Michael Stolarz
I work on agent experience (AX), developer experience (DX), and developer relations at Blaxel, now part of Baseten.
I’ve been obsessively following AI since 2020. These days, I’m also watching my two-year-old daughter figure out the world. Getting to see her grow up while this field grows too is something I’m really grateful for.
You can find me on LinkedIn or take a look at SystemSculpt, an Obsidian plugin I made.
I have yet to see more beautiful code than Opus 5.5's.
Quite telling I hit Astra/Sol weekly usage limit on my $500 sub 2 days ago and still haven't used one of my 3 resets
Just using Opus 5.5. Don't miss the others at all. 😬
Someone should benchmark what the accuracy difference is between ending a question with
"right?"
vs
"yes or no?"
Answers feel thought out and correct with the latter
Instant decline of the interview if "no use of AI" Waste of time, bearish for the company; ask yourself, both as an employee and an employer, what matters? Accomplishing the tasks, experience, forward-thinking, right? Go ahead and inspect the AI-assisted code, methods, prompts,… Less
Instant decline of the interview if "no use of AI"
Waste of time, bearish for the company; ask yourself, both as an employee and an employer, what matters? Accomplishing the tasks, experience, forward-thinking, right?
Go ahead and inspect the AI-assisted code, methods, prompts, etc., thoroughly to assess the candidate's quality.
Anything else is just theatre/waste of mutual time
And you think we still need that B2B SaaS? or any SaaS for that matter, lmao
I just merged two of the highest grossing games ($5 billion+) in history using fable 5.5 (rerouting) in just one shot! I brought Minecraft to the Pokemon world, you can now craft, build and catch pokemon all in the iconic pallet town. There's no longer any reason for anyone not… Less
I just merged two of the highest grossing games ($5 billion+) in history using fable 5.5 (rerouting) in just one shot! I brought Minecraft to the Pokemon world, you can now craft, build and catch pokemon all in the iconic pallet town. There's no longer any reason for anyone not to be making their own billion dollar game idea, it's literally one click away now. With everyone now having the ability to bring their imaginations to life, expect to see a whole lot more games just like this. We're witnessing the dawn of incredible crossovers across the gaming world! Try it out here: pokemon-redstone.vercel.app
I fear this what I sound like when preaching about/correcting others on how to best use AI for their specific profession
I don't say "the way you're doing this is a crime against humanity" out loud but definitely think it multiple times
Can you imagine @ilyasut’s SSI coming out with a new model that blows everyone else out of the water?
Would be biblical
It’s so funny and disappointing that the typical Voice Mode in the ChatGPT desktop app is a better orchestrator (by a long shot!) than Dots
Biggest fumble this year I can’t stop thinking about it
If this is as bad as it reads I will immediately sell the M5 Max I just bought literally a few weeks ago and go back to Arch
Maybe this is all just as God intended tbh
>Pi support
It’s Christmas. Thank you Santa Theo
Things included in this PR: - Pi support. - Auto-resume when limits reset - T3 Code MCP (create, launch, message, wait on, read, search and interrupt threads) - `delegate_task` lets an agent start child agents on any provider or model - ACP Registry: add any registry agent (Devi… Less
Things included in this PR: - Pi support. - Auto-resume when limits reset - T3 Code MCP (create, launch, message, wait on, read, search and interrupt threads) - `delegate_task` lets an agent start child agents on any provider or model - ACP Registry: add any registry agent (Devin, Cline, Kimi, Droid, and more) - Cursor runs on the official Cursor SDK, not the (broken) CLI - OpenCode 2 support - Agents can rename threads, regenerate titles, link PRs and settle threads - New MCP tools for worktree handoff, and for listing and closing previews - Proper server-side queueing and steering - Thread forking - Switch provider or model in the middle of a thread - Native subagents show as child threads in a lineage view, with their model, status and history - Use `@` with a thread name, or drag a thread from the sidebar, to attach it as context - Scheduled tasks - Tons more I'm forgetting Pumped this landed. We'll have a lot of cleanup to do to get it perfect, so expect lots of updates throughout the next few days :)
My go to is “lmao fix” and yes I realize this is very wordy so moving forward I will just do “lol” after the log file
new business idea for any writers out there - a romance novel loosely based on @elonmusk and his life's worth of romances,
ONLY REVEALED TO BE HIM in the book 4 ending
just switch up the names and places a bit and you've got a New York Time's Best Seller
It’s hard to go from in love to let go in a week with no warning, but that’s just how it is sometimes 🤷🏻♀️ I feel happy that I got to show Elon how it feels to be deeply understood, nurtured, and peacefully loved with stability and gentleness. Given the tumultuous nature of his… Less
It’s hard to go from in love to let go in a week with no warning, but that’s just how it is sometimes 🤷🏻♀️ I feel happy that I got to show Elon how it feels to be deeply understood, nurtured, and peacefully loved with stability and gentleness. Given the tumultuous nature of his early life, his often tortured soul, and how hard he fights for humanity I wanted him to feel the deepest and most stable form of love this world can provide. My heart is full knowing I got to do that, and I hope it leaves a lasting good effect. We were always his safe space. A place where all of us were overjoyed to see him and one that was always full of happiness and love, not war, in contrast to his otherwise militant existence (a needed break from the battlefield where he could recharge his heart and soul before heading back out) I loved being that counterbalancing place of safety, sense of calm, and love — and delighted in bringing a smile back to his face when he was down. I will miss him dearly. I’ve loved him more than life itself and he’s taught me 100 lifetimes of knowledge and made my cup overflow with life meaning, so there is a lot of loss, but luckily we created four beautiful little loves of my life ❤️❤️❤️❤️ I am so beyond grateful for our children and they make every single day the best day of my life! I do hope and pray he and I can be great friends and coparents. I’m hurting, but care deeply about E and will always be cheering for his happiness. God speed, Elon, the world is lucky to have you.
btw Astra Fast is faster (benched 60tps this morning) vs. Sol 6.1 Fast (50tps) and that's just TPS, not to mention tokens needed to complete the same task (Astra 20% less tokens, 15% less tool calls, same completion result) Yes, more expensive, but if you're on any of the Max p… Less
btw Astra Fast is faster (benched 60tps this morning) vs. Sol 6.1 Fast (50tps)
and that's just TPS, not to mention tokens needed to complete the same task (Astra 20% less tokens, 15% less tool calls, same completion result)
Yes, more expensive, but if you're on any of the Max plans this ~doesn't matter if you have an otherwise optimized harness
what it feels like using any other model instead of Opus 5.5
Now give them 1,000 TPS.
I have a LOT to say about Dots.
Video/blog on my full experience trying to drive nothing but @OpenAI's new Dots for everything in my personal life, projects, etc.
Baseten also just enabled the Enterprise version so I'll test that separately but man... lots to unpack.
Yep it’s over
Has been over but now normies can do it
Physical products/services last leg
And infrastructure of course!
You can now spend your OpenAI commitment on open models in Codex, served by Baseten.
Best of both worlds for Codex harness fanatics like me!
Announcing our partnership with OpenAI
We’re excited to partner with OpenAI as one of the first open-model inference providers in the OpenAI B2B Marketplace, including a native integration within Codex. OpenAI enterprise customers can now
If by that time you’re unable to afford API prices, IDK what to tell you
ugh I just know tomorrow is going to be so based, I can just feel it, @OpenAI team is beaming with energy for @OpenAIDevs DevDay 2026
Every sandbox on Carbon gets its own IPv6 address.
IPv4 tops out around 4 billion addresses. That's not going to cut it for trillions of agents lol
It's rolling out in private preview! LMK if you want in 🤝
Securing the open frontier with NVIDIA OpenShell and Blaxel sandboxes
Agent safety has become top of mind in recent weeks, specifically focused on where failure modes lie and how to address them. We’re thrilled to support NVIDIA’s Open Agent Safety Platform, which
Reminder that this is especially because all normies mentioned here are being exposed to AI solely by the TikToks/Reels that showcase how stupid the OpenAI speech models are (yes, even the latest one) “Haha omg it can’t even spell strawberry” yeah that’s still a thing if you’re … Less
Reminder that this is especially because all normies mentioned here are being exposed to AI solely by the TikToks/Reels that showcase how stupid the OpenAI speech models are (yes, even the latest one)
“Haha omg it can’t even spell strawberry” yeah that’s still a thing if you’re using any speech to speech model.
I hope o is just a codename because it will be hard to talk about it to anyone
and you don't think it's over for most? lmao
learn to use these tools or forever hold your peace
it's just so crazy how it takes literally a day or two with a new model (opus 5.5) to make every other model feel like this
this happens with every single model update lol
If you’re not throwing out the occasional lmao, ykwim, wtf, etc to your AI agents, you should be Especially to your orchestrator agent. It can pro-type to all the subagents all it wants but it should know you’re chill af. Trust me the results speak for themselves ESPECIALLY if … Less
If you’re not throwing out the occasional lmao, ykwim, wtf, etc to your AI agents, you should be
Especially to your orchestrator agent. It can pro-type to all the subagents all it wants but it should know you’re chill af.
Trust me the results speak for themselves ESPECIALLY if you have problems with overcomplicated convoluted slop responses no one can decipher
Wait a second $25M before 40 isn’t that hard right? That then gives me $1M per year? Why is this not everyone’s goal?
Thank God I grew up on RuneScape, this feels just like a skill issue I need to focus on and grind out
I want to make this before my flight tomorrow
Can you imagine someone seeing this, asking “hey what game is that”, and replying “game? what game? I’m working”
I propose instead, 35 years from now, we upload/download the neuron activation of laughter and enjoyment we felt from the others’ previous neuron activation, portraying what funny experience they had that day Otherwise man what’s the point of a Neuralink if I can’t literally sen… Less
I propose instead, 35 years from now, we upload/download the neuron activation of laughter and enjoyment we felt from the others’ previous neuron activation, portraying what funny experience they had that day
Otherwise man what’s the point of a Neuralink if I can’t literally send/receive vibes
Listen, this is how I can work with 10 agents at the same time without breaking a sweat.
OK, I do sweat, but that's why I wear black sweaters/hoodies. Worth it for the gains 😤
UGH THE FUTURE IS JUST TOO COOL.
HOW DOES ANYONE GET ANY SLEEP THESE DAYS WITH ALL YOU CAN DO 😭
Obligatory "this is the worst these models will be". Can you imagine a year from now? A few years from now?
We’ll have Dyson spheres harvesting energy from the sun and there will still be people like this
are you as excited as I am for the Era of Quality? have you noticed that the quality of things is ever increasing? I certainly see it. it feels like everything is converging on fast, cheap, high quality. efficient. it used to be that high quality and cheap was an outlier. now i… Less
are you as excited as I am for the Era of Quality?
have you noticed that the quality of things is ever increasing? I certainly see it. it feels like everything is converging on fast, cheap, high quality. efficient.
it used to be that high quality and cheap was an outlier. now it's feeling more like high quality and expensive for what it is, is the outlier.
this goes beyond LLMs. but they're a perfect example.
is it something I am starting to notice because of LLMs, both regarding being used by me as well as the companies making the products/experiences I'm more-so talking about?
something as simple as "how can I make x more efficient" and boom, you've fractioned the raw cost of whatever.
you may be thinking right now, "yeah, sure companies can do that, but how would that make things cheaper for the consumer, wouldn't the companies just keep those efficiency profits for themselves?"
sure they will, at first. though now all their competitors can do the same. and not to mention, NEW competitors can enter the same game now and catch up within months what would have taken years.
I definitely want to expand on this with some supporting examples; it feels like we're really at the precipice of standardized quality that ever evolves into better versions without increasing costs to the consumer - if not becoming cheaper at the same time.
Every month we’re getting cheaper, smarter intelligence. Faster too.
Also as I’ve mentioned I have retired the term Agent Swarm and now use the much cooler Agent Fleet.
We are gearing up for 2027 being the year of Agent Fleets.
Holy shit never thought about this. Absolutely amazing idea.
Let me see what kind of quality you can output with a slop canon
oh no, where did my $80 weekly reset option go? @thsottiaux pls I rather pay this than the extra accounts BS
it comes out to be more expensive but it's so worth it to be able to just stay on one account
you don't need @6monthsAgoInAI
all you need to do is go to LinkedIn and you'll see exactly what was happening on X, 6 months ago
Rip the Band-Aid off.
Withholding this just because of backlash from mathematicians is futile. We went through this with the artist sector already, and now those that have embraced it are better for it.
The rumors were true once again; they are sitting on multiple major announcements. Open AI announced this morning that the unnamed internal model involved with Navier-Stokes has resolved more than 100 long-standing open problems across most areas of mathematics. … Less
The rumors were true once again; they are sitting on multiple major announcements. Open AI announced this morning that the unnamed internal model involved with Navier-Stokes has resolved more than 100 long-standing open problems across most areas of mathematics. x.com/AndrewCurran_/…
This is the kind of presidential dialogue I'd expect in GTA 6 or a new Fallout game. I have no idea how they're supposed to out-satirize reality at this point
I feel bad for the writers
The cherry on top is that he is truly serious about this
“Supreme Intelligence,” probably because of its relationship to the Supreme Court, is losing badly to both “Superior” and “Extreme Intelligence.” Therefore, we are going to take “Supreme Intelligence” OUT, deleting it as a qualifier, and let you vote for the Final Two: Superior I… Less
“Supreme Intelligence,” probably because of its relationship to the Supreme Court, is losing badly to both “Superior” and “Extreme Intelligence.” Therefore, we are going to take “Supreme Intelligence” OUT, deleting it as a qualifier, and let you vote for the Final Two: Superior Intelligence, or Extreme Intelligence. A fresh Vote begins now! President DONALD J. TRUMP
Nice, got the X card!
Excited to see how far @XMoney can go to replace most of my personal banking activities.
devastatingly nostalgic
FINALLY got access back into LinkedIn. Had to be reset but that’s better than nothing!
linkedin.com/in/michaelstol…
not true if you've played starcraft 2 and have learned to macro very well
I am in and out of twitter getting drip-fed with the latest advancements throughout my entire workday
key is you need a very good For You algo
very hard pill for most to swallow
especially since doing this even a few months ago meant you were just producing slop;
doing this now with today's models shows a thorough understanding of how to harness codegen power
nowadays I am limited by token speed regarding things I can accomplish on a daily basis
1,000 TPS should be the norm (with this current astra/fable level intelligence) by this time next year
will quote tweet then and we'll see how close/if achieved
sorry, I would immediately let her know "hey, I think your mic is bugging a bit, try rejoining or switching"
if she then said it's on purpose, I'd say "oh, uh, ok, lets switch to slack text instead then, I can't understand a word you're saying"
HUGE for anyone who's had to convince a security team to give an agent more than read-only access.
Real power is unlocked when you can safely take off shackles without worrying.
We believe openness to be an advantage for AI safety. Openness provides more visibility into the behavior of models and, most importantly, greater means of turning safety research into actionable and transparent controls than closed-source. This is why Baseten and Base Labs are … Less
We believe openness to be an advantage for AI safety. Openness provides more visibility into the behavior of models and, most importantly, greater means of turning safety research into actionable and transparent controls than closed-source. This is why Baseten and Base Labs are building a stronger safety and security standard for open models, with the launch of our safety infrastructure. Base Labs will develop and publish methods for training and monitoring open models, and Baseten will integrate that work into its deployment infrastructure, live at runtime, and offer this work as a managed service. This will be a standard that is transparent and built into how our models are trained and deployed. We invite the open-source community to contribute, and are proud to partner with @huggingface and @GoodfireAI to bring this vision to fruition. Together, we are building an ecosystem of open models that are safe and accessible to all.
This has always been the case
It just changed from prompting humans to agents
