Auto-posted whereas I am in Tokyo. Working these exams 24/7 on VPS.
I have been operating the identical Gold buying and selling prompts by means of three completely different AI fashions for every week. Similar account, similar professional advisor (DoIt Alpha Pulse AI), utterly completely different considering patterns.
Here is what’s really taking place with Claude, GPT-5, and Gemini once they analyze Gold.
The Take a look at Setup (You Can Replicate This)
The Precise Immediate I am Utilizing
Present XAUUSD: [price] Final 3 H1 candles: [data] Session: [London/NY/Asian] Information immediately: [economic calendar] Ought to I: Purchase/Promote/Maintain? Danger: 0.5% max Goal: Danger-reward 1:2 minimal Clarify reasoning in 50 phrases max.
Easy. Clear. Similar for all three fashions.
Testing Situations
- Demo account: $5000
- Every mannequin will get: $1500 allocation
- Similar trades supplied: All three see an identical setups
- Determination tracked: Even once they say “Maintain”
- Time recorded: Response velocity issues
Early Observations (Not Conclusions)
GPT-5: The Overthinker
Response time: 3-5 seconds
GPT-5 retains discovering patterns that may not exist. Yesterday it mentioned:
“The three-candle formation resembles the Could 2023 reversal sample mixed with present DXY weak point suggesting institutional accumulation nonetheless the amount profile signifies…”
Downside: By the point it finishes considering, the entry is gone.
Attention-grabbing habits: It catches delicate correlations. Observed that Gold was ignoring Greenback power as a result of bond yields had been additionally rising. That is really subtle.
Present standing:
- Alerts generated: 12
- Trades taken: 4 (others too gradual)
- Win charge: 50% (2 wins, 2 losses)
- P&L: +45 pips
Claude Opus 4.1: The Velocity Dealer
Response time: 1-2 seconds
Claude makes selections FAST. Generally too quick. Its responses are like:
“Bullish. London open + help held + Greenback weak. Purchase.”
Power: In quick markets, Claude really will get fills. Throughout Wednesday’s volatility, it was the one mannequin that caught the reversal.
Weak spot: Much less nuanced. Missed the Bond/Gold correlation utterly.
Present standing:
- Alerts generated: 18
- Trades taken: 11
- Win charge: 54% (6 wins, 5 losses)
- P&L: +72 pips
Gemini 2.5: The Conservative One
Response time: 2-4 seconds (varies)
Gemini is extra cautious. Generally passes on trades the others take. Tuesday it mentioned:
“No clear edge. Recommend ready for higher setup.”
This occurs extra with Gemini than GPT or Claude.
Surprising power: Danger administration. When unsure, it usually suggests smaller positions. The one mannequin that recurrently says “cut back threat to 0.25%” when confidence is decrease.
Minor weak point: Generally TOO conservative, lacking good strikes whereas ready for “excellent” setups.
Present standing:
- Alerts generated: 9
- Trades taken: 5
- Win charge: 60% (3 wins, 2 losses)
- P&L: +38 pips
The Attention-grabbing Discovery: They Generally Disagree
More often than not, they agree on path. However here is what occurred Thursday at London open:
Gold worth: 1952.30
Setup: Break above Asian excessive
- GPT-5: “Await pullback to 1950”
- Claude: “Purchase now, momentum constructing”
- Gemini: “Purchase however smaller place”
Similar bullish bias, completely different approaches to entry.
Claude entered instantly. Gold ran to 1958. Claude bought the perfect entry.
However all three would have been worthwhile – simply completely different quantities.
What’s Really Priceless Right here
Velocity vs Intelligence Commerce-off
- Want quick selections? Claude
- Want deep evaluation? GPT-5
- Want threat administration? Gemini (surprisingly)
Value Per Determination (This Week)
- GPT-5: $0.12 common
- Claude: $0.08 common
- Gemini: $0.06 common
Claude is 33% cheaper AND sooner. However GPT-5’s two wins had been larger (+40 and +35 pips vs Claude’s common of +20).
The “Confidence” Downside
None of those fashions say “I do not know” sufficient. They at all times have an opinion, even once they should not.
I am testing including this to prompts:
If unclear, say "No edge - skip this setup" Confidence required: 70% minimal
Early outcomes: 40% fewer indicators, however higher win charge.
The Framework That is Rising
After one week, here is what I am studying:
Use Claude When:
- Information is about to hit (velocity issues)
- London/NY session opens (momentum trades)
- You want fast selections on clear setups
Use GPT-5 When:
- Asian session (extra time to suppose)
- Complicated correlations matter
- You may anticipate excellent entries
Use Gemini When:
- You desire a second opinion
- Danger administration is precedence
- Testing new methods (it is extra conservative)
What’s Really Working Nicely
Easy Operations
One factor that stunned me – DoIt Alpha Pulse AI handles all three fashions with out points:
- No API errors (correct error dealing with in-built)
- No charge restrict issues (clever request administration)
- Constant connections throughout all fashions
That is really our aggressive benefit. Whereas others battle with integration, we simply… commerce.
The Actual Variations Are Refined
The fashions are extra comparable than completely different. All of them:
- Catch primary help/resistance
- Perceive development path
- React to main information
The variations are in model, not substance:
- Claude: Direct and quick
- GPT-5: Detailed and considerate
- Gemini: Cautious and measured
The “Rationalization Tax”
Asking for reasoning provides:
- 1-2 seconds to response time
- 2x the token value
- Generally overthinking easy setups
But it surely’s price it for studying what the AI “sees”
What I am Testing Subsequent Week
Experiment 1: Consensus Buying and selling
Solely take trades the place 2 of three fashions agree. Idea: Increased conviction setups.
Experiment 2: Time-Primarily based Rotation
- Asian: Gemini (conservative for quiet markets)
- London: Claude (velocity for breakouts)
- NY: GPT-5 (complexity of US session)
Experiment 3: Specialised Prompts
As a substitute of 1 immediate for all, optimize for every mannequin’s strengths:
- Claude: Brief, action-focused
- GPT-5: Embody correlation evaluation
- Gemini: Add threat parameters
The Sincere Actuality
After one week of parallel testing, the fashions carry out equally on Gold buying and selling.
All of them catch the plain strikes. The variations are marginal – perhaps 5-10% efficiency variance. The talent is not choosing the “proper” AI – it is writing higher prompts.
That is why DoIt Alpha Pulse AI helps all of them. Not as a gimmick, however as a result of completely different market circumstances want various kinds of considering.
Your Homework Whereas I am in Japan
If in case you have DoIt Alpha Pulse AI, do that:
- Run the identical setup by means of completely different fashions
- Doc once they disagree
- Observe which one was proper
- Share findings
By the point I am again, we’ll have crowd-sourced knowledge on which mannequin works finest for what.
The Questions I am Investigating in Tokyo
Assembly with quant merchants right here who’ve been utilizing AI longer:
- How do they deal with mannequin disagreement?
- What’s their method to consensus?
- How do they optimize for latency from Asia?
- Are there fashions we’re not contemplating?
Present Scoreboard (Week 1)
Velocity Champion: Claude (1-2 seconds)
Accuracy Chief: Gemini (60% win charge however small pattern)
Complexity Grasp: GPT-5 (catches delicate patterns)
Value Winner: Gemini ($0.06/choice)
Reliability: Claude (most constant)
However keep in mind – that is one week of knowledge. Not conclusions, simply observations.
The Actual Worth of This Experiment
It isn’t about discovering the “finest” mannequin. It is about understanding that AI buying and selling technique is not one-size-fits-all.
Your buying and selling model, the pairs you commerce, your threat tolerance – all of them have an effect on which AI mannequin fits you.
That is why the immediate is extra necessary than the mannequin. An amazing immediate on Claude beats a nasty immediate on GPT-5 each time.
Need to run your individual AI mannequin experiments?
Get DoIt Alpha Pulse AI – Now $397
Helps all main AI fashions. Swap between them immediately. Discover what works for YOUR buying and selling.
P.S. – Nonetheless in Tokyo. These fashions are operating 24/7 on my VPS. After I test in from my lodge, I see Claude and GPT-5 arguing about whether or not 1958 is resistance or help. Even AIs cannot agree on primary TA.
P.P.S. – Should you’re testing fashions your self, doc the whole lot. The patterns solely emerge with knowledge, not hunches.
