Tim Neunzig
2.2K posts
Tim Neunzig
@tim_neunzig
SaaS Killer & Dadpreneur Vibecoder for SMBs and Cities 🕉️⚛️🦓🌻💚
Werder (Havel), Germany Katılım Temmuz 2009
1.1K Takip Edilen439 Takipçiler
Anthropic just banned Claude subscriptions from powering OpenClaw.
Here's why my stack was already built for this.
I never ran Opus 4.6 through a subscription for OpenClaw or Hermes. It runs in Claude Code for complex external dev only. Same with GPT-5.4 in Codex.
The internal agent runtime is a completely different stack:
1. Qwen3.5 9B runs locally. $0. Always on. Feeds the subconscious ideation loop 24/7. Beats GPT-OSS-120B by 13x. Awesome.
2. MiniMax M2.7 is the agent's backbone. 97% skill adherence, built for agents, $0.30/M tokens. The $10 plan allows for 1500 calls every 5 hours. Amazing.
3. GPT-5.4 mini is the Hermes brain. debates ideas with the subconscious, builds output, ~$0.075 avg per run. It's smart enough to orchestrate your entire system, and you can actually use your subscription plan here via OAuth. Incredible!
Over the last 24 hours, the subconscious ran 15 times, for a total of $1.58. Not too shabby for an always-improving agentic system.
The lesson is to build your agent stack on a multiple LLM stack.
Local models handle volume. Generous subscription models handle execution and judgment. You own the cost structure.
Full-stack breakdown in the table. (see image)
Graeme@gkisokay
English
Tim Neunzig retweetledi
@fxnction models auth login --provider anthropic --method cli --set-default
English
Starting tomorrow at 12pm PT, Claude subscriptions will no longer cover usage on third-party tools like OpenClaw.
You can still use these tools with your Claude login via extra usage bundles (now available at a discount), or with a Claude API key.
English
@lennysan this must be the reason why I feel so wiped after 11am
English
"Using coding agents well is taking every inch of my 25 years of experience as a software engineer, and it is mentally exhausting.
I can fire up four agents in parallel and have them work on four different problems, and by 11am I am wiped out for the day.
There is a limit on human cognition. Even if you're not reviewing everything they're doing, how much you can hold in your head at one time. There's a sort of personal skill that we have to learn, which is finding our new limits. What is a responsible way for us to not burn out, and for us to use the time that we have?" @simonw
Lenny Rachitsky@lennysan
"Using coding agents well is taking every inch of my 25 years of experience as a software engineer." Simon Willison (@simonw) is one of the most prolific independent software engineers and most trusted voices on how AI is changing the craft of building software. He co-created Django, coined the term "prompt injection," and popularized the terms "agentic engineering" and "AI slop." In our in-depth conversation, we discuss: 🔸 Why November 2025 was an inflection point 🔸 The "dark factory" pattern 🔸 Why mid-career engineers (not juniors) are the most at risk right now 🔸 Three agentic engineering patterns he uses daily: red/green TDD, thin templates, hoarding 🔸 Why he writes 95% of his code from his phone while walking the dog 🔸 Why he thinks we're headed for an AI Challenger disaster 🔸 How a pelican riding a bicycle became the unofficial benchmark for AI model quality Listen now 👇 youtu.be/wc8FBhQtdsA
English
@amasad @galligator Give the market what they want and they will reward you
English
Cyprus 🇨🇾 -> Berlin 🇩🇪
Your luggage goes 3x with a baby LMAO
English
Day 27, Building GovTech in Public.
Holy shit. @ideabrowser just featured basically the same category I am building with VergabeMeister.de
Good.
That means the problem is real and the market is forming.
Now I just need to execute faster and own the German procurement niche.
English
anyone feel themselves using openclaw a bit less lately?
personally I feel like it’s memory is not great and it’s tool use even with skills is not close to claude code
I like it for quick on the go things but it’s not a workhorse for me by any means at this point
English
Build and kill that SaaS!
Michele Catasta@pirroh
The Buy vs Build dilemma is no more. Always start by building.
English
Tim Neunzig retweetledi
The Buy vs Build dilemma is no more.
Always start by building.
etn.@etnshow
President of @Replit Michele Catasta (@pirroh) explains why the decreasing cost of building tools has lead to several key shifts across start-ups: "Before you had to make the choice of shelling out tens of thousands of dollars, spending several months creating the first version of an internal tool - you'd rather go out and buy a SaaS". "The cost of creating it and putting in front of your employees and finding out if it helps or not has become extremely low." "So now that order has completely flipped and I think this trend can't really be stopped". "We're just at the beginning, these are the early innings of the game".
English
@itsumeshk It's not that hard to run an openclaws bot. Just did it with a class of 7th graders yesterday
English
We're launching RunClaw to kill OpenClaw.
OpenClaw costs $700 to set up.
RunClaw costs $1 no setup.
> OpenClaw can’t build you a website
> Can’t generate a video
> Can’t make a slide deck
> Has 9 security CVEs
RunClaw does all of it.
Better agents. More secure. Always in your DMs.
Try it now for $1.
English
looking for a handful of people to test something new...
i've been using it for a few months and am prepping to share.
if you're a fan of claude cowork, openclaw, manus, perplexity computer, etc then you're a perfect fit.
this will self destruct in 4hrs - please dm or reply.
Mckay Wrigley@mckaywrigley
you’re like 6 prompts away from infinitely customizable personal agi. anthropic gave you a world class agentic harness for free. use it!!!
English
You guys all run Claude Code with claude --dangerously-skip-permissions right?
Because otherwise how in the world can you sit there accepting every single permission when building something?
English
It is finally here! Agent 4
Amjad Masad@amasad
Software isn’t merely technical work anymore. It’s creative. Introducing Replit Agent 4. The first AI built for creative collaboration between humans and agents. Design on an infinite canvas, work with your team, run parallel agents, and ship working apps, sites, slides & more.
English
Software isn’t merely technical work anymore. It’s creative.
Introducing Replit Agent 4. The first AI built for creative collaboration between humans and agents.
Design on an infinite canvas, work with your team, run parallel agents, and ship working apps, sites, slides & more.
English
@paulg @noampomsky Germans unfortunately still smoke twice as much and it's uncomfortablly noticeabke tust even educated people smoke.
Boggles my mind..
English
@nicbstme So much nicer XP imo especially for non primary tasks
English
Why do I need openclaw? Am I missing out?
I run Claude Code from my phone with /remote-control. It has access to my filesystem, professional and personal Drive and emails with GogCLI, my sms etc.
It seems like 80% of the value prop without the security headache and token cost.
English
Vergabemeister, [3/6/26 10:52 PM]
Here’s a punchy X post:
€75M for “AI consulting” at a majority publicly-owned utility.
In 2026.
After years of “AI will boost efficiency.”
If AI is real, why are consulting budgets scaling like it’s 2009?
Build internal capability. Demand measurable outcomes. Stop funding slideware at industrial scale.
Tender: oeffentlichevergabe.de/ui/de/search/d…
Vergabemeister, [3/6/26 10:52 PM]
Award: oeffentlichevergabe.de/ui/de/search/d…
#AI #Procurement #PublicMoney #Consulting #GovTech
English