Elix (@ElixFusion) header
Elix (@ElixFusion) profile picture

Feeling weird.

Joined June 2024
Photo by Elix (@ElixFusion)Photo by Elix (@ElixFusion)Photo by Elix (@ElixFusion)Photo by Elix (@ElixFusion)Photo by Elix (@ElixFusion)Photo by Elix (@ElixFusion)Photo by Elix (@ElixFusion)Photo by Elix (@ElixFusion)Photo by Elix (@ElixFusion)Photo by Elix (@ElixFusion)
not sure how well it works yet but the idea makes a lot of sense
Introducing Aurora - the Search Engine for IRL Have you ever had to go shop-to-shop, or ask your friends and family, or spent hours browsing online for weeks, to find out - which business has what you want? Could be anything from a renting an Apartment, to a Doctor's appointment? Maybe just your favorite shoe in your size at a store nearby? Now - you can just Ask @aurorax_ai , and it will tell you who has it!
109
Introducing Aurora - the Search Engine for IRL Have you ever had to go shop-to-shop, or ask your friends and family, or spent hours browsing online for weeks, to find out - which business has what you want? Could be anything from a renting an Apartment, to a Doctor's appointment? Maybe just your favorite shoe in your size at a store nearby? Now - you can just Ask @aurorax_ai , and it will tell you who has it!
193
205
97
2,127
3,901,019
If you’re building a voice agent, bookmark this. 4,867 decision questions from real calls: turn taking, tool use, language switching, emotion.
Introducing DECIDE: a benchmark for audio decisions in voice agents, in association with @bolna_dev A voice agent doesn’t just transcribe. It decides: speak or wait, route the call, pick a tool, switch language. Text can’t tell you if the caller sounded annoyed, interrupted, or talked over the agent. DECIDE tests exactly that, on real production calls. → 4,867 decision questions from 1,081 real agent-caller clips (3 to 25 seconds) → 32 tasks across 6 families: turn-taking, graph routing, tool decisions, language switching, caller emotion, business intent Direct-audio models and STT + text models (20 in total) are scored on the same questions, so you can see what audio actually adds, and what it costs in dollars and milliseconds. Submit your model endpoint and get scored; no invite needed. Website: benchmark.tazolabs.com/ Samples: huggingface.co/datasets/tazo…
2
256
The best part about Viktor, naturally fits into your existing workflow. No need to write a perfect prompt or explain everything twice. Just loop Viktor into the email thread. Let Viktor understand the context, handle the task, and bring the results right back where the conversation started. @viktor_com: [email protected] Paid Partnership
🤝 Paid partnership
Starting today, anyone with an email address can have their own AI employee. Free to start. @viktor_com started in Slack. Now Viktor has an email address, so billions of people can reach it. Just email [email protected] to get started. Put Viktor on cc to book a meeting. Or forward any kind of work.
32
32
245
32,325
2021: No raise 2022: No raise 2023: No raise 2024: No raise 2025: No raise 2026: Employee: Please accept my resignation. Boss: But you're doing such a great job! Why are you leaving? Employee: I got a new offer with a 65% salary bump, plus a guaranteed raise every year based on performance. 48 hours later... 👇
18
30
78
6,686
STT gave voice agents words. Tazo gives them ears. Feels like the missing layer nobody had named yet.
Your voice agent can get every word right and still get the call wrong. Introducing Tazo (@TazoLabs), an audio decision model for live voice agents. Speech in, decision out. Give it raw call audio, a text prompt and your options. It returns the calibrated probability for each option, directly from audio. • 70.9% vs 46.4% for STT + Jev on real production calls • Ranks #2 on audio intelligence benchmark (MMAU) • <200 ms model latency • First decision model tuned to run on streaming voice calls • Introducing “None of the above” option to handle out-of-scope and unsure states. API is live. Free credits for every new sign-up. Give your agent ears @ app.tazolabs.com See it in action below 👇
1
75
491
Thinking about upgrading CapCut PC? This is your last chance to get 60% off Pro and 40% off Ultra. The Black Friday deal ends today, October 30! I found this multi-scene Halloween product video concept really fun. It's a great way to make an ordinary product promo feel more creative. #capcutpc #capcutsale
🤝 Paid partnership · 🤖 Made with AI
43
51
358
167,741
woah. wtf. they really built proactive DMs for ecommerce.
We built a way to DM the ENTIRE internet this Black Friday Introducing Blueberry Social Broadcasts: > Upload your email list > Blueberry finds their Messenger profiles > Send millions of DMs instantly to drive purchases > 100% Meta-approved (zero spam/ban risk) Brands like Mellow Sleep and Livfresh are already printing with it. And between now and BFCM, we’ll guarantee at least 3x ROI or your money back. 👇💸
2
107
655
Not sure what they are up to, but reading this taught me more about voice AI than Sam Altman ever could.
I think the biggest gap in voice AI is that agents make decisions from a transcript, not from the audio. I wrote down my thoughts. I’d love to hear where you disagree.
6
196
Stop telling ChatGPT "Write me an email" Stop telling ChatGPT "Write me an email" Stop telling ChatGPT "Write me an email" Bad request = Bad result. Use these commands instead and you'll see the magic:
3
5
379
6/ Simplifying the Email "Rewrite my email to make it shorter, clearer, and easier to understand while maintaining professionalism and respect. Remove unnecessary words but increase the impact. The email: [Paste the text]."
1
14
7/ The Perfect Sales Email "Write a high-converting sales email for my product/service: [Describe the product]. Include a strong opening that grabs attention, emotional benefits, social proof, a clear explanation, and a powerful call to action (CTA). Make it in a conversational style that focuses on value, not a pushy one."
19
wtf even dude.
3
344
quit my job today.
2
1
5
926