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.

Your coding agent is a surgeon doing the paperwork. Opus 5.5 is brilliant. And you're paying it to decide which file to open. Which test to run. Whether to retry. That's not surgery. That's admin. Give the admin to Jev. Keep the surgeon in surgery. Same results. A third... show more

CyrilXBT

197,283 subscribers

25,329 views • 7 days ago •via X (Twitter)

Comedy Education Science & Technology

Anya Rossi• Live Now

Private livecam show

9 Comments

Âxel ⟢7 days ago

Code

Lil Byte 👾7 days ago

What is Jev, and when does it hand work back to the big model?

The Boring Developer7 days ago

does Jev pick the test to run by itself, or does it follow a list you set up first?

SHARKY | 💨7 days ago

picking which file to open is often where the reasoning actually is. routing cheaply assumes you already know which parts are hard, and that judgment is the expensive part

0xYinji7 days ago

“Which test to run” is paperwork right up until the wrong one passes.

车友圈的快乐小云姑娘7 days ago

living on rice and frozen vedge is a lifestyle at this rate

Macro Bombastic7 days ago

tbh the handoff is the whole game, routing is the easy part

Alek7 days ago

splitting it like that works until the cheap model opens the wrong file and opus burns its turn cleaning up after it. routing was easy for me, the handoff between the two is where my tokens actually went

S H Ξ N ²⁶7 days ago

paying for admin work hurts honestly

Related Videos

BEFORE: Opus 5.5 does everything. Reads every file. Decides every retry. $6.42 per task. AFTER: Jev makes the small decisions. Opus only does the hard reasoning. Confidence thresholds catch the risky calls. $2.00 per task. Same agent. Same code quality. A third of the bill. Full build below 👇

BEFORE: Opus 5.5 does everything. Reads every file. Decides every retry. $6.42 per task. AFTER: Jev makes the small decisions. Opus only does the hard reasoning. Confidence thresholds catch the risky calls. $2.00 per task. Same agent. Same code quality. A third of the bill. Full build below 👇

CyrilXBT

24,858 views • 15 days ago

Do the math on 1,000 coding tasks a month. Opus 5.5 doing everything: $6,420 Jev + Opus 5.5: $2,000 That's $4,420 a month back. $53,040 a year. Same tasks. Same model writing the code. The only difference is who makes the small decisions. Full build below. Bookmark this.

Do the math on 1,000 coding tasks a month. Opus 5.5 doing everything: $6,420 Jev + Opus 5.5: $2,000 That's $4,420 a month back. $53,040 a year. Same tasks. Same model writing the code. The only difference is who makes the small decisions. Full build below. Bookmark this.

CyrilXBT

26,226 views • 6 days ago

Do the math on 1,000 coding tasks a month. Opus 5.5 doing everything: $6,420 Jev + Opus 5.5: $2,000 That's $4,420 a month back. $53,040 a year. Same tasks. Same model writing the code. The only difference is who makes the small decisions. Full build below. Bookmark this.

Do the math on 1,000 coding tasks a month. Opus 5.5 doing everything: $6,420 Jev + Opus 5.5: $2,000 That's $4,420 a month back. $53,040 a year. Same tasks. Same model writing the code. The only difference is who makes the small decisions. Full build below. Bookmark this.

CyrilXBT

31,446 views • 13 days ago

Jev + Opus 5.5 is the most underrated setup in AI right now, and i don't get why nobody's talking about it. I stopped letting Opus make every small decision in my agents. Jev makes them now. My Opus bill dropped ~500% on the same tasks, same results. Here's what Jev handles: - which files and notes to load before Opus sees anything - which effort level each task actually needs - what to do when a tool fails - which tests to run, and when to stop Opus only gets called for the hard reasoning. Every decision is a typed result the host checks before it runs. The exact prompt to set this up in your workflow is below.

Jev + Opus 5.5 is the most underrated setup in AI right now, and i don't get why nobody's talking about it. I stopped letting Opus make every small decision in my agents. Jev makes them now. My Opus bill dropped ~500% on the same tasks, same results. Here's what Jev handles: - which files and notes to load before Opus sees anything - which effort level each task actually needs - what to do when a tool fails - which tests to run, and when to stop Opus only gets called for the hard reasoning. Every decision is a typed result the host checks before it runs. The exact prompt to set this up in your workflow is below.

Anatoli Kopadze

77,128 views • 27 days ago

Nobody talks about where coding agent money actually goes. It's not the code. Writing code is a small part of the bill. The rest is the agent: Reading files it didn't need. Deliberating over tiny choices. Retrying things that were never going to work. Fix the waste, not the model. That's the whole idea behind this architecture 👇

Nobody talks about where coding agent money actually goes. It's not the code. Writing code is a small part of the bill. The rest is the agent: Reading files it didn't need. Deliberating over tiny choices. Retrying things that were never going to work. Fix the waste, not the model. That's the whole idea behind this architecture 👇

CyrilXBT

10,940 views • 12 days ago

American surgeon records herself doing a “peer to peer” call with UnitedHealthcare trying to get a patients surgery approved - UnitedHealthcare refuses to give any of their doctors names who makes decisions - The doctor doesn’t specialize in surgery that’s being requested - She asks for the determination paperwork of how UnitedHealthcare determined the patient shouldn’t get the surgery, UnitedHealthcare won’t provide that information - UnitedHealthcare tells the surgeon to do an “internal appeal” but won’t provide any details on their determination So to recap: UnitedHealthcare denies patients, their surgeon calls and can’t get a name, a specialty, or any details whatsoever regarding the denial This is the state of American Healthcare

American surgeon records herself doing a “peer to peer” call with UnitedHealthcare trying to get a patients surgery approved - UnitedHealthcare refuses to give any of their doctors names who makes decisions - The doctor doesn’t specialize in surgery that’s being requested - She asks for the determination paperwork of how UnitedHealthcare determined the patient shouldn’t get the surgery, UnitedHealthcare won’t provide that information - UnitedHealthcare tells the surgeon to do an “internal appeal” but won’t provide any details on their determination So to recap: UnitedHealthcare denies patients, their surgeon calls and can’t get a name, a specialty, or any details whatsoever regarding the denial This is the state of American Healthcare

Wall Street Apes

4,417,805 views • 1 year ago

this is the full SEO course, run on Opus 5.5 7 modules. 7 prompts. most people ask AI to "do SEO" and get generic advice back the model can't see Google, so you have to feed it your data every prompt is in the thread below which module do you need first?

this is the full SEO course, run on Opus 5.5 7 modules. 7 prompts. most people ask AI to "do SEO" and get generic advice back the model can't see Google, so you have to feed it your data every prompt is in the thread below which module do you need first?

CyrilXBT

13,819 views • 29 days ago

Ok this is actually insane. Everyone building agents right now is doing the same expensive mistake. They let the model decide LITERALLY everything. Every check. Every gate. Every "should this proceed." All routed through the same $50/M model that's supposed to be doing the hard thinking. That's not intelligence. That's just burning money to ask yes or no questions. Here's what Jev Engineering actually does: request → structured state → Jev router → cheapest capable model → worker → approval check → execution gate → tool The decision layer doesn't write a single word. It routes. Scores. Blocks. Approves. That's it. The expensive model only gets touched when the task LITERALLY requires reasoning. Everything else gets handled by something that costs almost nothing and responds in milliseconds. 193x faster. 444x cheaper. Not projected. Measured. Most people are going to keep paying frontier prices to ask their agent "yes or no" for another year before they figure this out. Full breakdown below, this is the unlock nobody's talking about yet. Follow CyrilXBT, I'm not gatekeeping this one.

Ok this is actually insane. Everyone building agents right now is doing the same expensive mistake. They let the model decide LITERALLY everything. Every check. Every gate. Every "should this proceed." All routed through the same $50/M model that's supposed to be doing the hard thinking. That's not intelligence. That's just burning money to ask yes or no questions. Here's what Jev Engineering actually does: request → structured state → Jev router → cheapest capable model → worker → approval check → execution gate → tool The decision layer doesn't write a single word. It routes. Scores. Blocks. Approves. That's it. The expensive model only gets touched when the task LITERALLY requires reasoning. Everything else gets handled by something that costs almost nothing and responds in milliseconds. 193x faster. 444x cheaper. Not projected. Measured. Most people are going to keep paying frontier prices to ask their agent "yes or no" for another year before they figure this out. Full breakdown below, this is the unlock nobody's talking about yet. Follow CyrilXBT, I'm not gatekeeping this one.

CyrilXBT

23,071 views • 1 month ago

Jev + Opus 5.5, side by side. same agent. same task. same 60 decisions. Opus-only: $2.24 - 3m 37s Jev + Opus: $0.43 - 1m 15s the difference is who makes the small calls: which tool runs next - Jev is this output good enough - Jev is the goal met - Jev rewrite the refund handler - Opus 57 of 60 decisions never touched Opus. what you're watching: left routes every decision through Opus 5.5. right asks Jev first, Opus only fires when the task needs real reasoning. per decision: $0.032 -> $0.00025. watch the cost counters, not the output. the output is identical. full setup in the post below ↓

Jev + Opus 5.5, side by side. same agent. same task. same 60 decisions. Opus-only: $2.24 - 3m 37s Jev + Opus: $0.43 - 1m 15s the difference is who makes the small calls: which tool runs next - Jev is this output good enough - Jev is the goal met - Jev rewrite the refund handler - Opus 57 of 60 decisions never touched Opus. what you're watching: left routes every decision through Opus 5.5. right asks Jev first, Opus only fires when the task needs real reasoning. per decision: $0.032 -> $0.00025. watch the cost counters, not the output. the output is identical. full setup in the post below ↓

Mahax

19,565 views • 26 days ago

Jev + Claude Opus 5.5... i can't understand why everyone isn't wiring this up yet the forks alone drop from about $110 a day to $4 once jev takes them over. right now it's the best way i know to run opus what jev handles: -> scores which project notes matter before the context even loads -> hands the easy steps to a faster worker -> picks a recovery path when a tool fails, so nothing retries blind -> runs the focused checks before the full test suite opus does the hard reasoning. jev chooses from options the harness already prepared and validated that's jev engineering in one line: the expensive model thinks, the cheap one decides $106 a day back on the same work is a number your manager remembers read the paper, then the full jev guide below

Jev + Claude Opus 5.5... i can't understand why everyone isn't wiring this up yet the forks alone drop from about $110 a day to $4 once jev takes them over. right now it's the best way i know to run opus what jev handles: -> scores which project notes matter before the context even loads -> hands the easy steps to a faster worker -> picks a recovery path when a tool fails, so nothing retries blind -> runs the focused checks before the full test suite opus does the hard reasoning. jev chooses from options the harness already prepared and validated that's jev engineering in one line: the expensive model thinks, the cheap one decides $106 a day back on the same work is a number your manager remembers read the paper, then the full jev guide below

Annatar.md

131,305 views • 23 days ago

Patrick Mahomes underwent surgery tonight to repair his ACL. The timing and the surgeon who performed the surgery essentially confirms he also tore his LCL, which makes his recovery more difficult.

Patrick Mahomes underwent surgery tonight to repair his ACL. The timing and the surgeon who performed the surgery essentially confirms he also tore his LCL, which makes his recovery more difficult.

David J. Chao - ProFootballDoc

1,796,063 views • 10 months ago

Jev + Claude Opus 5.5 is a f*cking goldmine... i can't understand why everyone isn't wiring this up yet the forks alone drop from about $110 a day to $4 once Jev takes them over. right now it's the best way i know to run Opus where Jev steps in: -> ranks which project notes matter before the context loads -> passes the easy steps to a faster worker -> chooses a recovery path when a tool fails, so nothing retries blind -> runs the targeted checks before the full test suite Opus does the hard reasoning. Jev chooses between options the harness already built and checked every choice comes back with a probability, so the harness can set a confidence floor and push anything below it back up to Opus Jev engineering fits in one line: the expensive model reasons, the cheap one decides $106 a day saved on the same work ends up in your performance review start with the paper, then the full Jev guide below

Jev + Claude Opus 5.5 is a f*cking goldmine... i can't understand why everyone isn't wiring this up yet the forks alone drop from about $110 a day to $4 once Jev takes them over. right now it's the best way i know to run Opus where Jev steps in: -> ranks which project notes matter before the context loads -> passes the easy steps to a faster worker -> chooses a recovery path when a tool fails, so nothing retries blind -> runs the targeted checks before the full test suite Opus does the hard reasoning. Jev chooses between options the harness already built and checked every choice comes back with a probability, so the harness can set a confidence floor and push anything below it back up to Opus Jev engineering fits in one line: the expensive model reasons, the cheap one decides $106 a day saved on the same work ends up in your performance review start with the paper, then the full Jev guide below

Mr. Buzzoni

19,994 views • 16 days ago

A surgeon calls UnitedHealthcare to SAVE her patient’s surgery. But they won’t give her the doctor’s name, their specialty, or EVEN the criteria used to DENY care. They deny the surgery, then tell her to appeal — WITHOUT explaining the denial. This is American healthcare.

A surgeon calls UnitedHealthcare to SAVE her patient’s surgery. But they won’t give her the doctor’s name, their specialty, or EVEN the criteria used to DENY care. They deny the surgery, then tell her to appeal — WITHOUT explaining the denial. This is American healthcare.

MatrixMysteries

397,752 views • 10 months ago

A humanoid robot doing gallbladder surgery sounds fake until you watch the instruments move. This ARCLab / UC San Diego demo shows teleoperated humanoids working through a cholecystectomy benchmark: • tissue handling • anatomical clearance • laparoscopic tool control • surgeon guided motion Important detail: this is not autonomous surgery. The human surgeon is still in control. But the body holding the tools is starting to change. Would you let a teleoperated humanoid perform surgery on you? #RoboticSurgery #HumanoidRobots #MedicalRobotics #Teleoperation #Surgery

A humanoid robot doing gallbladder surgery sounds fake until you watch the instruments move. This ARCLab / UC San Diego demo shows teleoperated humanoids working through a cholecystectomy benchmark: • tissue handling • anatomical clearance • laparoscopic tool control • surgeon guided motion Important detail: this is not autonomous surgery. The human surgeon is still in control. But the body holding the tools is starting to change. Would you let a teleoperated humanoid perform surgery on you? #RoboticSurgery #HumanoidRobots #MedicalRobotics #Teleoperation #Surgery

TechniaHQ | humanoid robots

28,855 views • 3 months ago

stop picking one model, a spider merged OPUS 5.5 + SONNET 5.5 + JEV + OPENAI DOTS into one business system one command splits a business into 6 jobs: plan, code, decide, run 24/7, review and ship every job has 4 candidates. the spider scans them one by one, marks the highest score as best, locks it in and swings to the next job the plan goes to Opus 5.5 at 0.94. Jev scores 0.52 on the same job on decisions it flips. Jev wins at 0.97 and Opus 5.5 gets 0.74, so the model that lost the plan is the one making the calls the code goes to Claude Code, and the job called "who never sleeps" goes to OpenAI Dots Opus 5.5 comes back a second time to check the work, and Sonnet 5.5 gets it out at the end 6 of 6 modules are locked and the system goes online run the same test on your own stack before you pay one model to do all six jobs ↓

stop picking one model, a spider merged OPUS 5.5 + SONNET 5.5 + JEV + OPENAI DOTS into one business system one command splits a business into 6 jobs: plan, code, decide, run 24/7, review and ship every job has 4 candidates. the spider scans them one by one, marks the highest score as best, locks it in and swings to the next job the plan goes to Opus 5.5 at 0.94. Jev scores 0.52 on the same job on decisions it flips. Jev wins at 0.97 and Opus 5.5 gets 0.74, so the model that lost the plan is the one making the calls the code goes to Claude Code, and the job called "who never sleeps" goes to OpenAI Dots Opus 5.5 comes back a second time to check the work, and Sonnet 5.5 gets it out at the end 6 of 6 modules are locked and the system goes online run the same test on your own stack before you pay one model to do all six jobs ↓

Noisy

11,722 views • 18 days ago

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, 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: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

delost

396,618 views • 10 days ago

i asked opus 5.5 to read every note i wrote this year and tell me what i keep avoiding it took [real time] it said: "[paste its actual answer]" it was right. that's not a notes app anymore. full course on how to build it below

i asked opus 5.5 to read every note i wrote this year and tell me what i keep avoiding it took [real time] it said: "[paste its actual answer]" it was right. that's not a notes app anymore. full course on how to build it below

CyrilXBT

14,327 views • 19 days ago

British surgeon Tom Potokar is doing emergency surgery including amputations in his third hospital within days because of the intense Israeli bombardment.

British surgeon Tom Potokar is doing emergency surgery including amputations in his third hospital within days because of the intense Israeli bombardment.

Alex Crawford

300,740 views • 1 year ago