
50% girl 50% AI ex @adidas, @BBDOWorldwide, @cointelegraph
follow on insta ππ»
Joined June 2022
- Tweets30.3K
- Following1.5K
- Followers11.8K
- Likes66.5K
girl.ai π
π» retweeted
1. Oh shit, AI can do my job better than me
2. Software engineering is dead!
3. I can vibe code as much slop as I want!
4. Oh, things are not going well. Fable/Sol/Opus all suuuck
5. But what if I constrain the agent? Put it in a straitjacket?
6. Oh, the results are pretty good now. How do I go deeper?
7. *Orders 12 software engineering books from Amazon*
8. Software engineering is alive!
We are living in the greatest 30 day time period in technology history
In the last month all of these have been released/are expected to be released:
β’ Opus 5.5: greatest AI model ever
β’ Meta Muse: The AI agent that will get a billion new people into AI agents
β’ ChatGPT 6 Astra: First model that could be considered AGI
β’ Grok 4.7: affordable version of Opus + Elonβs back
β’ GPT 6.1 sol: Basically free intelligence
β’ Sonnet 5.5 Dirt cheap intelligence you basically can't tell apart from Opus
β’ ChatGPT Dot: Incredibly powerful AI agent that's capable of building out large scale applications
The way you work 30 days from now will be dramatically different than the way you work today
You will be significantly more productive with significantly less effort required
Thank your God he/she decided you should be alive right now
girl.ai π
π» retweeted
JEV is INSANE.
We gave it 700 high-intent leads and personalised outreach messages.
In 40 seconds, it predicted how each message would perform, assigned a confidence score and detected lead-message mismatches.
All for just $0.09.
JEV can also score leads, analyse buying signals, match each prospect with the best message and identify the campaigns most likely to perform based on data.
Coming soon to @GojiberryAI+ MCP.
Comment βJEVβ for early access.
girl.ai π
π» retweeted
Astra is unusable
i've tried Astra on medium effort for the past 4 weeks and it's been terrible.
i run through 100% usage in 5 hours
switched over to GPT 5.6 Sol high effort
OpenAI needs to launch GPT 6 Sol asap.
Hermes Wingtips #75: `reasoning_effort` for side tasks
besides your chat, Hermes Agent makes small model calls of its own: the summary written when a long conversation is compacted, the name it gives a session, reading an image you paste, the check on whether a command needs your approval.
those calls run on your main model unless you gave them another one, at the provider's default thinking level.
but a session title does not need deep thinking.
each side task has its own `reasoning_effort`. set it to `low` or `none` for that task and the call comes back sooner and costs less, while your chat keeps the level you set for it.
girl.ai π
π» retweeted
to replicate any competitor's GEO strategy, do this:
1/ open the Ryze AI Chrome extension
2/ check the pages that got them cited in ChatGPT
3/ spot the sites that made ChatGPT trust them
4/ list the questions where ChatGPT names them, not you
5/ steal the page layout ChatGPT remembers
6/ ask Ryze AI to recreate it for your brand
that's it
literally so easy, your next $1M ARR is sitting in ChatGPT
In case local AI models are banned, it's critical you start experimenting with them now
Luckily Hermes just released an awesome feature that makes it easy for ANYONE to get started, no matter what computer you have
It will literally determine which model is best for you, then load it and run it. No technical work required at all
Just go into the Hermes desktop app then go to settings, providers, then local models.
From there is will recommend which model you should be running on your computer. Even if you're running a dirt cheap Mac Mini
You click 'set up for me' and it handles EVERYTHING for you
In no time you'll have literal unlimited intelligence running locally on your computer
No excuses. Do this ASAP
your Hermes Agent can brief itself on your project before every session. this prompt writes the file that does it.
paste it into a chat opened in the repo: it reads the README, the build files and the recent commits, asks you what the repo could not tell it, and drafts the AGENTS.md that Hermes loads at the start of every session in that folder.
copy / paste prompt in the first comment.
girl.ai π
π» retweeted
if you guys are wondering why I'm silent here well because it's more fun on insta

















