Sean Kerner

Sean Michael Kerner's Spring 2023 Human Writer certificate authory.com/SeanMichaelKer… That's write I'm human. I write about #AI. Skynet hasn't won (yet).

The open-source StarlingX distributed cloud platform gains precision timing support in its first major update of 2026. networkworld.com/article/416654…

@LayrKits Looking looking forward to seeing you right up. This is a problem that I’m struggling with right now.

For the last 2+weeks, I’ve been working on a pipeline for creating clean, production ready 2D sprite sheet animations. I’ve achieved really good results and I’m currently finalizing a full write up for the workflow. It will include a step by step guide you can feed to the coding agent of your choice to recreate the full workflow. And I’ll be including all the tips and tricks I’ve learned along the way. And yes, as you can see in the video it can handle the walk/run sequences as well 😄

open sourcing retrotech is great "Continuing the story of early DOS development" opensource.microsoft.com/blog/2026/04/2…

Meta abandons open-source Llama for proprietary Muse Spark: thenewstack.io/meta-abandons-… via @thenewstack & @sjvn If you're still using the #opensource #AI Llama, Meta's left you without a migration path.

Warp's gamble: Going open source to take on closed-source rivals: thenewstack.io/warp-open-sour… via @thenewstack

The retrieval rebuild: Why hybrid retrieval intent tripled as enterprise RAG programs hit the scale wall -no RAG is not dead, but it is...changing. venturebeat.com/data/the-retri… via @VentureBeat

I've been a networking 'guy' for a long time. But the kids out there today..they don't know ...and there is a looming skills gap that could be a real problem (one day). That's the 'big switch' that agentic AI could bring to networking that @AuvikOfficial is betting on. "The more we can automate and simplify and help people with auto remediation, the more powerful the platform becomes.” networkworld.com/article/416509…

Data pipeline failures are agentic AI failures - definity claims 10x faster Spark issue resolution by acting inside execution, not outside it. venturebeat.com/data/definity-… via @VentureBeat

Definity's $12M bet: stop pipeline failures from the inside. The startup embeds agents in Spark execution to intervene before bad data reaches downstream AI systems. venturebeat.com/ai/definity-em…

They stole a nonprofit. It’s not right.

@bwarrn how is this different than S3 Files?

I'm so excited to officially share what we've been cooking up at Mesa: the most powerful filesystem ever built for AI agents. The dirty secret of every "production" AI agent today: the filesystem is held together with duct tape. Teams are stitching together S3, GitHub, sandbox-local disks, and homegrown diff logic to give their agents something resembling persistent, versioned storage. None of it works. S3 isn't designed for parallel agents - concurrent agent writes silently overwrite each other. GitHub has the semantics but rate-limits you into the ground at agent scale and doesn't give you filesystem ergonomics. Sandbox disks vanish the moment the container dies. And your agents don't want to git clone and git push anyway. 𝗧𝗵𝗲𝘆 𝘄𝗮𝗻𝘁 𝘁𝗼 𝗿𝗲𝗮𝗱 𝗮𝗻𝗱 𝘄𝗿𝗶𝘁𝗲 𝗳𝗶𝗹𝗲𝘀. 𝗟𝗶𝗸𝗲 𝗲𝘃𝗲𝗿𝘆 𝗽𝗿𝗼𝗴𝗿𝗮𝗺 𝗲𝘃𝗲𝗿 𝘄𝗿𝗶𝘁𝘁𝗲𝗻. So we built the missing layer. Mesa is a durable, POSIX-compatible filesystem with version control built in. Branches, diffs, history, rollback, access control — every primitive a codebase has, for any file type, at agent scale. You mount it. Your agent uses it like a normal filesystem. We handle the rest. Private beta is live. Link in comments.

@Lovable do you have to be a subscriber first though? Can users on the free plan also do this?

Every product needs a home. Get yours before someone else does. Buy a custom domain in Lovable in the next 3 days for just $1.

We just published research on retrieval tradeoff that should get the attention of anyone building RAG or agentic systems. Read more here from @TechJournalist in @VentureBeat: venturebeat.com/data/rag-preci…

RAG precision tuning can quietly cut retrieval accuracy by 40%. Hybrid search won't fix it, and neither will reranking. Here's what the research says actually works. venturebeat.com/ai/rag-precisi…

AI's not going to kill open source code security theregister.com/2026/04/26/opi… via @theregister & @sjvn Don't follow Cal's footsteps and dump #opensource for fear that #AI will reveal security problems. It's not worth it.

RAG precision tuning can quietly cut retrieval accuracy by 40%. Hybrid search won't fix it, and neither will reranking. Here's what the research says actually works. venturebeat.com/data/rag-preci… via @VentureBeat

The conclusions here feel wrong to me. The two lessons I see are: 1. Don't run agents anywhere they might be able to access production environment credentials - it's on you to know which credentials those are 2. Keep tested backups that are independent from your production host

We are hiring a bunch of Members of the Technical Staff for @GoogleAIStudio who can blend PM, design, eng, and more If this is you, pls DM me, we will move fast for the best people.

@Rosebud_AI How?

The AI game dev stack is getting absurd: ChatGPT Image 2 → cinematic world + sprites (seconds) Rosebud → auto-slices them into your game You → shipping multiple levels in <20 min Reply and we'll send a Rosebud code so you can try it.

Interesting! Anthropic spent $10B building a model so dangerous they wouldn't release it to the public. then a private Discord group accessed it because they guessed the URL. Cybersecurity is officially a comedy.