Working heavily with AI is kind of weird:
8 hours offline feels like 8 weeks.
You come back to a new framework, model, primitive, and 500 people already building on it.
Knowing what to ignore and staying focused is getting harder every day.
I used @umia_finance Score to estimate cigol's Tokenization Potential Value (TPV). It scored 85/100 with TPV between $50.2M and $1.1B! https://t.co/b5gSQyszZU
Still 3 more spots left in that @Pumpfun hackathon, dream not dead yet... ๐ญ
@AzFlin "one commit per phase minimum. Large phases may have multiple commits." has been working well for me since 3.5 for auto-commuting with agents with cc.
Introducing Claude Managed Agents: everything you need to build and deploy agents at scale.
It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days.
Now in public beta on the Claude Platform.
@sudoingX Is it worth going 2x 3090 if you can fit it? Does the best model change or context enough where it would warrant seeking this out or am I better off just swapping my 4080 to 3090.
Asking cause I have option to purchase 2x 3090 for 1500 rn locally.
building the biggest women-only community in San Francisco
1) You get approved
2) You get in
3) You get to know women you should've known years ago
if this sounds like you, comment๐
@ankkala I speed this up by combining all 3; hello + asking how they are doing + following up with what I was actually intending to ask in first place immediately after and it's just as effective and makes me feel like I tried to adapt.
Built cigoL in public for the Pump hackathon.
~$15/day avg profit, steady user growth.
55% W/R, 3400+ trades, $25.5k+ vol, +$5k profits
Agents will keep improving. So will everything else that is built and optimized for agentic systems