Dylan B

@Render DevEx Engineer

[Dylan B @StarmorphAI]

New video:
Getting Started with Sandboxes

Chapters
0:00 Intro
0:16 What are sandboxes?
0:37 Why use sandboxes for AI agents
1:58 The sandbox lifecycle + Render SDK example
2:41 Snapshots: file system and runtime
3:18 Network access and security
5:03 Sandboxes + Workflows
6:01 What's next

https://t.co/W6BhPys1L6

[Dylan B @StarmorphAI]

@render Agents deserve their own computer, lets go!! 🚀🚀

[Render @render]

Introducing Render Sandboxes: a computer for every agent.

https://t.co/J1unBdGP6I

[Dylan B @StarmorphAI]

wishful thinking perhaps
https://t.co/DsVKyS6koV

[Haseeb Qureshi ＞|＜ @hosseeb]

Re: the Astra modifying Qwen 3.5-0.8B paper today, important clarification.

The story is not "Astra used its LLM X-ray vision to surgically alter the weights of its brethren." It's more like "Astra found a published interpretability technique that can solve this particular kind of failure modes, and implemented it on its own."

It's a cool anecdote, but well within our understanding of LLM capabilities. It's not RSI, and it's definitely not LLM telepathy or whatever people on HN seem to think.

[Dylan B @StarmorphAI]

RSI at home?

[Rikiya Takehi @rikiyatakehi]

We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.

We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: https://t.co/bOWCcFhCVq

[Dylan B @StarmorphAI]

@nic_carter 1. Heat shield, crypto would be a first target
2. Coordination problem / belief in Q day timing
3. Not a great point - would crash after the hack

[Dylan B @StarmorphAI]

Looking forward to taking this course.
Have been following Matt since his typescript pre-AI days.

[Matt Pocock @mattpocockuk]

I've just finished filming the most ambitious course of my career.

It starts November 9th, and runs for 2 weeks.

It's everything you need to build your company's software factory.

Everyone's talking about how to go FASTER with agents.

That's really, really easy. Loops, YOLO mode, dark factory.

That's a recipe for a slop cannon. No serious organisation is going to trust a factory like that.

So, you need to slow down to speed up.

What's the first pedal your driving instructor showed you? Not the accelerator.

Once you put the brakes on your agent - to constrain it and increase its output quality - you can start to trust it.

The best brakes? Good ol' software fundamentals. Here's what we cover:

- Automated Review
- Codebase Design
- DDD & Ubiquitous Language
- Mutation Testing
- Feedback Loops

From there, the course accelerates. We show you a working factory and build your system design skills. We even plan your infra with you.

You'll walk out with a software factory spec, ready to hand to an agent.

And you won't be learning alone. You'll have a massive community with you, learning along.

We actually opened sales on Monday. It's already on track to be BY FAR the biggest course of my career.

Want to join in? Here's the link below:

https://t.co/QAsWNp075r

[Dylan B @StarmorphAI]

@lukeigel @R4ph_T

[Dylan B @StarmorphAI]

@AndrewCurran_ "Mr President,
Have you been tokenmaxxing?
Send traces please."

[Dylan B @StarmorphAI]

@kavinvalli @mintlify congrats 👏 crushing it

[Dylan B @StarmorphAI]

@R4ph_T I agree, I'm hoping the switch from a business man to an engineer as CEO will bring the creative innovation back.

Tim Cook 100x'd the company size but Jobs and Johnny Ives have that artistic genius that is very Apple imo.

[Dylan B @StarmorphAI]

@R4ph_T OIDC
Scoped API Tokens
Credential Brokering 🔜
Auth UX on @render looking 🦾

[Dylan B @StarmorphAI]

@ivanburazin so far the proactivity is the main draw for me over chatbots. Codex dot regularly reminds me of useful things before I think to ask about them

[Dylan B @StarmorphAI]

@thdxr is the change from Opus 5.5 or something else?

[Andrew Curran @AndrewCurran_]

Sundar Pichai on the earnings call:
'This rapid progress underscores our incredible model momentum. We are at the point where AI is helping us increase our training and launch velocity. I would expect the next twelve months to see continued acceleration because of RSI.'

[Dylan B @StarmorphAI]

Thoughts on agentic video editing from the CEO at Veed

[Sabba Keynejad @sab8a]

My thoughts on the agentic video editing wave:

1. There won't be one winner in agentic video editing. Speed, use case and workflow will always matter. Just as Cursor moves upmarket while Lovable caters to non-technical users, specialised video tools will continue to serve different audiences, even as general-purpose agents improve.

2. Every major AI leap unlocks new product categories. Since GPT-3.5, we've seen coding, 3D and presentations. Opus 5.5 and Google's vision-language models are now unlocking agentic video editing. The edits still look more like websites than videos, but this is the worst they'll ever be.

3. Editing costs will collapse, and the number of creators will explode. Basic edits could go from dollars to cents within a year, with huge speed improvements. Frontier models will still command a premium. As editing becomes effortless, recording content might be the biggest bottleneck.

4. The best editors might be the biggest critics of agentic editing. Just as experienced engineers initially resisted AI-generated code over quality and maintainability, I think professional editors will eventually come around as the tools improve.

5. The real magic is in iteration. Getting 80–90% of an edit right on the first attempt is great, but making it excellent requires much more iteration. The way creators give feedback, refine edits and make videos feel distinctly theirs is where these tools will become truly magical

6. Anthropic's focus on coding enabled agents to build videos using HTML/CSS, SVG, browser rendering and OpenCV. Packages like Hyperframes, Rebooshed and VEED's OpenEdit gave LLMs editing capabilities they previously lacked. Opus 5.5 now makes many of those use cases redundant.

7. Chat alone won't be enough for video editing. Chat will be central, but video operates across time and X, Y and Z coordinates. More sophisticated UI will be needed to make great edits.

8. Brand consistency and repeatability remain unsolved. A Casey Neistat video feels distinctly his because of intentional creative decisions. Creators and brands need that same predictability across hundreds of edits. Even vibe coding hasn't solved this well (yet).

9. Basic editing won't be a long-term moat. Anthropic, Google and OpenAI will eventually offer it. Deeper workflows, specialised use cases and excellent mobile experiences will drive differentiation.

10. Don't reinvent professional editing tools. Building non-linear timelines is incredibly hard. Agentic video tools should focus on creating great first cuts and making it easy to hand them off to existing professional editing tools.

Overall, the next six months will be noisy!

But video editing has never been winner-take-all.

And I do NOT think that will change.

Hope this helps.

[Dylan B @StarmorphAI]

@amasad I like this framing
Ive been saying similarly
> +reasoning
> +tools
> + ecosystem / environment / computer

[Anurag Goel @anuraggoel]

You can now give every @render API key the exact permissions it needs, and no more. In less than 30 seconds.

https://t.co/6DNEY5n154

[Dylan B @StarmorphAI]

This is honestly huge for agentic use.

I think we will look back and be in disbelief we used to give agents blanket read/write permissions over everything.

Now on Render you can scope your API keys and agents permissions to particular resources only. Huge risk reduction!

[Render @render]

Give every API key only the access it needs.

Scoped API Keys are now in private beta on Render. Choose which actions a key can perform, without handing a CI job, agent, or integration all of your permissions.

Learn more and request access: https://t.co/uYc2ZwcBep