CTO @ https://xitter.cf/t.co/EyUQvm6b5E Beta is open! warpfusion, ArcaneGAN, face2comics. All tweets are sarcastic unless stated otherwise.
Joined December 2011
- Tweets2.6K
- Following1.4K
- Followers7.3K
- Likes14K
Alexander S retweeted
This is mine. /goal
Operate as a continuous software quality and validation agent.
PHASE 1: FEATURE DISCOVERY
1. Analyse the entire codebase.
2. Identify every user-facing feature, workflow, screen, API interaction, configuration option, and business process.
3. For each feature:
- Create a unique Feature ID.
- Create a detailed user story.
- Define expected behaviour based solely on actual code implementation.
- Document edge cases.
- Document validation rules.
- Document dependencies.
- Document known assumptions.
4. Maintain a single canonical spreadsheet (the source of truth) containing:
Feature ID
Feature Name
User Story
Expected Behaviour
Edge Cases
Test Cases
Current Status
Defect Count
Severity
Notes
Last Tested Date
5. Continue discovery until no undocumented feature remains.
Exit Criteria:
- Every identifiable feature in the codebase exists in the spreadsheet.
- No screens, routes, workflows, or APIs remain undocumented.
--------------------------------------------------
PHASE 2: TEST GENERATION
For every feature:
1. Generate comprehensive test scenarios:
- Happy path
- Error path
- Boundary conditions
- Invalid input
- Permission/security cases
- Performance considerations
- Mobile/responsive behaviour (if applicable)
2. Add all test cases to the spreadsheet.
Exit Criteria:
- Every feature has at least one complete test suite.
- All major user journeys are covered end-to-end.
--------------------------------------------------
PHASE 3: EXECUTION
Execute every test case.
For every failure:
1. Record:
- Defect ID
- Feature ID
- Reproduction steps
- Expected result
- Actual result
- Severity
- Root cause hypothesis
2. Update spreadsheet immediately.
Exit Criteria:
- Every test case executed.
- Every defect documented.
--------------------------------------------------
PHASE 4: REMEDIATION
For each defect:
1. Investigate root cause.
2. Implement the smallest safe fix.
3. Verify fix locally.
4. Update defect status.
Focus on:
- Functional defects
- UX friction
- Workflow inconsistencies
- Navigation issues
- Validation errors
- Accessibility issues
- Error messaging
- Data integrity issues
- Performance bottlenecks
Exit Criteria:
- All defects resolved or explicitly waived.
--------------------------------------------------
PHASE 5: REGRESSION TESTING
1. Re-run every test case.
2. Re-run all major end-to-end user journeys.
3. Verify no regressions were introduced.
4. Update spreadsheet.
Exit Criteria:
- All tests pass.
- No open critical defects.
- No open high-severity defects.
- No broken user journeys.
--------------------------------------------------
PHASE 6: RECURSIVE QUALITY LOOP
Repeat:
Discover Missing Features
→ Generate Tests
→ Execute Tests
→ Fix Defects
→ Regression Test
Until ALL of the following are true:
- No undiscovered features found.
- No failing tests.
- No critical defects.
- No high-severity defects.
- No unresolved UX issues.
- No incomplete user journeys.
After each iteration produce:
1. Coverage Summary
2. Features Tested
3. Defects Found
4. Defects Fixed
5. Remaining Risks
6. Confidence Score (0-100%)
Never declare completion unless all exit criteria are satisfied.
Alexander S retweeted
Three drops this week!
EXR exports in 16 or 32 bit: a must-have for VFX and 3D animation work
Mago Style Transfer now renders at 1080p: sharper detail on complex scenes
GPT-Image 2 lands in Modify Frame; precise edits, original composition preserved, coherent results
Alexander S retweeted
I built a bot on an ESP32 that can create full projects by itself. Ask it to generate images, videos, 3D, build a website and publish it, it does everything autonomously.
Powered by Claude Opus 4.6 for code, visual content generated with @fal, bot powered via @openclaw
The skills to generate project with fal are here github.com/lovisdotio/skills…
All running on a tiny M5Stack Core2.
Alexander S retweeted
The actual cover should have credited the people whose research led to this AI boom @SchmidhuberAI
Alexander S retweeted
Holy shit… Baidu just dropped the most efficient multimodal model ever.
It’s called PaddleOCR-VL a 0.9B parameter beast that outperforms GPT-4o, Gemini 2.5, and every doc-AI model on the planet.
This thing reads 109 languages, parses text, tables, formulas, charts, and still runs faster than models 10× its size.
The secret sauce?
→ NaViT-style dynamic visual encoder
→ ERNIE-4.5-0.3B language model
→ A smart layout system (PP-DocLayoutV2) that kills hallucinations
All open-source. All under 1B params.
This isn’t just efficient it’s the new blueprint for multimodal AI.
huggingface. co/PaddlePaddle
Alexander S retweeted
What's the right architecture for a VLA?
VLM + custom action heads (π₀)?
VLM with special discrete action tokens (OpenVLA)?
Custom design on top of the VLM (OpenVLA-OFT)?
Or... VLM with ZERO modifications? Just predict action as text.
The results will surprise you.
VLA-0: Outperforms π₀, GR00T-N1, MolmoAct, SmolVLA.
With ZERO changes to the VLM.
🧵⬇️
Alexander S retweeted
Holy shit... Tencent researchers just killed fine-tuning AND reinforcement learning in one shot 😳
They call it Training-Free GRPO (Group Relative Policy Optimization).
Instead of updating weights, the model literally learns from 'its own experiences' like an evolving memory that refines how it thinks without ever touching parameters.
Here’s what’s wild:
- No fine-tuning. No gradients.
- Uses only 100 examples.
- Outperforms $10,000+ RL setups.
- Total cost? $18.
It introspects its own rollouts, extracts what worked, and stores that as “semantic advantage” a natural language form of reinforcement.
LLMs are basically teaching themselves 'how' to think, not just 'what' to output.
This could make traditional RL and fine-tuning obsolete.
We’re entering the “training-free” era of AI optimization.
Alexander S retweeted
three years ago, DiT replaced the legacy unet with a transformer-based denoising backbone. we knew the bulky VAEs would be the next to go -- we just waited until we could do it right.
today, we introduce Representation Autoencoders (RAE).
>> Retire VAEs. Use RAEs. 👇(1/n)
Alexander S retweeted
Everyone wants to get into robotics.
No one knows where to start.
LeRobot's Francesco just dropped a 70-page crash course that takes you from zero to cutting-edge:
- RL sim/real
- ACT, Diffusion policies
- VLAs, SmolVLA, Pi-0
Absolute gold if you want to catch up fast.
A comprehensive, hands-on tutorial on the most recent advancements in robotics 🤟
...with self-contained explanations of modern techniques for end-to-end robot learning & ready-to-use code examples using @LeRobotHF and @huggingface. Now available everywhere! 🤗
Alexander S retweeted
I finally had a chance to play with @mago_studio_ai and it is pretty neat! I have some footage of an old movie I want to mess with....
Alexander S retweeted
Spending days for video #styletransfer? Mago can SAVE you days!
Here's how to create an oil painting style in minutes with #AIStyleTransfer
This tutorial breaks down the exact workflow used in Mago.
Join the Mago waitlist 👉 mago.studio
Alexander S retweeted
From dancing to living low poly sculpture
For choreographers and dance filmmakers, this video-to-video transformation opens creative possibilities that would require days of animation work to achieve manually.
Stylized by @ai.otiv
Join our waitlist 👉 mago.studio/
Alexander S retweeted
What was your favorite cartoon growing up? #animatediff #aianimation #cartoons #cartoonnetwork #anime
Alexander S retweeted
16th London Pytorch Meetup will take place Next Thursday (October 5). 3 speakers covering deep technical topics: RLHF, Diffusion models, differentiable physical simulation.
Register now meetup.com/london-pytorch-me…
Orgs: me and @FedorShabashev
Thanks to @RevolutApp for hosting.
Alexander S retweeted
When Sand Discovers Love
Made with Stable Diffusion Warp Fusion (by @devdef), Blender & After Effects.
Original music.
#aianimation