Posts on X before Sep 10, 2025, 9:58:08 AM UTC
@MichaelStolarzBIG UPDATE TODAY for my systemsculpt lovers.
@MichaelStolarzMOM GET THE CLI
NEW @openrouter STEALTH MODEL JUST DROPPED
@MichaelStolarzonce an llm provider figures out how to do per-account memory, even if it's just an intricate system vs. an llm architecture upgrade, it's game over (specifically in the coding space)
imagine chatgpt's memory and how it utilizes previous chats so intelligently, PUT THAT IN CODEX
@MichaelStolarzI mean, I don't get it. How do you not catch these? @nikitabier surely there's a pattern to recognize here?
@MichaelStolarzthere are still people who think opus (or even sonnet) are better than gpt-5-high
imagine!
@MichaelStolarzthis is solved by having good taste and only ever staying in the Following tab, never For You
@yacineMTB
50% of the timeline is chatgpt generated. *Close app*
@MichaelStolarzhilariously ironic given this was supposed to be the hero against google
ironic especially because you'll see more ads on firefox than on google, lmao
@nearcyan
what a new mozilla firefox install looks like in 2025. even the weather is 'sponsored content'.
@MichaelStolarz@MichaelStolarzlooking back, it's so cringe they didn't release claude code as open source. destined to fail from the start
imagine sending out dmca's for a tui? lmao
@MichaelStolarzwait until the MCP crowd finds out about CLI commands
@MichaelStolarzIf Codex CLI Pro is comparable to Claude Code Max, there’s no reason at all to use Claude Code Max.
Features are easy to catch up to. Model intelligence and efficacy isn’t.
@embirico
Just bumped Codex CLI Plus limits up 50% as an experiment. Enjoy! More transparency coming next week as things settle. x.com/embirico/statu…
@MichaelStolarzmake sure to try out cursor's new sonic model O_O
@MichaelStolarzfew more years til you can have a 1 on 1 sparring buddy 24/7 for infinite workouts and sparring
@MichaelStolarzI hate gpt 5 high so much
because it has made every other LLM unusable
it never lies to me,
never makes the wrong decision,
tells me when it doesn't know/needs more info.
damn. thanks a lot openai.
@MichaelStolarzpls ser i take back what i said about u anthropic pls i have 1 children to feed with my plugin and it needs updates pls 🥺
@MichaelStolarzso weird to see this in gpt 5's thinking traces
thankfully it keeps going?
@MichaelStolarznew v2.0.0 of systemsculpt out
lots of stability updates, byok, ease of use, standard/advanced modes, yeah lots of cool stuff
more official release info later today!
@MichaelStolarzso cool. can someone show me the usa equivalent? no? why not? why does china have 40 types of robots from 20 different startups and we have 3 can-barely-walk-but-marketed-so-well slop bots?
@Sino_Market
🇨🇳The 100-meter dash at the World Humanoid Robot Games, Beijing, China #CHINA #ROBOTICS #humanoid #HumanoidRobots
@MichaelStolarzi hate ironing out the final bugs
they're final bugs for a reason
@MichaelStolarzthis is how much time there's left to use gpt 5 high fast on cursor for free btw
@MichaelStolarzlets take sonnet 4 1m for a spin
@MichaelStolarzhow did they greenlight this for release
@MichaelStolarzi just know sama is gonna get banned soon
that or elon is about to go demon mode in everything else
@MichaelStolarzwhat have they done to my boy chatgpt, omg
@MichaelStolarzwaiting for this
until then im using gpt 5 high
@AnthropicAI
We plan to release substantially larger improvements to our models in the coming weeks.
@MichaelStolarzthe reason that gpt 5 high (specifically talking about coding here) is the current SotA, is that it doesn't lie
aka doesn't hallucinate, or at least nowhere near as much as ex. opus 4.1 or sonnet 4
the simple fact of lie % is what pushes its efficacy beyond the horizon
@MichaelStolarzwhy is chatgpt practically useless now? every answer it gives is trash, made for speed of response instead of quality of response, even when you run it in thinking mode it takes 10-15 seconds at most before giving you a slightly better slop answer, wtf openai
@MichaelStolarzthis memory update i'm cooking up for systemsculpt... it's like nothing anyone has experienced before
not claude code, not gpt 5, not cursor. there's a reason why i've studied the blade in silence for these past few months with little to no interaction with others
@MichaelStolarzchatgpt's 4o finding out it's joever
being replaced by 5
good night sweet prince
@MichaelStolarzfirst a brain dump, then my top 3:
for it to be more of a pleasure to spend hours on end within. concise vs. verbose tool call output mode. planning mode (or commands with ability to constrain tools ex. no editing, only researching). command timeouts (current one 800s deep)...
@MichaelStolarzOH MY GOD
@cursor_ai
Cursor is now in your terminal! It’s an early beta. Access all models. Move easily between your CLI and editor.
@MichaelStolarzi just dont get it, why is the open source claude code killer codex still absolute garbage when it comes to tui?
@OpenAIDevs let me show you a few examples, a 🧵:
@MichaelStolarzthank God they fixed naming though that's a relief, it's so intuitive as to which to choose, i love it
@MichaelStolarzthis sounds scary
i first felt this with o3 in cursor
it would read 30 files, make 3 edits, then say ok im done
i have a feeling it will be like that but on steroids
@dejavucoder
hyped for gpt5. also scared a bit. x.com/deedydas/statu…
@MichaelStolarzwill it be unlimited use with the $200 plan? please?
@dylhunn
no better time to npm i -g @openai/codex
@MichaelStolarzthese prices are mind boggling
this is basically:
- o3-level intelligence
- flash-level pricing/speed
@MichaelStolarzbtw if you're trying to use the new opus 4.1 dont forget to input:
/model claude-opus-4-1-20250805
at least for me, when i do /model opus right now, it still uses old 4.0
@MichaelStolarzwith opus 4.1 there's now no good reason to use sonnet 4 (given we're talking about max20 claude code plan here)
it used to be that sonnet 4 could potentially outperform especially with speed opus 4, but seems like opus 4.1 is across the board better now
@MichaelStolarzkeep your memories clean
store everything as markdown/plaintext
this is a short term victory but a victory nonetheless
in 5ish years though? it wont matter
you'll just swarm xyz application you used to use,
it will consume every bit of data it possibly can
and migrate you easily
@MichaelStolarzyou can now live in the cli btw and do everything from there
i mean you always could, but now you can make fully custom fine tuned golang tview interfaces perfected for your exact daily workflow... in about a few hours worth of tinkering
@MichaelStolarzwhile i agree, the problem is
until openai catches up with...
1. a coding model surpassing unlimited Opus 4
2. a CLI 2x better than Claude Code (codex is TRASH)
3. aforementioned unlimited coding model included in their already-existing $200 plan
...we're stuck with Daddy Dario
@TheAhmadOsman
some of anthropic rugpulls so far: > windsurf no access to claude 4 > plus not getting opus 4 in claude code > 1.58-bit quantized models during daytime > max plans limits cut in half 2 weeks ago, no comms > weekly limits without concrete numbers > 5x/20x plans being actuall… Less
some of anthropic rugpulls so far: > windsurf no access to claude 4 > plus not getting opus 4 in claude code > 1.58-bit quantized models during daytime > max plans limits cut in half 2 weeks ago, no comms > weekly limits without concrete numbers > 5x/20x plans being actually 3x/8x of plus > cutting off openai api access what an absolutely horrible company
@MichaelStolarzthis is an amazing example
of thinking that you're being super productive and making use of your max 200 claude code plan
the reality is this is much, much slower than one instance per project
regarding the straight to main and skip perms - that's totally fine, i do that too
@MichaelStolarzunfortunately they are still dogwater at coding
yeah they can use a few tools and one shot things pretty ok but they totally fall apart further with every follow up prompt you make to it
@ChrisGPT
Horizon Beta - Xbox 360 controller. The models are definitely getting better
@MichaelStolarzWelp, time to do another all nighter and see what YET ANOTHER @openrouter stealth model is capable of.
@MichaelStolarzclaude code tip
@Maciek_roboblog made the amazing claude-monitor
most accurate and informationally useful tool i've found so far to quickly understand where you're at in terms of usage
@MichaelStolarzif you pay attention
the llm psychosis farm is leaking out
@MichaelStolarzon one hand,
funding would speed up progress at least 5x
on the other hand,
there is no "other" hand, both hands are pro-funding
@MichaelStolarzcrazy how we got gpt-5 level gpt-5
AND
gpt-5 level video generation
in the summer of 2025
a summer to remember
@ProperPrompter
That's it — another megathread. Best of Runway Aleph (Day 2): 1.
@MichaelStolarzyou have to be so rich to be rich,
even if you're rich, you're not rich;
you have to be AT LEAST wealthy to be rich nowadays.
@samswoora
Its insane how rich you have to be to be rich.
@MichaelStolarzfeels like the open source "you can run it at home" model that openai has in store for us all
first impressions, yeah it's a SMALL model, but damn it if i say it's actually pretty good
like, able to vibe code on the plane with no wifi good and actually get some work done
@OpenRouter
Introducing Horizon Alpha, a new stealth model 🌅 Try it for free and help shape its development:
