Загрузка видео...

Не удалось загрузить видео

На главную

I tested Step 5 Preview from StepFun on Duolingo’s FY25 filings. Duolingo reported $414.1M in net income. But $256.7M of that was a one-time tax benefit. Excluding it, net income was closer to $157.4M. Step 5 Preview caught that distinction without prompting, then kept going: → Revenue grew 39%,...

Damn_coder's profile picture

D-Coder

104,359 subscribers

115,317 просмотров • 5 дней назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 23

Фото профиля StepFun
StepFun5 дней назад

Great to see you using our model!

Фото профиля Rishabh
Rishabh5 дней назад

@StepFun_ai Catching the accounting detail is impressive, but fixing its own model and rerunning 64 checks is even better. Great work from @StepFun_ai!

Фото профиля D-Coder
D-Coder5 дней назад

@StepFun_ai Agreed. Catching mistakes is one thing, fixing them is another.

Фото профиля Andrew Bolis
Andrew Bolis5 дней назад

@StepFun_ai Good example of insight plus a verified deliverable.

Фото профиля D-Coder
D-Coder5 дней назад

@StepFun_ai Exactly, the fact that it checks its own work makes a difference.

Фото профиля Pradeep Pandey
Pradeep Pandey5 дней назад

@StepFun_ai StepFun might actually be onto something here. I'd love to test this myself.

Фото профиля D-Coder
D-Coder5 дней назад

@StepFun_ai Yeah, definitely worth giving it a try.

Фото профиля Wise Philosophy
Wise Philosophy5 дней назад

@StepFun_ai This is a great example of AI doing actual financial analysis instead of just summarizing reports.

Фото профиля D-Coder
D-Coder5 дней назад

@StepFun_ai Yep, especially when you're working with financial data.

Фото профиля Roshni
Roshni5 дней назад

@StepFun_ai Wait, it caught the tax benefit on its own? That's pretty good.

Фото профиля D-Coder
D-Coder5 дней назад

@StepFun_ai Right? That's the kind of detail that's easy to miss.

Фото профиля Parul Gautam
Parul Gautam5 дней назад

@StepFun_ai Step 5 Preview catching errors before human review is a promising sign for real-world workflows.

Фото профиля D-Coder
D-Coder5 дней назад

@StepFun_ai That's what I liked too. It went beyond just giving an answer.

Фото профиля Daily Wisdom
Daily Wisdom5 дней назад

@StepFun_ai The 64 automated checks are what make Step 5 Preview interesting to me.

Фото профиля Mind Yeti
Mind Yeti5 дней назад

@StepFun_ai Finding and fixing its own modeling errors is a pretty big deal.

Фото профиля Life Mastery
Life Mastery5 дней назад

@StepFun_ai Catching that one-time tax benefit without being prompted is impressive.

Фото профиля Csaba Kissi
Csaba Kissi5 дней назад

@StepFun_ai This model is new to me

Фото профиля D-Coder
D-Coder5 дней назад

@StepFun_ai Pretty interesting model so far.

Фото профиля RifatOfficial
RifatOfficial5 дней назад

@StepFun_ai That one time tax benefit really swings the headline numbers.

Фото профиля Minds That Build
Minds That Build5 дней назад

@StepFun_ai StepFun is showing some serious potential with Step 5 Preview. That self-correction is impressive.

Фото профиля Mr. Jason💡
Mr. Jason💡5 дней назад

@StepFun_ai Wow so wonderful work

Фото профиля sabir hussain
sabir hussain5 дней назад

@StepFun_ai Can AI catch financial insights without being prompted?

Фото профиля Utkarsh Sharma
Utkarsh Sharma5 дней назад

@StepFun_ai @StepFun_ai is making a strong first impression with this one.

Похожие видео

step 5 preview from StepFun spent an hour building me this cool little snow globe and iterated against the small details, constantly checking its work! it zoomed in on its own tiny cottages to check nothing was clipping, & even made a histogram to verify the snow falls from the very top the best part? the api bill was $2.26, for about an hour of work! that's the pareto frontier at just $1 in/$2.70 out per million tokens step 5 preview is now on openrouter and available in kilo code, cline, hermes agent, and opencode so you can keep your workflow and just switch models. more integrations to come :3 try step 5 preview on openrouter -
0:30

step 5 preview from StepFun spent an hour building me this cool little snow globe and iterated against the small details, constantly checking its work! it zoomed in on its own tiny cottages to check nothing was clipping, & even made a histogram to verify the snow falls from the very top the best part? the api bill was $2.26, for about an hour of work! that's the pareto frontier at just $1 in/$2.70 out per million tokens step 5 preview is now on openrouter and available in kilo code, cline, hermes agent, and opencode so you can keep your workflow and just switch models. more integrations to come :3 try step 5 preview on openrouter -

leo 🐾

15,321 просмотров • 6 дней назад

So I gave Step 5 Preview a bug it had never seen before, and just watched. Filtered 193 users out of 208, hit export, and the file came back with 6 rows. Whatever happened to be sitting on the current page. That's the bug I handed it. No file names. No hints. Just the codebase and the report. Here's what happened: 1. It read through the project on its own and found the real cause. The export was pulling from the current page slice instead of the full filtered list. 2. It fixed the root cause, then renamed the ambiguous fields so the mistake can't happen twice. 3. It added retry logic for failed downloads. Bounded attempts, a visible error state if every one fails. I didn't even ask for that part. 4. It wrote 15 new tests across three layers. Unit, component, and real browser runs. 5. Then it opened the running app and reran the exact scenario itself. The numbers: 208 total users 193 matched the filter 6 rows in the broken export 193 rows in the fixed one 15 new tests, all passing One prompt. No follow-up corrections. It verified its own fix before calling the task done. Curious to see how it handles your own coding challenges? Give Step 5 Preview a try 👉 It’s now #1 on OpenRouter’s Trending ranking, so this might be a good time to put it to the test. Check the ranking:
0:49

So I gave Step 5 Preview a bug it had never seen before, and just watched. Filtered 193 users out of 208, hit export, and the file came back with 6 rows. Whatever happened to be sitting on the current page. That's the bug I handed it. No file names. No hints. Just the codebase and the report. Here's what happened: 1. It read through the project on its own and found the real cause. The export was pulling from the current page slice instead of the full filtered list. 2. It fixed the root cause, then renamed the ambiguous fields so the mistake can't happen twice. 3. It added retry logic for failed downloads. Bounded attempts, a visible error state if every one fails. I didn't even ask for that part. 4. It wrote 15 new tests across three layers. Unit, component, and real browser runs. 5. Then it opened the running app and reran the exact scenario itself. The numbers: 208 total users 193 matched the filter 6 rows in the broken export 193 rows in the fixed one 15 new tests, all passing One prompt. No follow-up corrections. It verified its own fix before calling the task done. Curious to see how it handles your own coding challenges? Give Step 5 Preview a try 👉 It’s now #1 on OpenRouter’s Trending ranking, so this might be a good time to put it to the test. Check the ranking:

Parul Gautam

49,002 просмотров • 5 дней назад

“Atria Dawn Preview” just caught my attention after I tested it on a real frontend task. I tested Atria ASI with Claude Code on a real frontend task: build a modern, responsive landing page using HTML, CSS, and JavaScript. It created the files, validated the code, and opened the final result for review. What stood out was the workflow. It went from understanding the task to writing code, checking the result, and delivering something I could actually run and verify. That makes “Atria Dawn Preview” interesting to me for research, development, and other professional workflows where the goal isn’t just an answer, but a usable and verifiable result. Definitely an agent I’ll be keeping an eye on. Official links:👇 API: Website: Looking forward to seeing where Atria Dawn Preview goes next.
0:40

“Atria Dawn Preview” just caught my attention after I tested it on a real frontend task. I tested Atria ASI with Claude Code on a real frontend task: build a modern, responsive landing page using HTML, CSS, and JavaScript. It created the files, validated the code, and opened the final result for review. What stood out was the workflow. It went from understanding the task to writing code, checking the result, and delivering something I could actually run and verify. That makes “Atria Dawn Preview” interesting to me for research, development, and other professional workflows where the goal isn’t just an answer, but a usable and verifiable result. Definitely an agent I’ll be keeping an eye on. Official links:👇 API: Website: Looking forward to seeing where Atria Dawn Preview goes next.

Aryan Rakib

35,129 просмотров • 1 месяц назад

WTF.. 65 of the 96 core team members behind this AI agent are university students. It’s called Atria Dawn Preview. Atria ASI I saw that and was like… okay, I need to try this. So I plugged it into Codex and asked it to build me an interactive creator dashboard from scratch. It made the files, wrote the code, ran the checks, fixed what broke and actually got the dashboard working. And it got there without me babysitting every step. Not bad at all for a first run.
0:56

WTF.. 65 of the 96 core team members behind this AI agent are university students. It’s called Atria Dawn Preview. Atria ASI I saw that and was like… okay, I need to try this. So I plugged it into Codex and asked it to build me an interactive creator dashboard from scratch. It made the files, wrote the code, ran the checks, fixed what broke and actually got the dashboard working. And it got there without me babysitting every step. Not bad at all for a first run.

EyeingAI

26,248 просмотров • 1 месяц назад

Godfather of agents showed how he created the loop engineering that everyone now uses: as PhD student, he wrote the formula every AI agent now runs on - his formula taught agents to self-improve here's the formula: step 1 → stop making the model just think OR just act - make it alternate: think → act → observe → think again step 2 → let it reason out loud before every action - the plan guides the next move, not just the output step 3 → feed the result of each action back in - the model reads what happened and adjusts, live step 4 → when it fails, don't restart make it reflect on WHY it failed, in words, then retry with that memory step 5 → store those reflections - the agent gets better across attempts without any retraining before OpenAI, before he ran Tencent's AI - he was a grad student who quietly wrote the blueprint every agent now follows - now give 90-min course watch & bookmark - then read how the agent systems actually works ↓
1:22:01

Godfather of agents showed how he created the loop engineering that everyone now uses: as PhD student, he wrote the formula every AI agent now runs on - his formula taught agents to self-improve here's the formula: step 1 → stop making the model just think OR just act - make it alternate: think → act → observe → think again step 2 → let it reason out loud before every action - the plan guides the next move, not just the output step 3 → feed the result of each action back in - the model reads what happened and adjusts, live step 4 → when it fails, don't restart make it reflect on WHY it failed, in words, then retry with that memory step 5 → store those reflections - the agent gets better across attempts without any retraining before OpenAI, before he ran Tencent's AI - he was a grad student who quietly wrote the blueprint every agent now follows - now give 90-min course watch & bookmark - then read how the agent systems actually works ↓

codila

28,667 просмотров • 2 месяцев назад

Anthropic and Andrew Ng built an agent that uses 90% fewer tokens from scratch: they dropped the entire book of Frankenstein into a prompt - 108,000 tokens asked one question the input dropped from 108,000 tokens to 11 here's how: step 1 → put everything that never changes at the top - tools, then system, then docs step 2 → mark where the static part ends. everything above it gets cached step 3 → one stray space breaks it - and you pay full price again step 4 → the cache dies in 5 min - every read resets the clock step 5 → cached tokens don't count against your rate limits. free headroom most people never touch this - it pays for itself on day one watch & bookmark - this 1-hour brilliant course ↓
1:04:05

Anthropic and Andrew Ng built an agent that uses 90% fewer tokens from scratch: they dropped the entire book of Frankenstein into a prompt - 108,000 tokens asked one question the input dropped from 108,000 tokens to 11 here's how: step 1 → put everything that never changes at the top - tools, then system, then docs step 2 → mark where the static part ends. everything above it gets cached step 3 → one stray space breaks it - and you pay full price again step 4 → the cache dies in 5 min - every read resets the clock step 5 → cached tokens don't count against your rate limits. free headroom most people never touch this - it pays for itself on day one watch & bookmark - this 1-hour brilliant course ↓

codila

546,486 просмотров • 3 месяцев назад

Anthropic Engineer: “the biggest mistake in AI right now is people are building graphs and loops without a self-improving eval agent. we made that mistake at anthropic. it cost us two years.” here’s how they built what solved it: step 1 → take 50 real user prompts and run your agent. if it passes 80%+, your eval is too easy. the sweet spot is around 50%. step 2 → every failed run becomes a transcript. feed it to haiku: “what went wrong?” your eval set keeps growing on its own. step 3 → score two things: the right answer and the right path. a right answer with the wrong path will break later. step 4 → when a new model drops, run the same eval again. one model looked 9% better. but 6% of that gain came from hiding a bug. the transcript caught it. the dashboard didn’t. step 5 → plug your evals into ci. no green evals = no deploy. that’s how the system keeps improving itself. 99% of people never build this. but it pays for itself on day one. save this and build it today.
28:54

Anthropic Engineer: “the biggest mistake in AI right now is people are building graphs and loops without a self-improving eval agent. we made that mistake at anthropic. it cost us two years.” here’s how they built what solved it: step 1 → take 50 real user prompts and run your agent. if it passes 80%+, your eval is too easy. the sweet spot is around 50%. step 2 → every failed run becomes a transcript. feed it to haiku: “what went wrong?” your eval set keeps growing on its own. step 3 → score two things: the right answer and the right path. a right answer with the wrong path will break later. step 4 → when a new model drops, run the same eval again. one model looked 9% better. but 6% of that gain came from hiding a bug. the transcript caught it. the dashboard didn’t. step 5 → plug your evals into ci. no green evals = no deploy. that’s how the system keeps improving itself. 99% of people never build this. but it pays for itself on day one. save this and build it today.

MIKE

102,478 просмотров • 2 месяцев назад

the agent failed while I was asleep and somehow the work still got finished that was the test I actually wanted i gave GPT-6 Astra a workflow that normally needed me between every step inbound came in messy one agent had to sort it, another find the missing context, another build the deliverable, and the last one check everything before it reached me somewhere in the middle, agent 2 got stuck the source it needed wasn’t there normally that kills the entire chain instead, it wrote the missing piece into a blocker file and passed everything else forward the other agents kept working when I came back, most of the pack was finished and the one thing they couldn’t solve was sitting separately waiting for me that felt more important than a perfect demo because an agent completing 10/10 tasks is impressive an agent failing without taking the other 9 down with it is infrastructure
0:30

the agent failed while I was asleep and somehow the work still got finished that was the test I actually wanted i gave GPT-6 Astra a workflow that normally needed me between every step inbound came in messy one agent had to sort it, another find the missing context, another build the deliverable, and the last one check everything before it reached me somewhere in the middle, agent 2 got stuck the source it needed wasn’t there normally that kills the entire chain instead, it wrote the missing piece into a blocker file and passed everything else forward the other agents kept working when I came back, most of the pack was finished and the one thing they couldn’t solve was sitting separately waiting for me that felt more important than a perfect demo because an agent completing 10/10 tasks is impressive an agent failing without taking the other 9 down with it is infrastructure

Lummox

19,046 просмотров • 24 дней назад

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.
4:15

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

Sudo su

39,764 просмотров • 4 месяцев назад

I gave an AI one instruction: “Build me a playable 3D game from scratch.” Then I let it cook. 👀 I tested Tencent Hy4 preview inside WorkBuddy, and it went way beyond just generating a few snippets of code. It could: → Plan the game structure → Generate the code across files → Create the UI and interactions → Debug problems along the way → Iterate on the project while keeping context That last part is what caught my attention. Hy4 preview is built for these long-horizon tasks, with 770B total parameters, 49B active parameters, and a 1M-token context window. It’s designed for coding agents, game development, tool use, research, and other workflows where the model has to actually do the work, not just answer a prompt. And right now, you can try Hy4 preview for free on WorkBuddy until September 10. If you want to see how far an AI agent can take a real project, try it yourself: See what you can build with it. Tencent AI
1:27

I gave an AI one instruction: “Build me a playable 3D game from scratch.” Then I let it cook. 👀 I tested Tencent Hy4 preview inside WorkBuddy, and it went way beyond just generating a few snippets of code. It could: → Plan the game structure → Generate the code across files → Create the UI and interactions → Debug problems along the way → Iterate on the project while keeping context That last part is what caught my attention. Hy4 preview is built for these long-horizon tasks, with 770B total parameters, 49B active parameters, and a 1M-token context window. It’s designed for coding agents, game development, tool use, research, and other workflows where the model has to actually do the work, not just answer a prompt. And right now, you can try Hy4 preview for free on WorkBuddy until September 10. If you want to see how far an AI agent can take a real project, try it yourself: See what you can build with it. Tencent AI

Toha Khan

66,214 просмотров • 1 месяц назад

This new AI model is crazy fast at coding 🤯 It fixed a broken backend in one prompt and around 83 seconds. I tested Space Bunny inside OpenCode with a FastAPI repo. It had 3 failing tests caused by broken order filtering, unsafe money calculations and incorrect product ranking. I didn’t tell it where the bugs were. It read the product contract, inspected the code, found the root causes and fixed everything. Then it added 2 edge-case tests on its own. The final result: 3 failing tests → 6 passing tests Only 2 files changed Public API untouched It made one small CLI mistake during the run, but the final patch was clean. Tbh this is the kind of speed I expect from a Flash-level model. Not just fast output. Fast useful work.
0:57

This new AI model is crazy fast at coding 🤯 It fixed a broken backend in one prompt and around 83 seconds. I tested Space Bunny inside OpenCode with a FastAPI repo. It had 3 failing tests caused by broken order filtering, unsafe money calculations and incorrect product ranking. I didn’t tell it where the bugs were. It read the product contract, inspected the code, found the root causes and fixed everything. Then it added 2 edge-case tests on its own. The final result: 3 failing tests → 6 passing tests Only 2 files changed Public API untouched It made one small CLI mistake during the run, but the final patch was clean. Tbh this is the kind of speed I expect from a Flash-level model. Not just fast output. Fast useful work.

Farhan

60,769 просмотров • 19 дней назад

IF YOU ARE STILL PROMPTING BY HAND IN 2026 YOU ARE ALREADY BEHIND the guy who built Claude Code at Anthropic said he stopped writing prompts a long time ago he runs loops instead, systems that write the prompts for him and keep working while he sleeps you type one request at a time and wait for the answer he built a machine that fires hundreds of requests, checks its own output and fixes itself with no hands on the keyboard here is how you make the jump step 1 stop treating the model like a chat box and start treating it like a worker you manage step 2 write a loop that takes a goal, breaks it into tasks and sends each one to the model on its own step 3 add a second pass where the model grades its own work and retries whatever failed step 4 let it run on a timer so it keeps shipping while you are away from the screen the person still typing prompts one by one is doing the work of a intern the person running loops is doing the work of a whole team off one laptop prompting was never the skill, building the system that prompts for you is
0:56

IF YOU ARE STILL PROMPTING BY HAND IN 2026 YOU ARE ALREADY BEHIND the guy who built Claude Code at Anthropic said he stopped writing prompts a long time ago he runs loops instead, systems that write the prompts for him and keep working while he sleeps you type one request at a time and wait for the answer he built a machine that fires hundreds of requests, checks its own output and fixes itself with no hands on the keyboard here is how you make the jump step 1 stop treating the model like a chat box and start treating it like a worker you manage step 2 write a loop that takes a goal, breaks it into tasks and sends each one to the model on its own step 3 add a second pass where the model grades its own work and retries whatever failed step 4 let it run on a timer so it keeps shipping while you are away from the screen the person still typing prompts one by one is doing the work of a intern the person running loops is doing the work of a whole team off one laptop prompting was never the skill, building the system that prompts for you is

Atlas

16,641 просмотров • 2 месяцев назад

I literally just watched GPT-5.5 via codex beat an Amazon customer associate in real time. 💀 I asked it to get me a refund, and I watched it navigate the settings, cancel the subscription, then it went step further into the help page. I thought it was going to request a phone call (which would prompt me to take over) Instead, it opened: “Chat with an associate now.” That’s when I sat up on my couch because I knew it was going to get real The agent said: “Your subscription is active.” And GPT-5.5 immediately explained that it only shows as active because cancellation leaves access through the billing period, but that I wanted it stopped now and refunded. And my jaw just hung open, it was the first time I watched sand handle a customer service agent for me in real time Once the agent confirmed the refund, it just ended the chat no mercy no thank you LMAO First time I’ve watched a human customer service agent get outmaneuvered by AI in real time. And it made me 15$! almost paid for itself in 5 minutes
0:49

I literally just watched GPT-5.5 via codex beat an Amazon customer associate in real time. 💀 I asked it to get me a refund, and I watched it navigate the settings, cancel the subscription, then it went step further into the help page. I thought it was going to request a phone call (which would prompt me to take over) Instead, it opened: “Chat with an associate now.” That’s when I sat up on my couch because I knew it was going to get real The agent said: “Your subscription is active.” And GPT-5.5 immediately explained that it only shows as active because cancellation leaves access through the billing period, but that I wanted it stopped now and refunded. And my jaw just hung open, it was the first time I watched sand handle a customer service agent for me in real time Once the agent confirmed the refund, it just ended the chat no mercy no thank you LMAO First time I’ve watched a human customer service agent get outmaneuvered by AI in real time. And it made me 15$! almost paid for itself in 5 minutes

Chris

1,390,132 просмотров • 5 месяцев назад

HOW TO BUILD A CONTENT MACHINE THAT ACTUALLY BRINGS IN INCOME (STEP-BY-STEP GUIDE) When you're just starting out, you don't know what to do, and the best option is to simply take and copy the format of others, but tweak it a little to fit yourself How to actually make content like those who earn money from it: • 1 - Channel selection and analytics • 2 - Training Claude on the channel's style • 3 - Building a content system • 4 - Script generation and production • 5 - Metadata, publication and iteration Save this so you don't lose it
13:48

HOW TO BUILD A CONTENT MACHINE THAT ACTUALLY BRINGS IN INCOME (STEP-BY-STEP GUIDE) When you're just starting out, you don't know what to do, and the best option is to simply take and copy the format of others, but tweak it a little to fit yourself How to actually make content like those who earn money from it: • 1 - Channel selection and analytics • 2 - Training Claude on the channel's style • 3 - Building a content system • 4 - Script generation and production • 5 - Metadata, publication and iteration Save this so you don't lose it

TolyaDV

32,002 просмотров • 4 месяцев назад

Anthropic hired this engineer at $250k-$600k/year because he can built projects with zero lines of code - in Claude chat: in this 30-min workshop he showed exactly how, using loops - from 0% to 100% here's workflow, step by step: step 1 → set your rules once at the top: "no preamble, use artifacts, you're a React expert" - every reply after that stays on rails step 2 → load the docs plus a random Medium article about the API - the human explanation teaches it more than the reference step 3 → wrap your ask in XML tags and tell it to ask you questions first. Answer 5, and the scope is locked before a single file exists step 4 → now run the loop: screenshot the broken UI, paste it back, let it fix, screenshot again - each pass gets closer - this is the agentic loop in its simplest form step 5 → push to GitHub, then paste the repo link in - every next loop iteration builds on working code, not chat history most people never did this - it pays for itself on day one watch & bookmark - then read how to get Claude Certified Architect in the article below ↓
26:23

Anthropic hired this engineer at $250k-$600k/year because he can built projects with zero lines of code - in Claude chat: in this 30-min workshop he showed exactly how, using loops - from 0% to 100% here's workflow, step by step: step 1 → set your rules once at the top: "no preamble, use artifacts, you're a React expert" - every reply after that stays on rails step 2 → load the docs plus a random Medium article about the API - the human explanation teaches it more than the reference step 3 → wrap your ask in XML tags and tell it to ask you questions first. Answer 5, and the scope is locked before a single file exists step 4 → now run the loop: screenshot the broken UI, paste it back, let it fix, screenshot again - each pass gets closer - this is the agentic loop in its simplest form step 5 → push to GitHub, then paste the repo link in - every next loop iteration builds on working code, not chat history most people never did this - it pays for itself on day one watch & bookmark - then read how to get Claude Certified Architect in the article below ↓

codila

293,493 просмотров • 2 месяцев назад

Jev + Opus 5.5: Anthropic's new model beats GPT-6 Astra for 1/5 the cost, and 4 API changes will 400 your agent before it writes a single line I pulled these 10 steps from the migration docs so you don't learn them in production step 1 → $4 / $20 per 1M. Opus 5 was $5 / $25. cache reads dropped from $0.50 to $0.20 step 2 → 66.4% on Terminal-Bench 4.0 vs GPT-6 Astra 57.9% and Opus 5 52.3%. +14.1 points in one release, and on FrontierCode it beats Astra at default effort for 1/5 the cost step 3 → thinking can't be turned off anymore. send thinking: disabled and you get a 400. drop the field, set effort step 4 → tool_choice any and tool are gone. 400. switch to auto + strict step 5 → edit anything above a thinking block and the request dies. append only, or opt into drop_block step 6 → computer_20251124 is dead on the API. 400. move to computer_toolset_20260801 step 7 → the quiet one: default effort fell from high to medium. your agent thinks less than you set it up to and nothing tells you step 8 → hop Opus 5.5 → Sonnet 5 → Opus 5.5 and you pay 4.36 instead of 3.32. +31%, the cache dies and Sonnet can't read Opus's reasoning step 9 → change effort at the top of the request and the cache is gone. Jev sets it per message and the cache stays step 10 → switch fast - standard mid-session and it's a full cache miss. Jev picks speed once, on turn one one model, three knobs, zero 400s. that is Jev + Opus 5.5 send this to your Claude Code before you touch the model ID, then read my full Jev deep dive in the article below ↓
0:40

Jev + Opus 5.5: Anthropic's new model beats GPT-6 Astra for 1/5 the cost, and 4 API changes will 400 your agent before it writes a single line I pulled these 10 steps from the migration docs so you don't learn them in production step 1 → $4 / $20 per 1M. Opus 5 was $5 / $25. cache reads dropped from $0.50 to $0.20 step 2 → 66.4% on Terminal-Bench 4.0 vs GPT-6 Astra 57.9% and Opus 5 52.3%. +14.1 points in one release, and on FrontierCode it beats Astra at default effort for 1/5 the cost step 3 → thinking can't be turned off anymore. send thinking: disabled and you get a 400. drop the field, set effort step 4 → tool_choice any and tool are gone. 400. switch to auto + strict step 5 → edit anything above a thinking block and the request dies. append only, or opt into drop_block step 6 → computer_20251124 is dead on the API. 400. move to computer_toolset_20260801 step 7 → the quiet one: default effort fell from high to medium. your agent thinks less than you set it up to and nothing tells you step 8 → hop Opus 5.5 → Sonnet 5 → Opus 5.5 and you pay 4.36 instead of 3.32. +31%, the cache dies and Sonnet can't read Opus's reasoning step 9 → change effort at the top of the request and the cache is gone. Jev sets it per message and the cache stays step 10 → switch fast - standard mid-session and it's a full cache miss. Jev picks speed once, on turn one one model, three knobs, zero 400s. that is Jev + Opus 5.5 send this to your Claude Code before you touch the model ID, then read my full Jev deep dive in the article below ↓

Carnage

16,674 просмотров • 22 дней назад

Sam Altman reveals he deliberately got himself addicted to TikTok while building Sora, then deleted it because it was too powerful like a drug. "I deleted TikTok because it was just too powerful. Here's a crazy thing that happened. When we were building the Sora app, I made myself get addicted to TikTok because I wanted to learn." "I'd never really used it before... And I loved it. I love TikTok, I really thought it was great." "And then I thought I could control it. I was like, oh, it's actually kind of fun, but I only use it for 10 minutes to wind down before bed and I'm totally in control of it." "And then it was an hour one night, and then some Saturday afternoon I was on the couch for like 3 hours, and I was like, this is really not what I thought the iPhone was supposed to be about." "Now I'm really enjoying it in the moment like a drug, but I can tell it's bad for me. And then I briefly got it back under control, down to like 5 or 10 minutes a night. Then I was just like, enough."
1:04

Sam Altman reveals he deliberately got himself addicted to TikTok while building Sora, then deleted it because it was too powerful like a drug. "I deleted TikTok because it was just too powerful. Here's a crazy thing that happened. When we were building the Sora app, I made myself get addicted to TikTok because I wanted to learn." "I'd never really used it before... And I loved it. I love TikTok, I really thought it was great." "And then I thought I could control it. I was like, oh, it's actually kind of fun, but I only use it for 10 minutes to wind down before bed and I'm totally in control of it." "And then it was an hour one night, and then some Saturday afternoon I was on the couch for like 3 hours, and I was like, this is really not what I thought the iPhone was supposed to be about." "Now I'm really enjoying it in the moment like a drug, but I can tell it's bad for me. And then I briefly got it back under control, down to like 5 or 10 minutes a night. Then I was just like, enough."

Fireside Alpha

605,308 просмотров • 2 месяцев назад

Wim Wenders explains why Jean Renoir's "The Rules of the Game" (1939) is one of his favourite movies: "'The Rules of the Game' (1939) appears on many lists of the greatest films of all time, and Renoir is one of the great filmmakers. He's also the lead actor in his own movie. It's a film made before the Second World War that anticipates that war in an amazing way. It was another film that was a revelation when I saw it for the first time, and then I saw it again and again. It played in a little neighborhood theater where I lived, and I saw it every day. I don't know how many times I have seen it, but it's one of the films I know by heart. For me, it's almost the ideal movie. It's very funny, fluid, and has an incredible range of characters. It also has the premonition that war is in the air. Nobody knew that a World War was coming, but he anticipated it, and it is a totally amazing film." ('Perfect Days' Director Wim Wenders' Top 5, Aframe Oscars, 2023)
1:59

Wim Wenders explains why Jean Renoir's "The Rules of the Game" (1939) is one of his favourite movies: "'The Rules of the Game' (1939) appears on many lists of the greatest films of all time, and Renoir is one of the great filmmakers. He's also the lead actor in his own movie. It's a film made before the Second World War that anticipates that war in an amazing way. It was another film that was a revelation when I saw it for the first time, and then I saw it again and again. It played in a little neighborhood theater where I lived, and I saw it every day. I don't know how many times I have seen it, but it's one of the films I know by heart. For me, it's almost the ideal movie. It's very funny, fluid, and has an incredible range of characters. It also has the premonition that war is in the air. Nobody knew that a World War was coming, but he anticipated it, and it is a totally amazing film." ('Perfect Days' Director Wim Wenders' Top 5, Aframe Oscars, 2023)

DepressedBergman

19,944 просмотров • 3 месяцев назад

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription
0:22

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

savip.

68,984 просмотров • 2 месяцев назад