AI Educator | Helping You Make Money with AI, Tech Tools & Digital Skills📩 DM or Email for Collaborations:💬 pwpexpert.fwd@gmail.com
Joined April 2026
- Tweets3.4K
- Following43
- Followers6.6K
- Likes2.4K
AI With Ridi retweeted
If your brand runs on AI agents, track whether they get faster on the work they repeat every week. That's where improvement should show first.
🤝 Paid partnership
OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience.
On Continual-ARC, our new benchmark at @letsunifyai, none of them were able to memorize anything of value and none were able to generalize to new tasks. Training a small 9B model's weights did both.
AI With Ridi retweeted
Small teams would win big if their AI tools got cheaper with every month of work! 👏
🤝 Paid partnership
OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience.
On Continual-ARC, our new benchmark at @letsunifyai, none of them were able to memorize anything of value and none were able to generalize to new tasks. Training a small 9B model's weights did both.
AI With Ridi retweeted
💡 Buying an AI Tool That Says It "Learns"?
Ask to see it handle a similar task in week one and in week four. If nothing changed, it didn't learn.
OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience.
On Continual-ARC, our new benchmark at @letsunifyai, none of them were able to memorize anything of value and none were able to generalize to new tasks. Training a small 9B model's weights did both.
AI With Ridi retweeted
Creators, the AI tools worth paying for are the ones that learn your style instead of asking for it every single time 💯
OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience.
On Continual-ARC, our new benchmark at @letsunifyai, none of them were able to memorize anything of value and none were able to generalize to new tasks. Training a small 9B model's weights did both.
AI With Ridi retweeted
🚀 Outstanding question for anyone building agents
Does your agent actually get better at the work, or do the same thing every time?
OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience.
On Continual-ARC, our new benchmark at @letsunifyai, none of them were able to memorize anything of value and none were able to generalize to new tasks. Training a small 9B model's weights did both.
AI With Ridi retweeted
PERSONAL AI YOU WEAR AROUND YOUR NECK
the problem:
three kids, three pickup times, one group chat you never scroll back through
what it is:
Luna, AI jewelry that remembers for you
how it works:
it hears the plan when it's said out loud and reminds you when it counts. the mic goes off with a tap
when:
72 hours on Kickstarter, link in the comments
made for real parent life. I live this.
AI can now tap your shoulder
This is Luna, and it speaks up before you have to ask
Back Luna on Kickstarter now: moonshot.computer/luna
Engineers, an agent that redoes every repeat task from zero isn't saving you anything. Check whether yours gets faster the second time round.
OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience.
On Continual-ARC, our new benchmark at @letsunifyai, none of them were able to memorize anything of value and none were able to generalize to new tasks. Training a small 9B model's weights did both.
AI With Ridi retweeted
OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience.
On Continual-ARC, our new benchmark at @letsunifyai, none of them were able to memorize anything of value and none were able to generalize to new tasks. Training a small 9B model's weights did both.
AI With Ridi retweeted
You'd drop a gym buddy who forgot your routine every single week.
Weird how much we put up with from AI assistants that do exactly that.
OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience.
On Continual-ARC, our new benchmark at @letsunifyai, none of them were able to memorize anything of value and none were able to generalize to new tasks. Training a small 9B model's weights did both.
AI With Ridi retweeted
Big day for us at @pluraiAI ! Plurai Simulation is live and free for every AI engineer.
AI agents look great in demos. Until real users break them.
So we built a world where your agent can fail, learn, and get fixed before your users ever see it.
→ Digital twin: Your real agent, its tools, and environment recreated from your code
→ Simulated users & tasks: Realistic users, tasks, and workflows that push your agent into the edge cases that matter
→ Auto evals: Check what your agent actually did, not just what it said
→ Verified fixes: Every failure comes with the run that exposed it and a fix you can verify
→ Replays: Turn any production failure into a simulation and replay it against every new version of your agent
All inside the coding agent you already use: @claudeai code, @OpenAICodexCli , or @GitHubCopilot .
Start simulating for free: simulation.plurai.ai/connect
AI With Ridi retweeted
I'd never wear an AI necklace with a mic that's always on.
Luna's can be switched off with a single tap.
When it's on, its proactivity comes from you just living your life.
that's the only version I'd try.
AI can now tap your shoulder
This is Luna, and it speaks up before you have to ask
Back Luna on Kickstarter now: moonshot.computer/luna
AI With Ridi retweeted
luna just dropped.
an AI necklace that remembers what the teacher said at pickup, and reminds you before you forget.
as a person with ADHD I need this.
AI can now tap your shoulder
This is Luna, and it speaks up before you have to ask
Back Luna on Kickstarter now: moonshot.computer/luna
AI With Ridi retweeted
Every AI wearable this year: looks like it came out of a lab.
Luna looks like jewelry. Inside it's a personal AI that remembers for you and speaks up first.
YC. Kickstarter. Live now.
I've owned the lab ones. they never left the drawer. I'd keep this on.
AI can now tap your shoulder
This is Luna, and it speaks up before you have to ask
Back Luna on Kickstarter now: moonshot.computer/luna