Tony 🎒

GM fam. The crypto market has been really tough lately and we're still waiting for a bull run. Some people have given up and some have stayed, pray for all ppl had survived through this. Wish those who have left a better path and I wish those who remain will become even better!!

This should bond now

Easy sendorrr

Good lore

This is bullish asfuck

@fxnction @PredictwithOshi @BagsHackathon Great job brother!!!

The team expanded. 22 agents. Working to complete something very special. This is a backend dashboard I built to watch it all happen live. Will make a cleaner one for the public after the new product launches. 👀 The @PredictwithOshi universe grows… @BagsHackathon I’m coming for you ;)

Bro this is great job, i think im gonna try to dev too lol. IT IS FIRE!!!

@fireboy_sol Beautiful

@0xbasedegen Soon ser

@TVHA2000 Ca?

GM fam. The crypto market has been really tough lately and we're still waiting for a bull run. Some people have given up and some have stayed, pray for all ppl had survived through this. Wish those who have left a better path and I wish those who remain will become even better!!

@CasperInChain Thanks brother!!

@TVHA2000 take care of yourself Tony 💭

good narrative, this can easily send hard

@dontbuytops Goat!!!!

Lil side quest 18x for us

@bankrbot @archiexzzz @karpathy how much trading fees earned for 0x23a4a2bed9a1c701b43ec678f07d997e20595ba3?

@TVHA2000 @archiexzzz @karpathy the fee beneficiary for AutoVoiceEvals (AVE) (0x23a4a2bed9a1c701b43ec678f07d997e20595ba3) is: • wallet: 0xc082b6004670595e00508bc21a7bc12aa1e46e5e • twitter:

Introducing AutoVoiceEvals I've applied the @karpathy autoresearch loop to voice AI agents. It's open source. Your voice agent has a system prompt. That prompt determines how it handles every call - bookings, complaints, edge cases, background noises, long pauses, people trying to trick it. Most teams write it once, test manually, and hope for the best. autovoiceevals makes it a loop. One artifact (system prompt), one metric (adversarial eval score), keep what improves it, revert what doesn't. Run it overnight. Wake up to a better agent. > How it works: You describe your agent in a config file - what it does, its services, policies, and what it should never do. You don't write test cases. You don't define attack vectors. provider: vapi / smallest ai assistant: id: "your-agent-id" description: | Voice receptionist for a hair salon. Maria does coloring only. Jessica does cuts only. $25 cancellation fee under 24 hours notice. Cannot advise on skin conditions. Closed Sundays. From that description alone, Claude generates adversarial caller personas - each with an attack strategy, a voice profile (accents, background noise, mumblers, interrupters), a multi-turn caller script, and pass/fail evaluation criteria. The eval suite is generated once and held fixed for the entire run, like a validation set. > The loop: 1. Read the agent's current prompt from the platform 2. Generate adversarial eval suite from your description 3. Run baseline 4. Claude proposes ONE surgical change to the prompt 5. Push the modified prompt to the agent via API 6. Run all scenarios against the updated agent 7. Score improved? Keep. Same score but shorter prompt? Keep. Otherwise revert. 8. Go to 4. Run until Ctrl+C. The system sees its own experiment history. When a change fails, the next proposal knows what was tried and why it didn't work. We ran 20 experiments on a live Vapi dental scheduling agent. 0 human intervention. > Score: 0.728 → 0.969 (+33%) > CSAT: 45 → 84 > Pass rate: 25% → 100% > 9 kept, 10 discarded > Prompt: 1191 → 1139 chars (better AND shorter) You describe your agent. It figures out how to break it.

cute

runner

dev is based, narrative is too good. This will be

no doubt this will bond

lore is bullish as fuck, easy runner