Luke Haines (@LukeGainzz) header
Luke Haines (@LukeGainzz) profile picture

Front end engineer. Currently working in the CRO & AB testing world.

London, England
Joined November 2011
Luke Haines retweeted
Un-slopping a vibe coded website using blender and Fable 5.2 Free skill is in comments for anyone who wants to improve their site. Just put in your URL and use the skill Show me what you guys make in the comments😀
2
1
63
10,001
Luke Haines retweeted
If you're running subagents of Astra or Sol 6.2, I can't recommend enough running them in what I call dry mode. Everything on top of the model is disabled. These models are absolutely beasts, and they will answer and operate much faster and more efficiently this way.
79
58
2
1,602
101,657
Luke Haines retweeted
anon, you don't need to look far for a crystal ball into the future starting from this assumption, what's your next move?
7
27
1
389
25,204
If you want to understand the Google models released this week read this
Gemini 4 Neon and Gemini 4 Carbon: first impressions. I've been using these models for a while now and have some things to say: Gemini 4 Neon 1. The most creative model I've ever seen. Because it doesn't have the brakes that Fable 5.2 and GPT-6.2 Astra have, it can come up with more interesting solutions to hard problems than they do. I'd been working on a difficult problem with Fable 5.2 for 2 days and was stuck on it. But Neon came up with an absolutely brilliant solution. By the way, Opus 5.5 couldn't handle the task at all 2. You can tell it's a relatively small model. It lacks intellectual horsepower in some places. Because of that, it may not dig into the details as deeply as Fable does 3. Its execution level is comparable to Opus 5.5. Honestly, I don't see any difference between them in coding. Neon might even be better in places. It writes cleaner, more beautiful code 4. In conversation, Neon is practically indistinguishable from a real person. It writes the most beautiful and clear text. I tested it in Russian and English, and its writing is very pleasant to read. I'd say the best of anything on the market 5. On top of the text quality, I'd add its optimism and positivity. It's like your best bro. But sometimes this trait gets in its way on technical tasks. It can judge a potential result too positively and overlook the details and weak spots of its own solution 6. Understands a codebase extremely well. Good bug hunting. And a complete absence of slop in the code 7. If you need to come up with a marketing plan, a project idea, or some features, nobody will do it better than Gemini 4 Neon 8. Excellent taste. At the very least on par with Opus 5.5. But I haven't done much comparison on UI tasks 9. It can sometimes get lost in long tasks. I haven't tested this much, but I have a feeling it may suffer from context rot. I need to work with it a bit longer and test more 10. Very fast. On xhigh it runs at the same speed as Opus 5.5 on medium This is definitely one of my favorite models now. I want to work with it more and more Gemini 4 Carbon 1. In benchmarks Neon beats Carbon, but that's clearly not the real picture. Carbon is without a doubt the bigger and smarter model 2. More thorough and thoughtful than Neon. Give it a big, complex task, and it will autonomously investigate everything and come back with a detailed, thorough, high-quality result. I can't say it's better than Fable 5.2, but it's definitely no worse. As a researcher and analyst specifically, they're on the same level 3. Carbon is 100% better than GPT-6.2 Astra. Literally at everything. The gap is like the one between Fable and Sonnet. And I'm not exaggerating 4. Very, very, very slow. I haven't seen a model this slow in a long time. Ask it the simplest question, something like "How are you," and it'll come back with an answer in about 5 minutes 5. Because of how slow it is, I wouldn't trust it with coding tasks, and there's no point anyway. Neon writes better code 6. Otherwise it's the same as Neon. All of Neon's strengths apply to Carbon too. I won't list them again If you need to plan a big, complex project, you can confidently turn to Carbon. Thanks to its creativity and good writing, in most cases it will give you a more interesting result than Fable 5.2, which is heavily stifled by its system prompt and distillation
1
72
Luke Haines retweeted
Interesting experiment: Showing a live AI avatar her own face in a mirror 🪞 How will she react? You'll be surprised!
205
282
95
3,321
526,331
Luke Haines retweeted
show this video to anybody that is an old school programmer that hates AI this is one of the best videos I’ve seen all month.
1,058
6,218
1,229
45,402
3,718,166
do u fucking ppl understand where we're at rn
Researchers have used reinforcement learning to teach a 5-tonne John Deere skid-steer loader to perform complex acrobatic manoeuvres autonomously. Trained in simulation and transferred to a real machine, the system can balance on two wheels, navigate rough terrain, spin, and control its bucket before landing safely. The research demonstrates the potential of AI-driven automation for heavy construction and industrial machinery. Video Credit: @leggedrobotics / @ETH Paper: wevlv.co/4kltYys #engineering #technology
205
611
39
14,920
828,537
Luke Haines retweeted
Gemini 4 Neon is a huge surprise: first impressions Pros: - Competent - Great communicator - Responds well to correction - Figures out intent like Claude - Best writing model I've ever seen - Very good at learning from context Cons: - Its one shot demos look bad - Doesn't go above and beyond by default - Verifies everything to death (also a Pro kinda) - Slow because of too many tool calls and bad latency Subsidization: Not too bad! ~OpenAI level subsidization And that's on top of already good cost performance at API rates Pretty cost-efficient!
60
25
8
1,088
65,473
Luke Haines retweeted
2022 was the year of autocomplete 2023 was the year of chat 2024 was the year of the AI IDE 2025 was the year of coding agents 2026 was the year of agent orchestration 2027 will be the year of outcome engineering
126
92
35
1,413
717,827
Gemini 4 Neon has entered the arena xitter.cf/demishassabis/status/2…
Gemini 4 Neon even surpassed Fable 5.2 in coding agent index and sits 6 points ahead of the yesterday released GPT-6.2 Astra.
66
Luke Haines retweeted
Replying to @GergelyOrosz
Pretty well deserved by Theo tbf, early to market, focussing on execution, and has a good immediate feedback loop with his customers via Twitter
1
2
669
Truly exceptional work. Renting GPU’s blew my mind the first time I read it but it makes so much sense
The Fable of Clawd A 2 minute 4K film made entirely in Blender, from one prompt on Fable 5.2. It took about 4.5 hours. Claude built every asset in Blender by writing Python: - 5 characters and props: Clawd, his friend Pip, a toy truck, a 3D-printed tulip and a gift box - 7 full sets: a study, a staircase, a street, a workshop, an airport, a night sky and a house - every camera move and every frame of animation across 52 shots That came to 12,500 lines of code. It started 7 copies of itself to build the sets at the same time. Then it rented 89 GPUs through RunPod to render 3,220 frames as fast as possible, 36 of them running at once. Total cost: a little over $20. My biggest takeaway is my Claude Code knows it has access to cloud compute, so it's much more ambitious. I tried a similar prompt on my other computer that doesn't have the runpod skill setup and it wasn't nearly as high quality Full details linked below.
23
Luke Haines retweeted
Fable 5.2 vs. GPT-6.2 Astra - ROUND 2 - 242 KB - 11.1 MB - $158.88 - $39.68 now with eric's 3D skill + xhigh, it computed baked binaries from .cpp files once my tokens reset I'll run another benchmark with modified prompt, have some ideas... 🤔
Fable 5.2 vs. GPT-6.2 Astra - 242 KB - 32.9 MB 💀 5h 34m of compute each @threejs
6
1
1
28
13,198
Luke Haines retweeted
I almost forgot my favourite GPT-6.2-Astra generation - this is SVG (yes SVG!!) of a peacock - no other model came close to the precision, lifelike nature and detail of this generation, incl. Fable
64
101
25
1,624
86,603
Luke Haines retweeted
Stay AWAY from GPT-6.2 Astra on low If you're dropping Astra to low to save usage, just use Sol and turn reasoning up I recommend Claude over OpenAI models right now anyway But if you're going to use OpenAI models, don't use Astra on Low
9
1
2
114
12,129
Luke Haines retweeted
every. single. marketing. department. will. be. flipped. upside. down.
Video editing is following the same path AI coding took in 2025–26. The 10x–100x programmers don’t write code anymore. They build software factories. The people who deeply understand video, brand and storytelling will soon be building content factories.
33
72
13
1,110
86,643
Luke Haines retweeted
the @every team's full ratings for Astra and Sol 6.2 hard to remember a frontier model release like this. opus 5 is the closest comp every.to/vibe-check/vibe-che…
40
8
221
47,471
Luke Haines retweeted
Replying to @nicksaraev
Google has an Ai branding issue. Also, it's voice models are still not SOTA so nobody cares, nor has the google Ai subscriptions - so they don't get used
1
20
1,743
Luke Haines retweeted
Some of you have been asking very politely. Some of you have just been asking. GPT-6.2 Astra and Sol are now available. Super efficient and built to perform where it counts—the real world. openai.com/index/introducing…
2,276
3,604
3,717
35,934
11,761,985
Luke Haines retweeted
ChatGPT and Google give you 20x the usage for 10x the money. Claude gives you 10x.
110
16
6
801
81,954