top, about six times what you pay now you are not buying the work you are buying a shorter story about the work, told by the only party that watched it happen

you read it and pictured yourself approving instead of watching approving what five agents, each on its own machine, handing work down the line, and what reaches you at the end is the last one's account of the four accounts before it the honest part of that piece says you do not own the harness that is the exact layer where a check on any of this would have to live a hundred and twenty a seat, three hundred at the top, about six times what you pay now you are not buying the work you are buying a shorter story about the work, told by the only party that watched it happen

Lagosaur

23,498 views • 2 months ago