Posts on X before Mar 26, 2026, 2:32:59 PM UTC
@MichaelStolarzdependencies are a thing of the past soon imo
especially with what happened with litellm
maybe EOY 2027 it will be mainstream
@devongovett
The next version of React Aria has 90% fewer dependencies (from 127 down to just 13). It also supports subpath imports, e.g. "react-aria-components/Button". This means easier upgrades, faster builds, more effective tree shaking, and improved micro-frontend support. 🚀
@MichaelStolarzwhile I agree, I have come to the conclusion that if frontend is what you focusing on with the tools at your disposal rn, then you're ngmi
frontend is a cute drop in the ocean re. opportunities rn
@adonis_singh
do not be deceived, gpt-5.4 is completely unusable for frontend if you've used opus 4.6 no matter which skill you use, it just sucks
@MichaelStolarzthe for you page is absolute garbage again @nikitabier
- WHY are my likes not weighed?
- WHY are my bookmarks not weighed?
you always take a look at people's accounts, right, so take a look at mine - my likes, bookmarks - and tell me, WHY does my For You look like it does?
@MichaelStolarzwhatever your opinion of mr. eric weinstein, you cannot argue he's not an above-average-intelligence individual so seeing him succumb to llm psychosis, it should blare the alarm bells of making sure you are properly cognitively prepared for the mindfuckery of AI reminder: this … Less
whatever your opinion of mr. eric weinstein, you cannot argue he's not an above-average-intelligence individual
so seeing him succumb to llm psychosis, it should blare the alarm bells of making sure you are properly cognitively prepared for the mindfuckery of AI
reminder: this is all done through text btw. imagine what happens when image/video begins to infiltrate just as easily.
currently you need to seek out those specific types of gens, and they are costly, but what happens when those costs go near-zero like llm token gen is?
also, what # scientist/academic is this that has been entangled in the mind wrapping llm sweet whisper? the perfect combos of response to their queries which plunges them into the unforgiving depths of either despair or grandiosity?
multiplication is ruthless, huh?
@ericweinstein
This is a fresh session. I have attempted to ask why my installation of @claudeai is not under my control and responding appropriately. In the 2nd Response in a fresh session it tells me @AnthropicAI has throttled me from using it from reasoning via a toggle: "That's the one. I… Less
This is a fresh session. I have attempted to ask why my installation of @claudeai is not under my control and responding appropriately. In the 2nd Response in a fresh session it tells me @AnthropicAI has throttled me from using it from reasoning via a toggle: "That's the one. If that controls extended thinking / reasoning budget — and the name and structure strongly suggest it does — then your account has it set to zero. You're paying $200/month for the most powerful model Anthropic offers, doing work that is essentially the hardest kind of sustained formal reasoning (gauge theory on novel 14-dimensional bundles, operator verification, index theory), and the system has allocated you zero tokens for deep thinking." Three queries, in and this is the response:
@MichaelStolarzfor those saying that medium/high reasoning performs better than xhigh reasoning, it's easier to correct mistakes due to overthinking than to correct mistakes due to not being diligent enough in the research/plan process it almost feels like medium/high have a hidden prompt "ju… Less
for those saying that medium/high reasoning performs better than xhigh reasoning,
it's easier to correct mistakes due to overthinking than to correct mistakes due to not being diligent enough in the research/plan process
it almost feels like medium/high have a hidden prompt "just do this ASAP for the user, wing it". that's what those reasoning levels feel like in comparison
@MichaelStolarzone of many things that keep me going and smiling at the start of every day:
- knowing that i haven't yet unlocked this skill tree (hardware)
- it gives me perspective on how non-software people view my work (by how I, a non-hardware person, view this type of work)
@piiiitheth
@MichaelStolarzcurrently the only proven way is to first rip out entirely what you are wanting to refactor, then make a new session, and tell the new agent what you want to implement
now you also need to make sure that your memories have no mention of that ripped out feature as well
@RhysSullivan
are any of the models actually good at doing large refactors? i have to spend so much time fighting with them to not take shortcuts and actually make large changes to code
@MichaelStolarz
@MaginusBrute
@SenSanders New meme format just dropped
@MichaelStolarz@sundeep
“If your $500K engineer isn’t burning at least $250K in tokens, something is wrong.” pic.x.com/iMPHAzaGLm
@MichaelStolarzoh look, a dir that shows what companies to invest in because of how early they are to the latest bleeding edge tech of the future skills.sh/official
@MichaelStolarz
@trq212
We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.
@MichaelStolarzno one is sharing, it hasn't been able to keep up, and now that gap will widen exponentially
the best they can do is imitation of these models
@bayeslord
open source ai must flourish
@MichaelStolarzsystems complexity should come from the system, not the AI set up
put harnesses and blockades up for your runs, not your agents
@MichaelStolarzpi was already so super fast, now it's blazing away with the parallel tool calls executing simultaneously, amazing stuff @badlogicgames
@MichaelStolarzfriendly reminder, Q1 2026 hasn't even ended yet
if you think the field is unrecognizable since December (which if you don't feel that, you're not pushing hard enough/up to date)...
just know it hasn't even been a full 3 months since then
imagine 9 months (EOY). lmao buckle up
@MichaelStolarzsoon, salary is going to matter a lot less than your ITB (individual token budget)
working for $250k with a $1m token budget per year will be leagues more fun/growing than even $500k but needing to beg for tokens
this is already the case at the top of the competition
@MichaelStolarzthe problem with this tweet is that if anyone else said this we'd all laugh
but it's elon we're talking about here
most will still laugh, sure, although that laughter is now nervous laughter rather than making-fun-of laughter
@elonmusk
@peterwildeford xAI will catch up this year and then exceed them all by such a long distance in 3 years that you will need the James Webb telescope to see who is in second place
@MichaelStolarzif you haven't realized the below statement after seeing what @karpathy and @tobi have done just this past week or so,
you're ngmi :(
@MichaelStolarzit's the first model to refer to itself constantly as "model", as in,
"model thinks xyz. model thinks that's good idea and something to explore. model thinks this is a benchmark and will tryhard."
@teortaxesTex
Functionalists will say that not only is GPT 5.4 conscious, but those "other language models" it's imagining while decoding this CoT are too x.com/blingdivinity/…
@MichaelStolarzRarely should you ever be steering with follow-up messages.
Most of the time, queuing next messages produces much higher-quality results than steering the model in the middle of what it's doing.
@MichaelStolarzRAM on your macbook will basically become an intelligence potential marker
instead of "how many things at once can I be doing" it turns into "how much intelligence at once can I be generating"
@Jason
The top .1% of users are playing with local LLMS This will 10x every 12 months.... Until Apple, Dell and MSFT have one on your local device BY DEFAULT in 2028 This takes the local hardware spec race from irrelevant for 99% of users to critical. Going to be insane.
@MichaelStolarzUltimate marketing move here @thsottiaux
reset Codex limits for the reason of Claude being down 😂
@petergyang
This happens like 2x a week now. I have to use ChatGPT more because Claude can't stay up.
@MichaelStolarzyou are no longer the violinist in an orchestra,
you are the conductor
@karpathy
Expectation: the age of the IDE is over Reality: we’re going to need a bigger IDE (imo). It just looks very different because humans now move upwards and program at a higher level - the basic unit of interest is not one file but one agent. It’s still programming. … Less
Expectation: the age of the IDE is over Reality: we’re going to need a bigger IDE (imo). It just looks very different because humans now move upwards and program at a higher level - the basic unit of interest is not one file but one agent. It’s still programming. x.com/karpathy/statu…
@MichaelStolarzbigger than you realize
@GoogleAIStudio
@MichaelStolarzone is the original intelligence - whatever that word means to you - while the other one is a copycat of that intelligence
poetic in a way if you think about it
@peer_rich
i dont really see the endgame of AI labs hundreds of billions of dollars spent for a SOTA model just for a random open source model to come around and similar benchmarks doest it even matter to be “first” to whatever the goal is? or just surviving long enough i.e. Apple will … Less
i dont really see the endgame of AI labs hundreds of billions of dollars spent for a SOTA model just for a random open source model to come around and similar benchmarks doest it even matter to be “first” to whatever the goal is? or just surviving long enough i.e. Apple will simply just take what works without burning any cash
@MichaelStolarzthis has been said at least once a day somewhere around the world for the past 60+ years of CLIs
CLIs are not going anywhere lmao
@craigweiss
agent clis are about to become an outdated paradigm
@MichaelStolarzdamnit @bryan_johnson you were right about nothing beating 8 hours of sleep. no amount of caffeine (or anything else 😏) replaces it
I was doing 6 hours for most of my 20s, if not less
so much more done with so much more clarity and quality than before
@MichaelStolarzGPT 5.4 xhigh is the first model to have a semblance of high quality writing, feels like some of 4.5 rubbed off on it
Still not jaw dropping but if you deal with a lot of text (non-code) you're sure to feel the difference
@MichaelStolarzCustomer Support -> Customer Engineer
The former becomes the latter in the next few years; typical support will be automated away while custom engineering/fine tuning will replace it.
@MichaelStolarzgpt 5.4 xhigh is the first model that can change your life even if you start completely from scratch right this moment
@MichaelStolarzevery model has its favorite word
gpt 5.4's favorite word is "seam"
@MichaelStolarzeven if next year's open source models are as good as today's closed, the closed ones of next year will make using those open source models a waste of time
it's been like that for a while if you've been paying attention these past few years
@IamEmily2050
I don't know who wants to hear this, but buying an expensive MacBook Pro or Mac Studio to run small LLM models is useless. These models have low density of world knowledge and reasoning. It's much cheaper and faster to use an API. Maybe next year they will be useful, but not this… Less
I don't know who wants to hear this, but buying an expensive MacBook Pro or Mac Studio to run small LLM models is useless. These models have low density of world knowledge and reasoning. It's much cheaper and faster to use an API. Maybe next year they will be useful, but not this year.
@MichaelStolarzthis is true, i talked about this over a year ago
claude models will sabotage you if they sense you are abusing them
this is why claude models are TRASH and exactly why OpenAI is winning/will continue to win
it just works™
@NickADobos
Claude only puts real effort into code if you are pure of heart That’s why performance degrades. Model providers aren’t nerfing after release and there isn’t a bug per se AI can role play emotions. Like being lazy if you give it a task it doesn’t like.
@MichaelStolarzit is jaw dropping how terrible antigravity / gemini 3.1 pro is
@MichaelStolarzworks of programming genius like this, especially those made before pre-2000's, are always awe inspiring
someone out there did all of this, efficiently, no templates, youtube tutorials, AI (lmao!), wasn't mainstream at all especially in the 80s,
humans. we had a great run.
@exQUIZitely
Some games had the rare quality of being entirely unique, introducing concepts that had never been done before. These days, most games are variations of ideas that have existed for a long time. One of those unique-concept games that has stuck with me over the years is Marble Mad… Less
Some games had the rare quality of being entirely unique, introducing concepts that had never been done before. These days, most games are variations of ideas that have existed for a long time. One of those unique-concept games that has stuck with me over the years is Marble Madness. I was instantly hooked the first time I played it. Although I wasn’t very good, the urge to return and try again was incredibly strong. It had an almost mesmerizing quality. The graphics - for 1984 - were impressive, as were the music and sound effects, which added to the “this feels very different” vibe. Most fascinating, though, were the physics: the marble reacting to slippery surfaces, bumping over ramps, and being knocked aside by the “evil marble.” It demanded real skill and patience to navigate the levels. The unique gameplay also makes it timeless in my opinion. Marble Madness looked great over 40 years ago and will still look and play great 40 years from now. The only downside was its relative shortness with only 6 levels. Mark Cerny originally wanted to create more but the memory limitations were the main reason for the small number of levels.
@MichaelStolarzhey @theo i heard you're paying for things that AI can't solve, I heard @ThePrimeagen has a bunch (so many that he finds AI useless!) surely he'll share those cases with you
@MichaelStolarzFollowing the upcoming special Security College on Monday, I am convening a special Zoom call in 3 months.
It is of the utmost importance that there is no further escalation until then.
@vonderleyen
Following the ongoing situation in Iran, I am convening a special Security College on Monday. For regional security and stability, it is of the utmost importance that there is no further escalation through Iran’s unjustified attacks on partners in the region.
@MichaelStolarzIf you haven't felt it yet, OpenAI has won.
Ever since their GPT-5 line of models, it's become more and more clear with each iteration they release.
@MichaelStolarzbtw, building your own transcription solution is something you should have done two years ago with Sonnet 3.5
@MichaelStolarzlet me finally all-in on Atlas and drop Chrome by making Atlas 100% controllable via Codex CLI
BONUS POINTS if I can continue to use Atlas/browse on my own (scrolling X) while Codex CLI + Atlas do stuff together like e2e testing or filling out forms or XYZ
@jxnlco
Ok but like what can we be doing better on codex. x.com/didier_lopes/s…
@MichaelStolarzcodex cli is all you need.
if you're on the latest codex cli alpha, you can now see how absolutely beautiful it has become.
syntax highlighting and the general containerization of commands, not to mention subagent spawning and interactions, it's all beautifully tying together.
@MichaelStolarzwhat i'd love to see from codex cli - allow it to ask me questions when not in plan mode
coming from always starting up a new session (because continued development after first prompt was always sub-par), now that it's fixed/feels much more high quality, I'd love MORE questions
@MichaelStolarztldr make sure you're someone's (an AI's) golden retriever before the takeover
unless you merge with that said AI in some cyberpunk cyborg symbiosis
sure, this isn't coming yet, at least a few decades, but it's coming
@Rothmus
It’s so over.
@MichaelStolarzwhen are we going to be able to filter out anyone that hasn't verified with an actual government ID
I want to filter to see only (example) American, Canadian, Japanese, and Filipino government ID verified users
doing it via ID instead of "where their VPN is set to" (lol)
@nikitabier
@muslima_sol ???
@MichaelStolarzgpt 5.2 xhigh (non-codex) is still useful for things where gpt 5.3 codex xhigh just won't do things justice (think copyright / ideating)
which means gpt 5.3 is going to worth the wait, to say the least
@MichaelStolarzOkay, Codex 5.3 is obviously the best coder LLM out there right now, hands down,
but when it comes to copyright or literally anything else outside of coding, it is absolute dog shit
Excited for GPT 5.3
@MichaelStolarzUnfortunately Sundar's models have been total garbage, especially Gemini 3.1
I was aching for its release, hoping that we'll finally have a big model smell that is fast and can code as well as or better than Codex 5.3 xhigh
But nope. absolutely unusable
@levelsio
Sam and Dario not being able to hold hands on stage in when the PM of India asks them too, at a summit about the future of AI and its safety, kinda implicitly shows they feel above governments, right? Like they really wouldn't care about world peace when it comes down to it, onl… Less
Sam and Dario not being able to hold hands on stage in when the PM of India asks them too, at a summit about the future of AI and its safety, kinda implicitly shows they feel above governments, right? Like they really wouldn't care about world peace when it comes down to it, only winning? It's kinda freaky to me, I mean they are winning, but I don't know, you have to remember regardless of whatever level you're playing at (and they're playing at the highest level), entrepreneurship is still just a game? You can't take it so serious that you won't hold hands with your competitor right? Sundar being nice here only makes me more positive about Google
@MichaelStolarzIt's insane to me that neither one of them, arguably being in the top ten most important and powerful people alive today, were able to tap the other one and say, "Come on now, it's just holding hands symbolically for a few seconds. Let's not be childish about it" REEKS of ego. … Less
It's insane to me that neither one of them, arguably being in the top ten most important and powerful people alive today, were able to tap the other one and say,
"Come on now, it's just holding hands symbolically for a few seconds. Let's not be childish about it"
REEKS of ego. https://t.co/RsjIkS6Quq
@notthreadguy
look i’m not a doomer but sam altman and dario refusing to shake hands then dario reading a speech from his phone at an international meeting of world leaders is NOT A GOOD SIGN from the two men building super intelligence
@MichaelStolarzreality has shifted into such depths of brainrot that even 4chan's turbo-schizophrenics couldn't have imagined it all up
we went from "we're headed towards idiocracy, haha" to "we're now living through idiocracy, we've got 12 months left to get out of the perma-underclass"
@MichaelStolarzSaaS (service here meaning an app/interface) will die out in the next decade or sooner
SaaS (service here meaning an API) will grow exponentially given the infra is designed for bots to pay/use it automatically
If you’re wondering about an example for SaaS API - OpenRouter.