HN user

onchainintel

9 karma

Solo founder working on PQS (prompt quality scoring) and OnChainIntel. 20+ years in marketing analytics. Now building AI/Web3 tooling. Based in Barcelona.

The world's first AI 'prompt quality' score. Your model isn't the problem. Your prompts are. x402-native on Base. http://pqs.onchainintel.net

Posts3
Comments23
View on HN
DeepSeek v4 3 months ago

Completely agree, not suggesting it needs ot just genuinely curious. Love that it can be run locally though. Open source LLMs punching back pretty hard against proprietary ones in the cloud lately in terms of performance.

Thanks for the bit of nostalgia today OP. I remember the first time that I saw that browser screen. Pure discovery back in those early days of the web. I can still hear the dial-up modem crackling...

DeepSeek v4 3 months ago

How does it compare to Opus 4.7? I've been immersed in 4.7 all week participating in the Anthropic Opus 4.7 hackathon and it's pretty impressive even if it's ravenous from a token perspective compared to 4.6

It all depends on what you do aka your use case. If you're in the content creatio business, which is part of my responsibilities, then yes has been massively helpful. For other roles, I can absolutely see no use case or benefit. Context matters, like with everything.

Brave Premium 3 months ago

Interesting. I wasn't aware that Brave had a separate offering like this and it's also a little confusing. It's not clear why or what is it about this "Brave" specifically, that is different from the mainstream Brave. They attempt to reference in that vague list of bullet points about this product versus the traditional Brave browser but doesn't really seem to answer it specifically. Do you know OP?

I imagine this would soon be the new normal. Car needs repairs? Take it to your dealer or favorite repair shop. They connect a diagnostic plugin to your vehicle, which is powered by a specialty LLM, trained on automotive data, specifically from that OEM and let the agent loose until it interrogates enough of the vehicle telemetry data to identify the problem. Hell, it's probably happening in dealerships today.

Your instincts are likely right on this one OP. Memory prices surged 80–90% in Q1 2026 compared to Q4 2025, DRAM, NAND, and HBM all at record highs. 3 suppliers for the entire planet?

No, it's not gone at all and likely never will be. It's just the same as it was when you were enjoying hacking and tinkering with tech as a 14 year old. You were then and are now a member of a very small tribe of people curious enough to explore this world, most people don't care, or not enough to take action and spend so much time on it. You're the minority relative to normies, that's all.

I agree with you directionally that project estimates are/will be affected by this but I don't see a scenario in which time is completely removed from the equation with respects to projects & estimates to execute on them. We're all constrained by time, finite resource. It's always a factor in business.

Slop Cop 3 months ago

Could you still utilize this tool running a local model (any Ollama model for example) instead of making calls out to Anthropic to avoid costs while running this tool or does it have something specific to Anthropic that requires it?