正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

> you installed Hermes Agent > you type a request, read the response, close the window > you've been using 8% of it > every single session > Hermes remembers everything. you never told it what to remember > it runs named personas on every task. you've never set... show more

Sharbel

72,972 subscribers

209,713 次观看 • 3 个月前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

The Tories are telling you that you've never had it so good. Do you agree with them?

The Tories are telling you that you've never had it so good. Do you agree with them?

The Labour Party

82,538 次观看 • 2 年前

Hermes Agent now has a desktop app! I made a quick video showing how easy it is to install, set up, and get to work! It perfectly synced with my existing agent, or you can use it to make a new one. Plus, a quick tour of the features! It's never been easier to start with Hermes!

Hermes Agent now has a desktop app! I made a quick video showing how easy it is to install, set up, and get to work! It perfectly synced with my existing agent, or you can use it to make a new one. Plus, a quick tour of the features! It's never been easier to start with Hermes!

tonbi

17,622 次观看 • 2 个月前

This guy literally tested Hermes Agent vs OpenClaw side by side. Hermes won. And it wasn't close. Here's what made the difference: → Hermes built the website faster → Hermes gave live updates the whole time. OpenClaw went silent. → Hermes designed a cleaner page using the exact same AI model → And then Hermes did something OpenClaw can't do at all. It learned from the task. Every mistake gets logged. Every win gets saved as a reusable skill. The more you use it, the smarter it gets. OpenClaw doesn't do this unless you manually set up a learning file. Hermes does it automatically. Every single time. Other wins: → Runs free with Ollama + MiniMax → Works on Telegram, Discord, Slack, WhatsApp, Signal, and Email → Supports 200+ AI models → Built-in migration tool from OpenClaw — one command to switch 11,600 GitHub stars. 142 contributors. If you're already on OpenClaw, you don't have to start over. Just ask Hermes to import everything.

This guy literally tested Hermes Agent vs OpenClaw side by side. Hermes won. And it wasn't close. Here's what made the difference: → Hermes built the website faster → Hermes gave live updates the whole time. OpenClaw went silent. → Hermes designed a cleaner page using the exact same AI model → And then Hermes did something OpenClaw can't do at all. It learned from the task. Every mistake gets logged. Every win gets saved as a reusable skill. The more you use it, the smarter it gets. OpenClaw doesn't do this unless you manually set up a learning file. Hermes does it automatically. Every single time. Other wins: → Runs free with Ollama + MiniMax → Works on Telegram, Discord, Slack, WhatsApp, Signal, and Email → Supports 200+ AI models → Built-in migration tool from OpenClaw — one command to switch 11,600 GitHub stars. 142 contributors. If you're already on OpenClaw, you don't have to start over. Just ask Hermes to import everything.

Julian Goldie SEO

40,877 次观看 • 4 个月前

Anthropic Managed Agents team: "Fable 5 is our best model for running self-improving agent systems. Add /loops, dynamic workflows, dreaming and you are unstoppable" in this video he breaks down exactly how most people are using Claude: - the 34% you lose to CLAUDE.md before typing a word - one agent researching. one building. one reviewing. one orchestrating - the architecture that separates hobbyists from real builders - the 3 properties every agent team needs to actually survive if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below

Anthropic Managed Agents team: "Fable 5 is our best model for running self-improving agent systems. Add /loops, dynamic workflows, dreaming and you are unstoppable" in this video he breaks down exactly how most people are using Claude: - the 34% you lose to CLAUDE.md before typing a word - one agent researching. one building. one reviewing. one orchestrating - the architecture that separates hobbyists from real builders - the 3 properties every agent team needs to actually survive if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below

Khairallah AL-Awady

21,533 次观看 • 2 个月前

Obsidian plus Hermes Agent equals a system that thinks, remembers, and runs your life. Works while you sleep. Vault holds the knowledge. Hermes reads it. Claude reasons across it. Outputs land back in the vault as new notes. Every morning brief grounded in your actual projects. Every inbox processed automatically. Every week synthesized without effort. The personal operating system that compounds forever. Read this and Bookmark it now.

Obsidian plus Hermes Agent equals a system that thinks, remembers, and runs your life. Works while you sleep. Vault holds the knowledge. Hermes reads it. Claude reasons across it. Outputs land back in the vault as new notes. Every morning brief grounded in your actual projects. Every inbox processed automatically. Every week synthesized without effort. The personal operating system that compounds forever. Read this and Bookmark it now.

CyrilXBT

43,403 次观看 • 2 个月前

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇

YanXbt

22,720 次观看 • 1 个月前

Every AI tool forgets what you told it yesterday. Tanka doesn’t. It’s your AI Co-Founder, the one that remembers everything so you never start from scratch again. Here’s how it changes the way founders work 👇

Every AI tool forgets what you told it yesterday. Tanka doesn’t. It’s your AI Co-Founder, the one that remembers everything so you never start from scratch again. Here’s how it changes the way founders work 👇

SARAH

127,107 次观看 • 9 个月前

OBSIDIAN PLUS HERMES AGENT IS THE MOST POWERFUL PERSONAL OPERATING SYSTEM AVAILABLE RIGHT NOW AND ALMOST NOBODY HAS BUILT IT YET. Obsidian holds everything you know permanently. Hermes reads it, reasons across it, and runs your most important workflows automatically. Morning briefs generated from your actual vault. Inbox processed every evening without you touching it. Project health monitored every Monday. Weekly synthesis ready every Sunday. One system. Thinks. Remembers. Runs your life. Read this and Bookmark it now.

OBSIDIAN PLUS HERMES AGENT IS THE MOST POWERFUL PERSONAL OPERATING SYSTEM AVAILABLE RIGHT NOW AND ALMOST NOBODY HAS BUILT IT YET. Obsidian holds everything you know permanently. Hermes reads it, reasons across it, and runs your most important workflows automatically. Morning briefs generated from your actual vault. Inbox processed every evening without you touching it. Project health monitored every Monday. Weekly synthesis ready every Sunday. One system. Thinks. Remembers. Runs your life. Read this and Bookmark it now.

CyrilXBT

122,498 次观看 • 2 个月前

"Never be afraid to fail... You put the confidence you have in everything you do when the lights are on because of everything you've done when no one is watching." Jalen Brunson on the mindset it takes to play and win at the highest level. Game 5: Saturday, 8:30pm/et, ABC

"Never be afraid to fail... You put the confidence you have in everything you do when the lights are on because of everything you've done when no one is watching." Jalen Brunson on the mindset it takes to play and win at the highest level. Game 5: Saturday, 8:30pm/et, ABC

NBA

185,948 次观看 • 2 个月前

There are 2 clips here. 1 you've likely seen, is now probably more suspect that it ever has been. The second, I've never heard anyone say before.

There are 2 clips here. 1 you've likely seen, is now probably more suspect that it ever has been. The second, I've never heard anyone say before.

Invisidon

178,904 次观看 • 10 个月前

Everyone is talking about Hermes Agent, and for good reason It is the most reliable AI agent on Earth right now A 24/7/365 employee that never crashes If you don't have one set up yet, you're missing out This is your COMPLETE guide to Hermes Agent, from set up to use cases:

Everyone is talking about Hermes Agent, and for good reason It is the most reliable AI agent on Earth right now A 24/7/365 employee that never crashes If you don't have one set up yet, you're missing out This is your COMPLETE guide to Hermes Agent, from set up to use cases:

Alex Finn

82,331 次观看 • 3 个月前

A DEVELOPER MADE A REAL COMMIT WITHOUT EVER TYPING GIT ADD OR GIT COMMIT -- JUST TO PROVE THE COMMANDS YOU LIVE BY ARE A THIN SHELL OVER A DATABASE YOU'VE NEVER ONCE OPENED 55 minutes from Tim Berglund, a longtime Git teacher and GitHub evangelist, taking the tool apart down to the raw objects almost nobody who uses it every day has ever touched. -> The moment it clicks, Git stops being a pile of memorized commands and becomes what it actually is underneath: a tiny content-addressed database of blobs, trees and commits. git add and git commit are just polite wrappers around writing objects into it by hand. Every commit you've ever made was Git hashing a snapshot and filing it by fingerprint. Branches are just labels pointing at one of those objects. The work you thought you destroyed with a bad reset is still sitting in the reflog. Once you can see that graph, the commands that used to terrify you stop being scary at all. Memorizing commands was never the skill -> reading the object graph in your head is. And with an AI agent now committing and rebasing on your machine faster than you can follow, the one person who can untangle the mess it leaves is the one who knows what's really stored down there. There's a person on every team everyone runs to when Git breaks. This is the talk that quietly turns you into them. You'll reach for it the next time a rebase goes sideways. Bookmark & Watch it today ↓

A DEVELOPER MADE A REAL COMMIT WITHOUT EVER TYPING GIT ADD OR GIT COMMIT -- JUST TO PROVE THE COMMANDS YOU LIVE BY ARE A THIN SHELL OVER A DATABASE YOU'VE NEVER ONCE OPENED 55 minutes from Tim Berglund, a longtime Git teacher and GitHub evangelist, taking the tool apart down to the raw objects almost nobody who uses it every day has ever touched. -> The moment it clicks, Git stops being a pile of memorized commands and becomes what it actually is underneath: a tiny content-addressed database of blobs, trees and commits. git add and git commit are just polite wrappers around writing objects into it by hand. Every commit you've ever made was Git hashing a snapshot and filing it by fingerprint. Branches are just labels pointing at one of those objects. The work you thought you destroyed with a bad reset is still sitting in the reflog. Once you can see that graph, the commands that used to terrify you stop being scary at all. Memorizing commands was never the skill -> reading the object graph in your head is. And with an AI agent now committing and rebasing on your machine faster than you can follow, the one person who can untangle the mess it leaves is the one who knows what's really stored down there. There's a person on every team everyone runs to when Git breaks. This is the talk that quietly turns you into them. You'll reach for it the next time a rebase goes sideways. Bookmark & Watch it today ↓

slash1s

237,718 次观看 • 2 个月前

WTF, THIS CHINESE FOUNDER RUNS HIS $10,000+ STARTUP'S ENTIRE WORKFLOW THROUGH HERMES AGENT ON FOUR MACHINES SIMULTANEOUSLY A studio founder just broke down why Hermes is different from every other AI tool right now: → Long-term memory. Most LLMs forget everything after the chat ends. Hermes remembers your work habits and gets sharper the more you use it. → Real execution, not suggestions. This is the core difference from Claude. Claude tells you what to do – you still do it. Hermes takes the instruction and finishes the task itself. → Scheduled tasks that just work. No complicated setup. Set the plan once, it runs on its own. This is what actual "hands-off" looks like. He's not running this on one machine. He's got FOUR laptops running Hermes simultaneously – each one handling a different part of his workflow at the same time. This is what it looks like when one person operates like a full team. He's dropping a full workflow build tutorial next – built for founders and operators trying to lighten their workload. Bookmark this, you'll want to come back to it later.

WTF, THIS CHINESE FOUNDER RUNS HIS $10,000+ STARTUP'S ENTIRE WORKFLOW THROUGH HERMES AGENT ON FOUR MACHINES SIMULTANEOUSLY A studio founder just broke down why Hermes is different from every other AI tool right now: → Long-term memory. Most LLMs forget everything after the chat ends. Hermes remembers your work habits and gets sharper the more you use it. → Real execution, not suggestions. This is the core difference from Claude. Claude tells you what to do – you still do it. Hermes takes the instruction and finishes the task itself. → Scheduled tasks that just work. No complicated setup. Set the plan once, it runs on its own. This is what actual "hands-off" looks like. He's not running this on one machine. He's got FOUR laptops running Hermes simultaneously – each one handling a different part of his workflow at the same time. This is what it looks like when one person operates like a full team. He's dropping a full workflow build tutorial next – built for founders and operators trying to lighten their workload. Bookmark this, you'll want to come back to it later.

SCOTTY BEAM

11,654 次观看 • 1 个月前

DMT takes you somewhere your mind was never built to go. Nothing you've read explains it. Nothing you believe prepares you for it. You just arrive and go "what the fuck IS this."

DMT takes you somewhere your mind was never built to go. Nothing you've read explains it. Nothing you believe prepares you for it. You just arrive and go "what the fuck IS this."

Taylor Sterling

16,811 次观看 • 4 个月前

how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of it like open claw but with built-in memory, 40+ tools out of the box, and 90% cheaper token costs. you install it with one command. 2. the 3 problems with open claw that hermes solves: no memory (you keep repeating yourself), constant gateway restarts, and zero visibility into what you're spending on tokens. 3. hermes remembers everything. every completed task gets saved to memory. it searches through past logs to find solutions. over time it literally gets smarter at your specific workflows. 4. connect it to open router. you see exact costs per model per task. free models rotate weekly. one founder went from $130 every five days on open claw to $10 on hermes. same output. 5. it comes preloaded with skills. apple notes, imessage, find my, browser, web search, image generation, cron jobs. no hunting for plugins. 6. connect it to obsidian so it reads your entire vault. connect it to gstack for your dev environment. create custom skills for your specific workflows. 7. the biggest money saver: have it write code once for recurring tasks. then it runs without burning tokens every time. stop paying an LLM to do the same scrape or report daily. 8. run it on android via telegram. name your agents. talk to them like coworkers. in this episode imran shows you how to set this up. 9. you can run it bare metal, in docker, or serverless on modal. pick your risk level. i begged imran to come on The Startup Ideas Podcast (SIP) 🧃 and walk through the full installation live. he made it impossibly clear. if you've heard of Hermes Agent and want the clearest explanation of how to get set up like a pro let me know what you want me to cover on the next ep this is the best personal agent setup video on the internet right now. watch

how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of it like open claw but with built-in memory, 40+ tools out of the box, and 90% cheaper token costs. you install it with one command. 2. the 3 problems with open claw that hermes solves: no memory (you keep repeating yourself), constant gateway restarts, and zero visibility into what you're spending on tokens. 3. hermes remembers everything. every completed task gets saved to memory. it searches through past logs to find solutions. over time it literally gets smarter at your specific workflows. 4. connect it to open router. you see exact costs per model per task. free models rotate weekly. one founder went from $130 every five days on open claw to $10 on hermes. same output. 5. it comes preloaded with skills. apple notes, imessage, find my, browser, web search, image generation, cron jobs. no hunting for plugins. 6. connect it to obsidian so it reads your entire vault. connect it to gstack for your dev environment. create custom skills for your specific workflows. 7. the biggest money saver: have it write code once for recurring tasks. then it runs without burning tokens every time. stop paying an LLM to do the same scrape or report daily. 8. run it on android via telegram. name your agents. talk to them like coworkers. in this episode imran shows you how to set this up. 9. you can run it bare metal, in docker, or serverless on modal. pick your risk level. i begged imran to come on The Startup Ideas Podcast (SIP) 🧃 and walk through the full installation live. he made it impossibly clear. if you've heard of Hermes Agent and want the clearest explanation of how to get set up like a pro let me know what you want me to cover on the next ep this is the best personal agent setup video on the internet right now. watch

GREG ISENBERG

619,380 次观看 • 3 个月前

.Secretary of War Pete Hegseth addressed our warriors at the D.C. Armory: "We are NOTHING but grateful for everything that you do. Every single day. Every single night. Every single risk that you are willing to take. The vigilance that you maintain on our behalf. Thank you for doing what most Americans could never do."

.Secretary of War Pete Hegseth addressed our warriors at the D.C. Armory: "We are NOTHING but grateful for everything that you do. Every single day. Every single night. Every single risk that you are willing to take. The vigilance that you maintain on our behalf. Thank you for doing what most Americans could never do."

DOW Rapid Response

35,325 次观看 • 8 个月前

Secretary of War Pete Hegseth from the D.C. Armory: “We are nothing but grateful for everything that you do… every single day, every single night, every single risk that you’re willing to take, the vigilance that you maintain on our behalf… Thank you for doing what most Americans could never do.” Subscribe to OAN Live Here:

Secretary of War Pete Hegseth from the D.C. Armory: “We are nothing but grateful for everything that you do… every single day, every single night, every single risk that you’re willing to take, the vigilance that you maintain on our behalf… Thank you for doing what most Americans could never do.” Subscribe to OAN Live Here:

One America News

14,133 次观看 • 8 个月前

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 次观看 • 3 天前

Threadguy explains why if you've never used Hyperliquid it's easy to be bearish on it and compares it to the Solana mistake from last cycle "If you never used Solana in 2024 you could have easily convinced yourself to be bullish on some other performance chain. Avax, whatever, they all did terrible. Solana mogged all of them. From the same lens, if you've never used Hyperliquid, it would be very easy to convince yourself that Coinbase or Robinhood is just gonna eat their lunch or that the product isn't that good or it's niche. It's very easy to make the same mistake if you've never used it as you could have made if you never used Solana in '24." "After using Hyperliquid every day for a year, I open up a brokerage account and try to trade on Robinhood and I'm like what the fuck is this? This is terrible. It's a product game. Robinhood won retail options because the product was so good, so smooth, so easy to use. I get on Hyperliquid for a month and Robinhood feels like garbage compared to it." "Think about how much money exists offshore that can't trade US equities that can now trade US equities on Hyperliquid. The only way you look at this price action and say all crypto sucks, this is a fake pump, is if you've never used the product."

Threadguy explains why if you've never used Hyperliquid it's easy to be bearish on it and compares it to the Solana mistake from last cycle "If you never used Solana in 2024 you could have easily convinced yourself to be bullish on some other performance chain. Avax, whatever, they all did terrible. Solana mogged all of them. From the same lens, if you've never used Hyperliquid, it would be very easy to convince yourself that Coinbase or Robinhood is just gonna eat their lunch or that the product isn't that good or it's niche. It's very easy to make the same mistake if you've never used it as you could have made if you never used Solana in '24." "After using Hyperliquid every day for a year, I open up a brokerage account and try to trade on Robinhood and I'm like what the fuck is this? This is terrible. It's a product game. Robinhood won retail options because the product was so good, so smooth, so easy to use. I get on Hyperliquid for a month and Robinhood feels like garbage compared to it." "Think about how much money exists offshore that can't trade US equities that can now trade US equities on Hyperliquid. The only way you look at this price action and say all crypto sucks, this is a fake pump, is if you've never used the product."

Kai

22,894 次观看 • 2 个月前

This film is probably one of the most brutally heartbreaking films I've ever seen. If you've never seen it, you need to

This film is probably one of the most brutally heartbreaking films I've ever seen. If you've never seen it, you need to

Queerly

103,855 次观看 • 3 个月前