semaphore
Honorary Master
- Joined
- Nov 13, 2007
- Messages
- 18,634
- Reaction score
- 9,720
South Africa’s biggest forum. Discuss, discover, and connect with thousands of members.
This your company?
Nah, I don't use claude
Might inform them they may be getting another bill thenNah, I don't use claude![]()
Excellent. Plausible deniability.
Need to create paper trails where I can.Excellent. Plausible deniability.
I want oneAnyone interested in this?
Probably around 90K-120K per machine, for that price, just get a https://www.nvidia.com/en-us/products/workstations/dgx-spark/I want one
Can i afford one?
![]()
Might be taking a shot at MacBook Pro users - at least the Windows developers... If you're a road warrior the laptop might be preferred.Probably around 90K-120K per machine, for that price, just get a https://www.nvidia.com/en-us/products/workstations/dgx-spark/
Well, codex spark models run on spark chips and its blazing fast, obviously a crappy context window. If we could get an open source model even close to the gpt spark models that would be great. I tried MiniMax M3 and even that's a big let down.Might be taking a shot at MacBook Pro users - at least the Windows developers... If you're a road warrior the laptop might be preferred.
geez I went through a whole rabbit hole with claude on a trading bot. Had a python app called Norman the trader running on a small VPS and connected to Telegram and did trading through the VALR API. Mixed results so far, although it wasn't doing any shorts and there were no gearing added. Technically it made a small profit even while the market was in down trend for the past few weeks.Been working on a trading bot with claude. Anyone notice if there is a performance difference between claude code (running on your pc) and the claude web interface ? Seem very similiar
In time. Imho it's inevitable that highly capable models become a commodity for offline usage.Well, codex spark models run on spark chips and its blazing fast, obviously a crappy context window. If we could get an open source model even close to the gpt spark models that would be great. I tried MiniMax M3 and even that's a big let down.