Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing WarpGrep v2. #1 on SWE-Bench Pro What if code search was a separate, specialized model? w/ WarpGrep v2: #1 on SWE-Bench Pro Opus 4.6 → 57.5 (+2.1) Codex 5.3 (cli) → 59.1 (+3.1) MiniMax 2.5 → 57.6 (+3.7) without WarpGrep: Opus 4.6 (high) → 55.4 GPT-5.3 Codex (high)...

morphllm's profile picture

Morph

3,229 subscribers

56,540 Aufrufe • vor 3 Monaten •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

One prompt. 6 frontier coding models. "Create a realistic fireworks show using HTML Canvas and JavaScript. No libraries." Some built a whole celebration. Others... lit a sparkler. The lineup: - GPT-5.3 Codex - Claude Opus 4.6 - Gemini 3.1 Pro - MiniMax M2.7 - GLM-5 - Kimi K2.5
0:14

One prompt. 6 frontier coding models. "Create a realistic fireworks show using HTML Canvas and JavaScript. No libraries." Some built a whole celebration. Others... lit a sparkler. The lineup: - GPT-5.3 Codex - Claude Opus 4.6 - Gemini 3.1 Pro - MiniMax M2.7 - GLM-5 - Kimi K2.5

stevibe

14,152 Aufrufe • vor 3 Monaten

After a weekend of testing and working on something with GPT-5.3-Codex & Opus 4.6, ChatGPT Pro + Claude Max 5x are still the best combo in my opinion Using Codex & Claude Code CLI running in tmux (the desktop apps are still a bit buggy) and they're accessible even on the go from iPhone with Termius (and VPN) Usually starting with GPT-5.3-Codex xhigh and Opus 4.6 in plan mode, discussing changes and options, and each writing their plans down to separate Markdown files Then letting GPT-5.3-Codex xhigh (or Opus 4.6) implement the changes as the first draft, then Opus 4.6 reviews them with a team of agents (works pretty well already with tmux even though still experimental) based on both prepared plans, fixes stuff, and then another review by GPT-5.3-Codex xhigh or vice versa Interesting that even Opus 4.6 still occasionally makes silly mistakes like wrong imports, partial or overly broad renaming of variables/functions, etc Fun fact, OpenAI apparently plans to use their Super Bowl ad to promote Codex - curious what that will look like
0:14

After a weekend of testing and working on something with GPT-5.3-Codex & Opus 4.6, ChatGPT Pro + Claude Max 5x are still the best combo in my opinion Using Codex & Claude Code CLI running in tmux (the desktop apps are still a bit buggy) and they're accessible even on the go from iPhone with Termius (and VPN) Usually starting with GPT-5.3-Codex xhigh and Opus 4.6 in plan mode, discussing changes and options, and each writing their plans down to separate Markdown files Then letting GPT-5.3-Codex xhigh (or Opus 4.6) implement the changes as the first draft, then Opus 4.6 reviews them with a team of agents (works pretty well already with tmux even though still experimental) based on both prepared plans, fixes stuff, and then another review by GPT-5.3-Codex xhigh or vice versa Interesting that even Opus 4.6 still occasionally makes silly mistakes like wrong imports, partial or overly broad renaming of variables/functions, etc Fun fact, OpenAI apparently plans to use their Super Bowl ad to promote Codex - curious what that will look like

Tibor Blaho

29,794 Aufrufe • vor 4 Monaten

Eulerian Fluid simulation test! Zero-shot! Opus 4.6 vs GPT-5.3 vs Gemini 3 Deep Think! My personal preference: 🥇 Gemini 3 Deep Think (really strong!) 🥈 Opus 4.6 🥉 GPT 5.3 High
0:19

Eulerian Fluid simulation test! Zero-shot! Opus 4.6 vs GPT-5.3 vs Gemini 3 Deep Think! My personal preference: 🥇 Gemini 3 Deep Think (really strong!) 🥈 Opus 4.6 🥉 GPT 5.3 High

Ivan Fioravanti ᯅ

38,277 Aufrufe • vor 4 Monaten

I don't even need to mention which landing page was created by Opus 4.6 and which one by GPT-5.3-CODEX
0:16

I don't even need to mention which landing page was created by Opus 4.6 and which one by GPT-5.3-CODEX

Karan

90,021 Aufrufe • vor 4 Monaten

It's Christmas morning: OpenAI and Anthropic shipped new models on the same day! We tested GPT 5.3 Codex vs. Opus 4.6 head-to-head. Verdict: the models are converging. Here’s what we found 🧵
0:15

It's Christmas morning: OpenAI and Anthropic shipped new models on the same day! We tested GPT 5.3 Codex vs. Opus 4.6 head-to-head. Verdict: the models are converging. Here’s what we found 🧵

Every 📧

11,945 Aufrufe • vor 4 Monaten

Choosing a model for your project isn't always easy, so our benchmark evaluates LLMs against actual Android development problems. Current top scores on Android Bench: 🔹 Gemini 3.1 Pro Preview 🔹 Claude 4.6 🔹 GPT 5.2 Codex Full leaderboard →
0:15

Choosing a model for your project isn't always easy, so our benchmark evaluates LLMs against actual Android development problems. Current top scores on Android Bench: 🔹 Gemini 3.1 Pro Preview 🔹 Claude 4.6 🔹 GPT 5.2 Codex Full leaderboard →

Android Developers

10,104 Aufrufe • vor 2 Monaten

The model is faster, the pelican isn't as good! GPT-5.3 Codex Spark on the left, GPT-5.3 Codex 5.3 on the right - both at medium quality settings
0:08

The model is faster, the pelican isn't as good! GPT-5.3 Codex Spark on the left, GPT-5.3 Codex 5.3 on the right - both at medium quality settings

Simon Willison

57,440 Aufrufe • vor 4 Monaten

🐐 Gemini 3 Pro GA One shot prompt is in comment with the codepen link I repeat no model in this entire world able to implement this level of physics and spatial reasoning Not even Opus 4.6 and Gpt-5.3 codex , this is like a generation gap Sub Woofer submitted this
0:15

🐐 Gemini 3 Pro GA One shot prompt is in comment with the codepen link I repeat no model in this entire world able to implement this level of physics and spatial reasoning Not even Opus 4.6 and Gpt-5.3 codex , this is like a generation gap Sub Woofer submitted this

Chetaslua

35,579 Aufrufe • vor 4 Monaten

Just shipped v2 of my flight sim inspired by @levelsio! You can now fly anywhere on Earth: - NY - Hong Kong - Rio - Your hometown - Literally anywhere Speedran this in ~1hr using Opus 4.6 and GPT-5.3 since they both shipped today!
0:15

Just shipped v2 of my flight sim inspired by @levelsio! You can now fly anywhere on Earth: - NY - Hong Kong - Rio - Your hometown - Literally anywhere Speedran this in ~1hr using Opus 4.6 and GPT-5.3 since they both shipped today!

Alistair McLeay

1,084,925 Aufrufe • vor 4 Monaten

MiniMax just dropped M2.5 and it's on par with Opus 4.6 while being 20x cheaper and 3x faster???
0:18

MiniMax just dropped M2.5 and it's on par with Opus 4.6 while being 20x cheaper and 3x faster???

shydev

442,571 Aufrufe • vor 4 Monaten

What's a game without a menu? I went with Opus 4.6 for this one (better taste for frontend UI than Codex 5.3). Also going with 'Zombies Per Minute' right now for name:) Curious to know what you think? Next up: leaderboards
0:15

What's a game without a menu? I went with Opus 4.6 for this one (better taste for frontend UI than Codex 5.3). Also going with 'Zombies Per Minute' right now for name:) Curious to know what you think? Next up: leaderboards

Nicolas Zullo

71,474 Aufrufe • vor 4 Monaten

MiniMax M3: Opus-level coding at DeepSeek pricing. On Terminal-Bench 2.1, it scores 66.0, only 0.1 behind Opus 4.7. I gave it a quick try on a few frontend tasks, and the output quality genuinely feels close to Opus 4.7.
0:13

MiniMax M3: Opus-level coding at DeepSeek pricing. On Terminal-Bench 2.1, it scores 66.0, only 0.1 behind Opus 4.7. I gave it a quick try on a few frontend tasks, and the output quality genuinely feels close to Opus 4.7.

Kai

25,648 Aufrufe • vor 23 Tagen

Ok... this is going further than I expected. Ended up vibe coding a FULL point and click level editor: > Full 3d space + navigation > Place hotspots anywhere > Transform, scale, rotate objects > Set interaction dialogs Opus 4.6 FAST + Codex 5.3 + Nano Banana Pro + Seedance
0:11

Ok... this is going further than I expected. Ended up vibe coding a FULL point and click level editor: > Full 3d space + navigation > Place hotspots anywhere > Transform, scale, rotate objects > Set interaction dialogs Opus 4.6 FAST + Codex 5.3 + Nano Banana Pro + Seedance

Chong-U

36,184 Aufrufe • vor 4 Monaten

MiniMax M2.7 is live on Runware on Day0! 🚀 - full end-to-end project delivery - self-evolving architecture: 30% performance gains across 100+ iterations - 97% skill adherence rate across 40+ complex tasks - 56.22% on SWE-Pro, 55.6% on VIBE-Pro, 57.0% on Terminal Bench 2
0:18

MiniMax M2.7 is live on Runware on Day0! 🚀 - full end-to-end project delivery - self-evolving architecture: 30% performance gains across 100+ iterations - 97% skill adherence rate across 40+ complex tasks - 56.22% on SWE-Pro, 55.6% on VIBE-Pro, 57.0% on Terminal Bench 2

Runware

38,628 Aufrufe • vor 3 Monaten

GPT-5.3-Codex built this Hytale mod with just a few prompts 👀
0:17

GPT-5.3-Codex built this Hytale mod with just a few prompts 👀

Hytale Alerts

151,770 Aufrufe • vor 4 Monaten

GPT-5.3-Codex with image gen skill (NBP) I'm loving this model so much. This is one-shot
0:14

GPT-5.3-Codex with image gen skill (NBP) I'm loving this model so much. This is one-shot

Angel 🌼

305,914 Aufrufe • vor 4 Monaten

Midjourney x Veo 3.1 x Claude Claude Opus 4.6 is the Goat.
0:11

Midjourney x Veo 3.1 x Claude Claude Opus 4.6 is the Goat.

Viktor Oddy

14,544 Aufrufe • vor 2 Monaten

ウチにもGPT-5.3-Codex-Spark来たので録画したらこれ。。 早すぎて表示処理が追いついてない。笑 1000Token/秒は、Windsurfのswe-1.5(最大950Token/秒)と同じくらい、CurrsorのComposer1.5(250Token/秒)の4倍早い👀 そして賢さはxhighモードで動かせば、 GPT-5.3-CodexのlowモードくらいのSWE-Bench 51%くらいで普通のコーディングは難なくこなすレベル。 難しいタスクはcodex, 通常のタスクはSpark使えばかなり効率いいですね🎵 今後はサブエージェント化する予定なので要注目です👀 いや〜それにしても早くて賢い✨ ・Introducing GPT-5.3-Codex-Spark | OpenAI URL: #codex
0:12

ウチにもGPT-5.3-Codex-Spark来たので録画したらこれ。。 早すぎて表示処理が追いついてない。笑 1000Token/秒は、Windsurfのswe-1.5(最大950Token/秒)と同じくらい、CurrsorのComposer1.5(250Token/秒)の4倍早い👀 そして賢さはxhighモードで動かせば、 GPT-5.3-CodexのlowモードくらいのSWE-Bench 51%くらいで普通のコーディングは難なくこなすレベル。 難しいタスクはcodex, 通常のタスクはSpark使えばかなり効率いいですね🎵 今後はサブエージェント化する予定なので要注目です👀 いや〜それにしても早くて賢い✨ ・Introducing GPT-5.3-Codex-Spark | OpenAI URL: #codex

あきらパパ【生成AI活用エンジニア&３児のパパ】

71,151 Aufrufe • vor 4 Monaten

MiniMax M2.5 is benchmaxed. I gave 4 models the same prompt: Create a neon "OPEN" sign in HTML. GLM 5: Clean, classic neon. Nailed it. Claude Opus 4.6: Stylized with glow. Solid. Gemini 3 Pro: Cursive with bloom lighting. Creative. MiniMax M2.5: Spelled it "O b∈ N" with broken spacing. This model ranks #2 on BridgeBench with a 59.7 score and 100% completion rate. But it can't spell a 4-letter word. Benchmarks don't tell the whole story. A model can ace structured tasks and fail basic creative prompts. High score ≠ production ready.
0:15

MiniMax M2.5 is benchmaxed. I gave 4 models the same prompt: Create a neon "OPEN" sign in HTML. GLM 5: Clean, classic neon. Nailed it. Claude Opus 4.6: Stylized with glow. Solid. Gemini 3 Pro: Cursive with bloom lighting. Creative. MiniMax M2.5: Spelled it "O b∈ N" with broken spacing. This model ranks #2 on BridgeBench with a 59.7 score and 100% completion rate. But it can't spell a 4-letter word. Benchmarks don't tell the whole story. A model can ace structured tasks and fail basic creative prompts. High score ≠ production ready.

BridgeMind

54,212 Aufrufe • vor 4 Monaten

GPT-5.3-Codex + Image-to-3D Skill Just generated a cute avatar for Sam Altman
0:17

GPT-5.3-Codex + Image-to-3D Skill Just generated a cute avatar for Sam Altman

Hyper3D by Deemos

80,329 Aufrufe • vor 4 Monaten