Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Some late-night vibe coding with Claude. This time I tried implementing the paper "Real-Time Ray-Traced Ambient Occlusion of Complex Scenes using Spatial Hashing" (by Pascal Gautron) using LightweightVK. The starting point was a basic working ray-traced AO demo without spatial hashing which I already had - just stochastic noise...

38,292 Aufrufe • vor 3 Monaten •via X (Twitter)

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

194,949 Aufrufe • vor 11 Monaten

CLAUDE CODE JUST SHIPPED THE FEATURE THAT SOLVES THE BIGGEST PROBLEM EVERY BUILDER HAS WITH AI AGENTS. The problem: Claude starts a task, gets distracted by a sub-problem, goes down a rabbit hole, and never finishes the original thing you asked for. The solution: /goal One command. You set the goal at the start of the session. Claude now has a north star it checks against every action it takes. Not just at the beginning. Throughout the entire session. Every time Claude is about to do something it asks: does this action move me toward the goal the user set or am I drifting? If it is drifting it corrects. If it completes a sub-task it returns to the primary goal. If it hits a blocker it reports back instead of spending 45 minutes solving the wrong problem. This sounds like a small feature. It is not. The reason most people do not trust Claude Code for long autonomous runs is not capability. It is reliability. A Claude Code session that reliably finishes what it started is worth 10 times more than one that is more capable but wanders. /goal is the feature that makes long autonomous sessions reliable. Set the goal. Let it run. Come back to a finished result. Not a result that got 70% done before Claude decided the sub-problem was more interesting. Done. The builders running overnight agent sessions are going to use this command on everything from today forward. Bookmark this. Follow CyrilXBT for every Claude Code feature the moment it ships.

CyrilXBT

19,586 Aufrufe • vor 2 Monaten

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

The Pragmatic Engineer

62,825 Aufrufe • vor 2 Monaten

"That pussy Adam Cole broke his ankle like the complete dork that he is." MJF talks about the revisionist history of his story with Adam Cole "Here's what happened. At the time, and this is just a fact, we were the highest minute-for-minute drawing angle, not just in AEW, but in all of professional wrestling at that point. We were moving the most merch in the company. At that point, and was to no fault, Bloodline's going to go down as one of the greatest long-term thing, but at that point there was a bit of lull in their story at that point in 2023, and we had taken lead and Better Than You, Baby is what everybody was talking about and then that pussy Adam Cole broke his ankle like the complete dork that he is and then he decided to turn on me because he's a horrible human being. But I learned a lot in that in that year I learned a lot about myself you know when I when I was out—full disclosure I was in a very dark place." I also asked about the injuries he had suffered "It was my hip, my left shoulder; my last two pay-per-view matches—pretty much the left side of my body was useless. But I wasn't going to tell the doctors that because that's not how I was brought up. In not just in real life, but in this business. When I had that time off, I had a lot of time to reflect and it made me angry. Now I look back on it and I shouldn't have been angry at the fans. Who I should have been angry was that myself. Because I went from being, ‘MJF is the best thing since sliced bread,’ and within a flip of a switch, ‘It's MJF sucks. He's killing this company that we love.’ It took, if we're being honest, it took all the way into like the first month of this year of 2025 for everybody to be like, ‘Maybe we were harsh. Maybe he's actually still one of the best in the world. They can't help it. But I know why. It's because nobody likes a braggart. But the unfortunate thing is I can't help myself. I'm just really good at my job and I can't help but talk about it."

Sean Ross Sapp of Fightful.com

31,538 Aufrufe • vor 6 Monaten