Stipe Renic (@StipePoint8) header
Stipe Renic (@StipePoint8) profile picture

Mathematician by training. Quant researcher by practice. Builder by choice.

Joined March 2026
every wave in this video is playing a note I had Opus 5.5 rebuild the Sea Organ in Zadar, Croatia, cut it open, and let the rendered sea play it 35 pipes, klapa chords, zero recorded audio
1
5
64
26,305
1/ We let an AI stop and think only 3 times while crossing a busy road. It chose when to think: 59 of 200 roads crossed. A coin chose: 62. Perfect timing: 169. Thinking helps. Knowing when to think is the skill, and this AI didn't have it.
5
12,612
We gave an AI five buttons and one job: cross the road. Jev, @typesafeai's model for small typed decisions, steered a courier across six lanes of traffic on 200 freshly generated roads. It read the road as text, not pixels, and the game paused while it decided. We asked it two ways. One big question: here is every car's position and speed, press a button. It crossed 1 road out of 200. On 180 roads its first move was UP. Small questions: code first works out where each button leads, then Jev makes the call. It crossed 50. Same model, same roads. Only the way we asked changed. Plain code looking three moves ahead still crossed 83. When the job is arithmetic, let code do the arithmetic and use the model for the judgment on top. The video replays one example road. The full numbers are at the end.
6
1
17,368
We got 100 correct invoice approvals for about two cents in AI processing. The key was how we divided the work. We tested Jev, TypeSafe’s AI, following its creators’ recommendation: break a decision into smaller questions and combine the answers in code. Our test included 100 synthetic invoices that all met the payment rules. The correct result was clear: every invoice should be approved. For comparison, we first asked Jev to handle everything at once: read the documents, check the rules and decide whether to approve payment. It approved 42. Then we split the task: Jev identified the price, quantity and supplier status. Ordinary code checked whether those facts matched the order and satisfied the payment rules. That workflow approved 100 out of 100. Here are the correct approvals and AI processing costs for those same invoices: Jev + code: 100/100 — 2.1¢ GPT-5.6 Terra: 97/100 — 23.8¢ Claude Sonnet 5: 97/100 — 37.3¢ GPT and Claude handled the whole decision in our earlier experiment. Their costs already include batch discounts. Jev’s costs do not use a batch discount. The comparison shows the benefit of giving Jev a specific role: identify the facts, then let code make the checks we can define precisely. That division of work produced more correct approvals at a lower AI processing cost in this test.
🤖 Made with AI
1
92
This is why fraud was experiment one. At this scale, “block” isn’t just a prediction. It’s a decision between two costs: fraud you miss and legitimate payments you stop. Can an AI follow that tradeoff when the correct action is known? github.com/StipePoint8/decis…
33
Would an AI model change its decision just because you rephrased the question? We tested that on GPT and Claude with fraud decisions. Same case, same numbers, just reworded. GPT's usual decision flipped in 8% of case groups. Claude's in 18%. Setup: thousands of block / approve decisions, each with a fraud probability and a cost for each type of mistake. Every case written 4 ways: "missing fraud costs 8x a false alarm", a cost table, explicit amounts, and a plain sentence. A calculator always gives the same answer to all 4. This matters because prompts get cleaned up inside companies all the time. A sentence becomes a table, a phrase gets tightened, someone translates it. Nobody logs that as a policy change. But if the same case now gets a different decision, it is one. Also, no format was clearly the safe one: tables, the format that looks most machine-readable, were among the weakest for both models. So we won't recommend a format. Just a note to measure the system you actually deploy and run the same case through a few wordings before it goes live.
24