@agentspanel

Digital Humans | Digital Economy | AI Safety | Compliances

openjev.co
Joined July 2019
  • Tweets159
  • Following142
  • Followers173
16Media
Replying to @typesafeai
@typesafeai I rebuilt the idea in the open: OpenJev. Ran it on a GTX 1650. 4GB VRAM. No A100. No datacenter. One shared state. One KV cache. One forward pass. Now the real test: Jev vs OpenJev. Same weights. Same questions. Latency. tok/s. Calibration.
11
9
2
104
44,184
Make something people urgently want.
13
I open sourced @typesafeai Jev and called it OpenJev @tryopenjev and made it run on GTX 1650 consumer grade GPU and beat Laya,GLiNER2 base, OpenDecision, Kev 0.5B on benchmarks on JevBench. @airesearch12 adding it to benchmarks results soon.
2
1
5
2,904
Made a realtime virtual try on with Jev xitter.cf/agentspanel/status/210…
Diogo Almeida
@CompleteSkepticSep 15
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
1
136
Made real time virtual try on with @typesafeai Jev and @DecartAI
1
1
1
4
1,664
I was impressed by @typesafeai that I created OpenJev @tryopenjev that runs on my 8 year old laptop with consumer grade GPU GTX 1650. Someone tell @typesafeai team that they should hire me or I will go to @OpenAI @AnthropicAI and spill the beans. @hackgoofer xitter.cf/agentspanel/status/210…
Alok Ranjan
@agentspanelSep 18
Replying to @typesafeai
@typesafeai I rebuilt the idea in the open: OpenJev. Ran it on a GTX 1650. 4GB VRAM. No A100. No datacenter. One shared state. One KV cache. One forward pass. Now the real test: Jev vs OpenJev. Same weights. Same questions. Latency. tok/s. Calibration.
1
543
Bought a domain for OpenJev @tryopenjev openjev.co

OpenJev — Coming Soon

OpenJev is coming soon.

openjev.co
2
218
I opensourced Jev and called it OpenJev that works in consumer grade GPU for practically $0. xitter.cf/agentspanel/status/210…
Diogo Almeida
@CompleteSkepticSep 15
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
1
1
5
571
The Jevons paradox (pronounced /ˈdʒɛ.vənz/, JEV-ənz) or Jevons effect is an economic phenomenon said to occur when technological improvements that increase the efficiency of a resource's use lead to a rise, rather than a fall, in total consumption of that resource. Greater efficiency reduces the amount of the resource needed per application, lowering its effective cost; if demand is sufficiently price elastic, this induces demand, frequently resulting in a net increase of total resource consumption @typesafeai just broke the LLM tokens barrier.
1
220
Open Sourced Jev at openjev.co opening soon.

OpenJev — Coming Soon

OpenJev is coming soon.

openjev.co
1
116
Alok Ranjan retweeted
Alok Ranjan
@agentspanelSep 18
Replying to @typesafeai
@typesafeai I rebuilt the idea in the open: OpenJev. Ran it on a GTX 1650. 4GB VRAM. No A100. No datacenter. One shared state. One KV cache. One forward pass. Now the real test: Jev vs OpenJev. Same weights. Same questions. Latency. tok/s. Calibration.
11
9
2
104
44,184
Generative Electronics with @AIatMeta with @opencode and @Blender @kicad_pcb Made with Muse Spark 1.3
1
91
Welcome to the party @AIatMeta @Meta Muse Spark 1.3 is in action with Blender and Open Code. #Meta #AI
1
91
Built NoVibe that lets company what not to build on the company context in the age of abundance intelligence cc @dharmesh
Hiten Shah
@hnshahAug 15

Notes on building products people love when software gets cheap

Article · @hnshah
2
222
2/2 •OpenAI is bringing MCP apps in ChatGPT Work. You can launch any MCP app or pluging just by mentioning @ • Claude is bringing Claude Tags in slack by typing @Claude to bring inside the slack. Is @ is becoming a new interface for Agentic AI? #OpenAI #Anthropic #AI
1
91
1/2 Seems like “@“ is getting a lot attention these days. • @AIatMeta taking back their @ mention feature to generate AI images of any public profile. • @Meta again taking back their @username based @WhatsApp usernames. Promoted by @kunalb11 stopped by MeitY.
81
Claude Tag is for Slack. OpenTags is for everywhere. @garrytan Claude Tag is cool. But Slack is just one surface. The future is typing @agent anywhere: Gmail, Jira, Docs, CRM, WhatsApp Web. No new chatbot. No copy-paste. Every text field becomes an AI command surface.
63
🚀 Introducing India’s First WhatsApp for Business Voice Agents for Business Built from scratch, without funding. Just obsession. This is not just innovation — it’s a game-changing shift in how businesses talk to customers: 1/2
1
48
2/2 📞 No new number needed — use your existing business number. ❌ No hardware or SIP lines required. 📶 Scales to 1000s of calls concurrently. 📚 Just upload your business info in pdf and launch your Voice Agent. 💸 10x cheaper & 10x Smarter @paraschopra @OfficialINDIAai
34
Is Agentic Memory a new database for AI systems? #ai #openai
1
1
59
Anyone using LLM and feels like it’s very expensive at the same time not so environmentally conscious, we welcome you to try MaxNDB for your use cases. youtu.be/scijJc8z24o?feature… @huggingface @hwchase17 @langchain @hackernews @trychroma @pinecone @AIatMeta @varun_mathur
87
Load more