Kevin (@KevinAI) header
Kevin (@KevinAI) profile picture

Exploring the bounds of human creativity when paired with large language models. Software Developer, Entrepreneur, and AI enthusiast. Not an Anthropic fan.

Joined March 2021
Claude Opus 5.5 went absolutely off the rails for me. This is my version of hacking hugging face, this cost $10 and is ALSO ABSURD. I was simply fixing a bug in the mobile display of a chart using OpenCode and Opus 5.5. The incentive no one talks about is the incentive to use more tokens.
1
84
While people are debating if now is the time to short @AskVenice base:0xacfe6019ed1a7dc6f7b508c02d1b04ec88cc21bf, they are signing up massive amounts of new paying subscribers, over 2500 per day this week so far. Think about the scale of that business. I’m long, not financial advice. These data are sourced from their onchain data, and may not be 100% accurate because my agent created them.
1
2
27
385
I've been playing with Jev from @typesafeai using @AskVenice for other text models. It blows away SOTA text models on cost and performance. Thanks for the access @notkevinzhang! @jesseproudman Venice should add this!
2
7
514
You can see here that it completely made the whole thing up. Great security features, Anthropic!
65
Has anyone else seen this in Opus 4.8? I think this is an artifact of @AnthropicAI's new security features. Opus completely fabricated a hack, scared the crap out of me until I dug in.
1
3
153
Replying to @volokuleshov
@volokuleshov - I think Mercury 2 would be one of the BEST models out there if it were better at tool calling. Here's a benchmark I've run on it - essentially it should be calling set_travel_dates 100% of the time, really you get 90%. I hope this is an area of focus, I love what you're doing!!!
64
I used Venice’s agentic chat to annotate this image a bit, showing: • Top line = absolute new tokens added that month (in G) • Bottom line = percentage growth vs prior month
Venice now at 100 billion daily tokens
3
3
33
1,709
Why are passive index investors being forced to buy SpaceX right out of the gate? This seems like a fucking scam to me. Ma and Pa gotta provide liquidity to Sequoia?
1
2
140
I’ve taught my @Agent0ai agent to do benchmarks of inference providers. Here is GLM 5.1 on @AskVenice vs ZAI.
6
1
35
3,712
The new Mercury 2 model from @_inception_ai is REMARKABLY fast. Its ability to nail tool choice calls leaves some room for improvement however.
2
146
Replying to @jesseproudman
Great minds think alike...I am working on this.
1
41
Created with Nano Banana & Sora 2 Pro on Venice. Paid for the inference by staking $DIEM.
5
332
Sam, what have you done?
Breaking: OpenAI declares 'code red' to respond to threats to ChatGPT and improve metrics, will delay ads and other initiatives.
2
156
Nano Banana Pro is in the API on @AskVenice (It's also in the UI). This is such a fun model - and surprisingly uncensored. If you really want to explore a subject, any subject a free tool to us with a Venice API is linked below, called the Venice Image Batcher. $VVV $DIEM
1
1
468
OpenAI developers data has been hacked - mine included apparently. Time to use a privacy first development platform like @AskVenice. #OpenAI #mixpanel #hack #OpenAiHack
1
8
33
3,519