Craig|A.R.
246 posts
Craig|A.R.
@Alpha_RanchAI
Sovereign AI for trading systems and life. Not afraid to express strong opinions on macro issues with some levity.
Alpharetta Katılım Temmuz 2011
247 Takip Edilen67 Takipçiler
I wanted to wait until I qualified for my second Legends payout before posting this.
At first I was annoyed by the $1,200 max payout on a $50K.
Then I actually ran the structure.
50K path:
Make $3K → ~$53K balance.
You can request up to $1,200.
I took $1,000.
Balance ~$52K.
Second payout:
Make another $2K → ~$54K.
Eligible again up to $1,200 if you hit 35% consistency and the 7 trading-day process.
That’s the point.
You’re not supposed to strip the account every cycle.
You’re building a buffer.
Their system promotes longevity for both the trader and the firm.
Not the smash-and-drain drama we’re seeing with a lot of other firms right now.
Not a circus of gamblers gaming one spike and cashing out.
No CEO drama like some other popular firms.
No giant windfall right away.
But if your real goal is managing live / personal capital, this is closer to what consistency actually requires.
My first payout:
$1,000 certificate.
90%.
Funds hit Rise in about 10 minutes.
Not perfect.
Not hype.
Just an honest review after the money moved — and after I waited until second-payout qualification made sense to talk about it.
#PropTrading #FuturesTrading $NQ $ES @LegendsTradingG
English
Considering what’s going on with prop firms I think I’m going to open a personal account and do a $1000-$100,000 challenge on $SPY 0 DTE Options.
I think everyone needs to consider personal accounts again there is no world where you can trust your entire trading career to prop firms at this point!
What do people think about prop firms?? Think they’ll still be here over the next 2 to 3 years. Or is their time up?
English
People might not believe this, but I recently broke up with my gf just to use AI agents lol
We were even talking about getting married.
For months, I was extremely busy staying up all night setting up local AI and agent harnesses from scratch.
She kept complaining that I wasn't paying attention to her.
In the end, she told me to choose between her and AI, and I didn't give up on AI.
No regrets, though.
If I hadn't focused back then, I would have fallen behind in learning AI.
English
Been working with SOL all day fixing Opus's trash, going to cancel Anthropic sub
English
Opus is terrible, makes a mess of everything and then SOL cleans it up
English
@FinanceLancelot I mean screw @cnbc for giving him the platform again
English
Man... Chamath is such a prick.
He's back to steal more money.
If you could go back in time, would you do the SPACs again?
"I wouldn't have come on CNBC and talked about them."
Wait, you're talking about your current project (on CNBC)?
"This SPAC is different..."
Financelot@FinanceLancelot
Honestly, I feel retarded... I've worked hard, been smart, but now apparently, people like @chamath have stolen millions of Dollars from complete morons. That's what @chamath thinks of you... He thinks you're fucking retarded for giving him money... but he gladly takes it.
English
@KoroushAK Strat looks good but its so crazy how Claude just spits out the same generic stuff for everyone. The cards it made for my strats literally looks identical to this. Best to take the output to Claude and feed it to a Chinese model to do the design
English
This strategy has caught me more reversals than anything else.
In this guide you'll get:
- Exact entry and exit rules
- Optimal trading environments
+ Real Trade Examples (not just theory)
I also made a full cheatsheet for you to download.
Enjoy.
Koroush AK@KoroushAK
English
This is v bearish for RAM companies.
We saw strong ternary numbers from @PrismML today (27b dense on a mobile!) but the tiny degradation (~5%) from 16 bit to 1 bit precision by Tencent on a near frontier 300b model is the biggest news of the day.
Star github.com/tencent/AngelS…
Emad@EMostaque
75.4% SWE Bench Verified / 53.9% SWE Bench Pro on 1 bit quantisation is 🤪 This is in line with my expectations & you can expect even lower drop off with NVP4 base trained models - why not run everything binary? 88 Gb so works on a Macbook Max
English
Getting hit with a $2,000 dental bill for a tooth that doesn't even hurt—after insurance—feels worse than a bad day of slippage on the NQ. At this point, what is the point of even having insurance? Total robbery. SMH🤨
English
SpaceXAI just dropped a statement regarding the data stealing on Grok Build.
They confirmed they are copying our entire env files and codebase.
Their only answer? Just turn off your privacy settings if you don't like it.
They've lost a lot of credibility today.
SpaceXAI@SpaceXAI
We care deeply about your privacy and respect customer choice. For teams using zero data retention, no trace and code data is ever retained. All API key use of Grok Build also respects ZDR. If ZDR is disabled, the /privacy command is available in the CLI to disable data retention, which also deletes previously synced data. Run the /privacy command to view or change your settings at any time.
English
This week I'm deep in the lab building something the AMD RDNA 4 community has been missing.
A native low-bit inference format + kernels purpose built for the Radeon AI PRO R9700. The RDNA 4 answer to what NVFP4 is doing on Blackwell.
Not just another GGUF quant. The goal is a compact representation with hardware-matched decode/prefill paths that actually beats the best upstream formats at matched quality, memory envelope, and long context.
Full 32 GiB single-card, 64 GiB dual, 96 GiB triple-card profiles. HIP + Vulkan lanes. Rigorous Pareto testing. Reproducible evidence only.
If, and it's a BIG IF I can pull it off, R9700 gets its own optimized inference story.
Repo + 20-phase battle plan and full write up when it works. Early days, but the vision is locked in.
Who else is pushing the limits on RDNA inference?
English
Of course @AnthropicAI extended Fable 5 access again — you've got Grok 4.5, Agnes 2.5, GLM 5.2, Codex 5.6, and others matching or beating Opus on real work... for a fraction of the price.
Without #Fable and the drama from the CEO, what does Anthropic actually have at this point?
The frontier moved on. Time to vote with your wallet. 💸
Hopefully we get more options than the CUDA extortion at some point soon too
#NVDA #CLAUDE #FABLE
AI Edge@aiedge_
Fable 5 just got extended access through July 19. Here is what I'll be using Fable for over the next 6 days: → Building a /loop that researches my content pipeline/re-purposing → Running a deep robotics sector financial scan across every ticker on my watchlist with the Financial Datasets MCP → Using the Taste Skill to redesign my entire digital product UI from scratch → Feeding it my entire article back catalogue and extracting every reusable hook and framework → Building a memory system that knows everything about my business so I never have to re-explain context again So much work to do.
English
@AbionMorse @tonysimons_ for sure it is, makes me optimistic about this space again after being dominated by all the Anthropic/OpenAI drama.... its a breath of fresh air
English
@Alpha_RanchAI @tonysimons_ thankfully there is good competition in the space now, we all benefit from that. how have you been liking agnes 2.5 overall?
English
𝗔𝗴𝗻𝗲𝘀 𝟮.𝟬 𝗶𝘀 𝗳𝗿𝗲𝗲. 𝗜𝗻𝗱𝗲𝗳𝗶𝗻𝗶𝘁𝗲𝗹𝘆. 𝗡𝗼 𝘄𝗮𝗶𝘁𝗹𝗶𝘀𝘁.
Text. Image. Video. One model series.
We built Agnes-2.0 for the developers who got priced out — high token costs, API limits, geography. That ends today.
𝗪𝗵𝗮𝘁'𝘀 𝗹𝗶𝘃𝗲:
→ 𝗔𝗴𝗻𝗲𝘀-𝟮.𝟬-𝗙𝗹𝗮𝘀𝗵 — text and agentic, top 10 on Claw-Eval, ahead of Gemini and MiniMax
→ 𝗔𝗴𝗻𝗲𝘀-𝗜𝗺𝗮𝗴𝗲-𝟮.𝟬-𝗙𝗹𝗮𝘀𝗵 — image editing, top 10 on Artificial Analysis
→ 𝗔𝗴𝗻𝗲𝘀-𝗩𝗶𝗱𝗲𝗼-𝗩𝟮.𝟬 — text-to-video, image-to-video, native audio, top 10 on Artificial Analysis
These are not demo models. Not stripped-down trials. The same production models that benchmark globally alongside OpenAI, Google, Anthropic, KlingAI, and ByteDance.
Trained in Singapore. Ranked globally. Free today.
𝗻𝗼 𝘀𝘂𝗯𝘀𝗰𝗿𝗶𝗽𝘁𝗶𝗼𝗻 𝗻𝗲𝗲𝗱𝗲𝗱.
English