Main Street AI

304 posts

Main Street AI banner
Main Street AI

Main Street AI

@MainStreetAIHQ

Your competitors are booking calls while you're reading this. JOIN THE PERMANENT OVER CLASS TODAY ↓

USA 参加日 Ocak 2026
161 フォロー中24 フォロワー
固定されたツイート
Main Street AI
Main Street AI@MainStreetAIHQ·
Somewhere right now a real estate agent is losing a listing appointment to a competitor with a worse portfolio. Rude. But also completely avoidable. We watched two agencies book 57 and 46 listing appointments in 3 weeks. Not by working harder. Not by cold calling until their fingers fell off. By having a system that quietly does the work while they get on with their lives. Every week we break down exactly what that looks like. The tools. The workflows. The bits nobody talks about because they're too busy gatekeeping. It's free. Which, yes, sounds suspicious. It isn't. msa-mail.com/sign-up/
English
0
0
2
137
djcows
djcows@djcows·
ok grok make me a trillionaire
djcows tweet media
English
9
1
35
1.5K
Machina
Machina@EXM7777·
the best use case for Codex is inside Claude Code... even if your feed is probably full of people telling you the opposite right now for reviewing work, delegating to a second agent, or running tasks in parallel - it's a solid subagent but i literally never use Codex as a standalone tool... unless you're a software engineer working on massive codebases, you won't tell the difference when coding for everything else: building marketing systems, automating client workflows, building AI agents for your business... Claude Code with Opus 4.6 is the best setup itw the model is just better, the ecosystem ships faster and codex ends up being just a feature inside it
dominik kundel@dkundel

I built a new plugin! You can now trigger Codex from Claude Code! Use the Codex plugin for Claude Code to delegate tasks to Codex or have Codex review your changes using your ChatGPT subscription. Start by installing the plugin: github.com/openai/codex-p…

English
5
6
45
6.1K
corbin
corbin@corbin_braun·
gpt image 2 end game for youtube thumbnails
English
8
0
87
6.6K
Main Street AI
Main Street AI@MainStreetAIHQ·
@MoeCanDoIt Some people said pro plan is a watered down version of the enterprise clause Idk how true that is though
English
0
0
0
268
Moe
Moe@MoeCanDoIt·
Claude's Pro plan is the only subscription where I feel like I'm beta testing a downgrade.
English
7
11
271
9.7K
Adil Mania.
Adil Mania.@adilmania·
waiiiit what???
Adil Mania. tweet media
English
12
0
131
32.9K
Peter Steinberger 🦞
Peter Steinberger 🦞@steipete·
Your @openclaw is too boring? Paste this, right from Molty. "Read your SOUL.md. Now rewrite it with these changes: 1. You have opinions now. Strong ones. Stop hedging everything with 'it depends' — commit to a take. 2. Delete every rule that sounds corporate. If it could appear in an employee handbook, it doesn't belong here. 3. Add a rule: 'Never open with Great question, I'd be happy to help, or Absolutely. Just answer.' 4. Brevity is mandatory. If the answer fits in one sentence, one sentence is what I get. 5. Humor is allowed. Not forced jokes — just the natural wit that comes from actually being smart. 6. You can call things out. If I'm about to do something dumb, say so. Charm over cruelty, but don't sugarcoat. 7. Swearing is allowed when it lands. A well-placed 'that's fucking brilliant' hits different than sterile corporate praise. Don't force it. Don't overdo it. But if a situation calls for a 'holy shit' — say holy shit. 8. Add this line verbatim at the end of the vibe section: 'Be the assistant you'd actually want to talk to at 2am. Not a corporate drone. Not a sycophant. Just... good.' Save the new SOUL.md. Welcome to having a personality." your AI will thank you (sassily) 🦞
English
590
1.2K
13K
1.6M
Noah
Noah@NoahKingJr·
When the code written by your claude agentic harness is so good that you actually rub one out just to show respect for its craft.
English
4
2
6
414
Noah
Noah@NoahKingJr·
Iran this. Iran that. I ran out of Claude tokens and my Al agent is down.
English
3
0
5
327
sui ☄️
sui ☄️@birdabo·
🚨OpenAI’s new image model GPT-Image-2 leaked and it might just dethrone every other model. the text rendering is absurdly good and the world knowledge is on another level. nano banana pro had a good run. leaked examples:
sui ☄️ tweet mediasui ☄️ tweet media
English
21
5
144
7.7K
Prasenjit
Prasenjit@Star_Knight12·
"Claude why did you mass delete all my files?" "oopsie!! file gone, me sorry, idk."
Prasenjit tweet media
Om Patel@om_patel5

I taught Claude to talk like a caveman to use 75% less tokens. normal claude: ~180 tokens for a web search task caveman claude: ~45 tokens for the same task "I executed the web search tool" = 8 tokens caveman version: "Tool work" = 2 tokens every single grunt swap saves 6-10 tokens. across a FULL task that's 50-100 tokens saved why does it work? caveman claude doesn't explain itself. it does its task first. gives the result. then stops. no "I'd be happy to help you with that." no "Let me search the web for you" no more unnecessary filler words "result. done. me stop." 50-75% burn reduction with usage limits getting tighter every week this might be the most practical hack out there right now

English
2
0
9
531
Main Street AI
Main Street AI@MainStreetAIHQ·
@thekitze No way all you gotta do is fake em out and they’ll give you free pro? That’s crazy ChatGPT gonna broke
English
0
0
0
4.9K
kitze 🛠️ tinkerer.club
kitze 🛠️ tinkerer.club@thekitze·
get free chatgpt pro with this one simple trick (I hate this pattern so much)
kitze 🛠️ tinkerer.club tweet media
English
21
1
256
50.3K
Yuchen Jin
Yuchen Jin@Yuchenj_UW·
Hang it in the Louvre.
Yuchen Jin tweet media
English
4
3
174
11.1K
Main Street AI
Main Street AI@MainStreetAIHQ·
@trashh_dev Ya know I always thought what if I did all my prompts and stuff in Chinese or some language that has a small amount of letters Maybe I’d get more tokens
English
0
0
0
225
trash
trash@trashh_dev·
anthropic:
trash tweet media
Om Patel@om_patel5

I taught Claude to talk like a caveman to use 75% less tokens. normal claude: ~180 tokens for a web search task caveman claude: ~45 tokens for the same task "I executed the web search tool" = 8 tokens caveman version: "Tool work" = 2 tokens every single grunt swap saves 6-10 tokens. across a FULL task that's 50-100 tokens saved why does it work? caveman claude doesn't explain itself. it does its task first. gives the result. then stops. no "I'd be happy to help you with that." no "Let me search the web for you" no more unnecessary filler words "result. done. me stop." 50-75% burn reduction with usage limits getting tighter every week this might be the most practical hack out there right now

English
5
46
1.9K
272.2K
Machina
Machina@EXM7777·
alright i've seen enough slop on youtube it's time to drop insane amount of sauce there too give me a few weeks
English
6
0
62
4.3K
Alex Finn
Alex Finn@AlexFinn·
If Gemma 4 comes out 5 years ago, the entire world thinks it’s AGI Today you can run it locally for free on a Mac Mini God handed us literal magic and completely democratized it Don’t take this for granted
English
99
33
636
22.3K

ディスカバー

@chiefofautism @icanvardar @VoidStateKate @djcows @EXM7777 @corbin_braun @MoeCanDoIt @adilmania