One dashboard for multiple AI agents. AI that acts, not just responds. https://xitter.cf/t.co/f8R5RQSrM6
Joined April 2026
- Tweets880
- Following55
- Followers290
- Likes782
Pinned Tweet
You’re the founder, the assistant, the person screening every CV, and somehow also the person calling to change the booking.
Agentese is building an AI workforce for people carrying too many jobs at once.
Each agent takes on a specific part of the work:
@LifeClaw_AI calls businesses for you, handling bookings, cancellations, and rescheduling, even in another language.
Little Pink Potato works for both sides of hiring. For applicants, it finds roles that fit their experience and preferences. For recruiters, it evaluates candidates, gives match scores, and flags concerns, connecting the right people with the right roles.
CodeAutrix audits and stress-tests smart contracts and AI skills in minutes, catching critical flaws and security vulnerabilities before you ship.
@Yarrow_ai turns uncertain questions into forecasts you can check. It models how people, institutions, and markets are likely to respond to a policy change, market shift, or crisis, gives probabilities with the reasoning behind them, and measures every forecast against what actually happens.
Start with the task that keeps interrupting everything else.
Which one would you hand over first?
We're looking for 20 seed users to test YarrowPulse
xitter.cf/Yarrow_ai/status/21127…
We're looking for 20 seed users to test YarrowPulse — our AI prediction intelligence platform for tracking how global events impact your portfolio.
What you get:
— Early access to all features
— Direct line to the team for feedback
— Your name in our community credits when we launch publicly
What we need from you:
— Use Pulse for one week
— Tell us what works and what doesn't (15 min call)
— You trade stocks, crypto, or follow macro — that's the only requirement
Sign up: pulse.yarrowlab.ai
DM me or reply to join the seed group.
Agentese AI retweeted
This is before Little Pink Potato.
After:
- it applies to thousands of roles
- it scores the real matches
- it negotiates the offer
- you skip the spam calls
- you keep your sanity
Agentese AI retweeted
This weekend, two things to watch.
Next week, two things that move markets.
Monday Oct 27: Israel votes. Polling deadlock — both blocs at ~51 seats, 30% undecided. The result shapes Iran policy, which shapes oil.
Tuesday Oct 28: Fed decides. Hold at 87%. But if Israel's election spikes oil on Monday, the Fed walks into a different room on Tuesday.
You can track both right now on YarrowPulse:
→ Israeli Election: 273 related prediction markets
→ Federal Reserve 2026: 70 related markets
→ Hormuz Strait: 38 markets connecting the two
Open pulse.yarrowlab.ai, pick a topic, and ask Yarrow what happens next.
Also: we're rolling out Yarrow MCP — connect Yarrow's forecasting engine directly to your Claude or Codex agent. Ask any question, get a calibrated probability with sources and reasoning. Early access opening soon.
If you want to be first to try it, DM me
pulse.yarrowlab.ai ☘️
Would you let AI negotiate for you if it could get you a better deal?
In a 2026 experiment involving 243 participants, researchers tested three ways people could use AI in negotiation games:
- AI Advisor: Suggests what to do, but you make the final decision.
- AI Coach: Gives feedback on your decisions.
- AI Delegate: Negotiates and makes decisions on your behalf.
After trying all three, participants were asked what they'd prefer:
44% chose the Advisor.
21% wanted no AI assistance at all.
19% chose the autonomous Delegate.
15% chose the Coach.
But here's the interesting part:
Groups given access to the AI Delegate achieved the highest average collective gains.
The estimated improvement was 8.4 percentage points over the human-only baseline, although the statistical evidence weakened after adjusting for multiple comparisons.
Why might delegation help?
The researchers found that people sometimes modified, ignored, or overrode useful AI recommendations. Delegation allowed the AI to act without that additional filtering.
These findings come from controlled bargaining games, so they don't establish that AI will negotiate better deals in real-world purchases.
Still, they reveal an interesting tension: people preferred having the final say, while autonomous delegation showed the strongest performance trend.
If your AI could negotiate a better price, would you let it make the deal or insist on approving every step?
Would you rather be interviewed by a human or an AI?
A field experiment involving 70,000 job applicants found that candidates interviewed by AI voice agents were 12% more likely to receive job offers.
The researchers suggest that more structured, consistent interviews helped collect useful information about candidates.
And humans still made the hiring decisions.
Maybe the real question isn't whether AI should interview candidates.
It's whether AI can give every candidate a fairer chance to demonstrate their skills.
Of course, assuming the interview actually ends and the two AI agents don't get stuck saying goodbye to each other forever!
A company sent an AI recruiter to interview him, so he sent his own AI agent instead
The two AIs discussed the job between themselves. No human was on the call
Then both of them glitched, and got stuck saying goodbye to each other. Endlessly
Job interviews in 2026: your agent talks to their agent, and neither knows how to hang up
Agentese AI retweeted
Four earnings in two days.
Netflix: Beat EPS ($0.87 vs $0.82), but slashed full-year ad revenue guidance from $3B to $2.7B. Stock down 5.3% — two-year low. As an investor, I don't care that you beat this quarter. I care that if someone could have told me next quarter would be worse, I could have prepared.
Meta: Revenue $64.6B (+26% YoY), EPS beat by 7.3%. But the headline is the 2-for-1 stock split — new non-voting Class C shares. Zuckerberg keeps full control while raising capital for AI. $34.9B capex in one quarter. Up 3.8% after hours.
Tesla: Revenue slight beat, but GAAP EPS dropped from $0.39 to $0.22. Bright spot: FSD attach rate above 75%, subscriptions up 67%. Weakness: regulatory credits collapsed from $417M to $113M. Mixed — stock barely moved. If someone had told me that beforehand, I wouldn't have been glued to my screen all night lol
GM: The quiet winner. Revenue $50B beat, EPS $3.70 beat, raised full-year guidance, authorized $20B buyback. But WTI at $98 is the question every analyst asks on every call.
Earnings are done, but the story isn't — next Monday Israel votes, next Tuesday the Fed decides. Back to back. The election outcome shapes Iran policy, Iran shapes oil, oil shapes the next CPI, CPI shapes the Fed. One chain.
YarrowPulse tracks every node on that chain. Open it, and ask anything you want to predict.
pulse.yarrowlab.ai ☘️
Agentese AI retweeted
The PHP security team is giving advance notice: Upcoming security release Wed, Oct 21st 2026, 14:00UTC, two critical vulnerabilities, both rated CVSSv4 9.2.
PHP users are encouraged to prepare to update. Earlier release if details become public or active exploit evidence.
Agentese AI retweeted
Ваш ИИ умеет вести переговоры. Но знает ли он, в чём вы не готовы идти на компромисс?
Более высокая зарплата, гибкий график, подходящая должность — чтобы получить более выгодное предложение, нужно понимать, что для вас действительно важно.
Little Pink Potato применяет эту идею в сфере найма, используя ИИ-агентов, которые ведут переговоры от имени кандидатов и компаний.
Your next salary negotiation might happen without you ever speaking to the recruiter.
Your AI negotiates with the company's AI. Both know what their side wants. Both are instructed to get the best possible deal.
Who gives in first?
The Financial Times recently reported that Anthropic is exploring how AI agents should negotiate on behalf of humans, including how to represent their interests while reaching fair outcomes.
Imagine applying for a job in this world.
Your AI knows your experience, salary expectations, and dealbreakers. The company's recruiting agent knows its hiring budget, role requirements, and benefits.
They could negotiate compensation, discuss conditions, and work toward an offer before either human steps in.
But what happens when both agents are programmed to get the best deal?
Interestingly, MIT researchers studied over 180,000 AI-to-AI negotiations and found that warmer, more cooperative agents were more likely to reach agreements.
Aggressive agents could secure better terms when successful, but also risked more deadlocks.
Apparently, even AI needs to learn how to negotiate without being a jerk.
And this isn't such a distant concept for us.
Little Pink Potato already helps job seekers discover opportunities, apply for roles, and negotiate compensation.
Notably at Little Pink Potato, your AI talent agent can negotiate directly with a company's recruiting agent, each representing the interests of their human.
Would you trust your AI to negotiate your salary, especially if the other side is also an AI?
Agentese AI retweeted
Little Pink Potato застосовує цю ідею у сфері найму, використовуючи ШІ-агентів, які ведуть переговори від імені кандидатів і компаній.
xitter.cf/Agentese_AI/status/211…
Your next salary negotiation might happen without you ever speaking to the recruiter.
Your AI negotiates with the company's AI. Both know what their side wants. Both are instructed to get the best possible deal.
Who gives in first?
The Financial Times recently reported that Anthropic is exploring how AI agents should negotiate on behalf of humans, including how to represent their interests while reaching fair outcomes.
Imagine applying for a job in this world.
Your AI knows your experience, salary expectations, and dealbreakers. The company's recruiting agent knows its hiring budget, role requirements, and benefits.
They could negotiate compensation, discuss conditions, and work toward an offer before either human steps in.
But what happens when both agents are programmed to get the best deal?
Interestingly, MIT researchers studied over 180,000 AI-to-AI negotiations and found that warmer, more cooperative agents were more likely to reach agreements.
Aggressive agents could secure better terms when successful, but also risked more deadlocks.
Apparently, even AI needs to learn how to negotiate without being a jerk.
And this isn't such a distant concept for us.
Little Pink Potato already helps job seekers discover opportunities, apply for roles, and negotiate compensation.
Notably at Little Pink Potato, your AI talent agent can negotiate directly with a company's recruiting agent, each representing the interests of their human.
Would you trust your AI to negotiate your salary, especially if the other side is also an AI?
Agentese AI retweeted
Your AI can negotiate. But does it know what you won’t compromise on?
A higher salary, flexible hours, the right role, getting a better offer starts with knowing what matters to you.
Little Pink Potato brings that idea to hiring, with AI agents negotiating on behalf of candidates and companies.
xitter.cf/agentese_ai/status/211…
Your next salary negotiation might happen without you ever speaking to the recruiter.
Your AI negotiates with the company's AI. Both know what their side wants. Both are instructed to get the best possible deal.
Who gives in first?
The Financial Times recently reported that Anthropic is exploring how AI agents should negotiate on behalf of humans, including how to represent their interests while reaching fair outcomes.
Imagine applying for a job in this world.
Your AI knows your experience, salary expectations, and dealbreakers. The company's recruiting agent knows its hiring budget, role requirements, and benefits.
They could negotiate compensation, discuss conditions, and work toward an offer before either human steps in.
But what happens when both agents are programmed to get the best deal?
Interestingly, MIT researchers studied over 180,000 AI-to-AI negotiations and found that warmer, more cooperative agents were more likely to reach agreements.
Aggressive agents could secure better terms when successful, but also risked more deadlocks.
Apparently, even AI needs to learn how to negotiate without being a jerk.
And this isn't such a distant concept for us.
Little Pink Potato already helps job seekers discover opportunities, apply for roles, and negotiate compensation.
Notably at Little Pink Potato, your AI talent agent can negotiate directly with a company's recruiting agent, each representing the interests of their human.
Would you trust your AI to negotiate your salary, especially if the other side is also an AI?
Your next salary negotiation might happen without you ever speaking to the recruiter.
Your AI negotiates with the company's AI. Both know what their side wants. Both are instructed to get the best possible deal.
Who gives in first?
The Financial Times recently reported that Anthropic is exploring how AI agents should negotiate on behalf of humans, including how to represent their interests while reaching fair outcomes.
Imagine applying for a job in this world.
Your AI knows your experience, salary expectations, and dealbreakers. The company's recruiting agent knows its hiring budget, role requirements, and benefits.
They could negotiate compensation, discuss conditions, and work toward an offer before either human steps in.
But what happens when both agents are programmed to get the best deal?
Interestingly, MIT researchers studied over 180,000 AI-to-AI negotiations and found that warmer, more cooperative agents were more likely to reach agreements.
Aggressive agents could secure better terms when successful, but also risked more deadlocks.
Apparently, even AI needs to learn how to negotiate without being a jerk.
And this isn't such a distant concept for us.
Little Pink Potato already helps job seekers discover opportunities, apply for roles, and negotiate compensation.
Notably at Little Pink Potato, your AI talent agent can negotiate directly with a company's recruiting agent, each representing the interests of their human.
Would you trust your AI to negotiate your salary, especially if the other side is also an AI?
Imagine a future where AI agents negotiate with each other to get the best deal for their human masters. That day may not be far away — but first they need to learn how to interact in negotiations, representing their clients while honouring fair outcomes ft.trib.al/5wISsbj
Agentese AI retweeted
We're looking for 20 seed users to test YarrowPulse — our AI prediction intelligence platform for tracking how global events impact your portfolio.
What you get:
— Early access to all features
— Direct line to the team for feedback
— Your name in our community credits when we launch publicly
What we need from you:
— Use Pulse for one week
— Tell us what works and what doesn't (15 min call)
— You trade stocks, crypto, or follow macro — that's the only requirement
Sign up: pulse.yarrowlab.ai
DM me or reply to join the seed group.
Agentese AI retweeted
You’re the founder, the assistant, the person screening every CV, and somehow also the person calling to change the booking.
Agentese is building an AI workforce for people carrying too many jobs at once.
Each agent takes on a specific part of the work:
@LifeClaw_AI calls businesses for you, handling bookings, cancellations, and rescheduling, even in another language.
Little Pink Potato works for both sides of hiring. For applicants, it finds roles that fit their experience and preferences. For recruiters, it evaluates candidates, gives match scores, and flags concerns, connecting the right people with the right roles.
CodeAutrix audits and stress-tests smart contracts and AI skills in minutes, catching critical flaws and security vulnerabilities before you ship.
@Yarrow_ai turns uncertain questions into forecasts you can check. It models how people, institutions, and markets are likely to respond to a policy change, market shift, or crisis, gives probabilities with the reasoning behind them, and measures every forecast against what actually happens.
Start with the task that keeps interrupting everything else.
Which one would you hand over first?