The cheapest MiCA-regulated crypto exchanges ↓ (bookmark for later) Revolut – 0% / 0.09% OKX – 0.08% / 0.1% Gate – 0.1% / 0.1% Bybit – 0.1% / 0.3% Bitvavo – 0.2% / 0.3% Blockchaincom – 0.2% / 0.4% Bitpanda – 0.3% / 0.3% Kraken – 0.3% / 0.4% Bitstamp – 0.3% / 0.4% Cryptocom – 0.3% / 0.5% Robinhood – 0.5% Bit2Me – 0.5% / 0.6% Coinbase – 0.6% / 1.2% eToro – 1% Swissquote – 1% / 1% Data from @DefiLlama.

$PONS revenue continues to base out after that incredible run up in early September token price continues to show resilience around the 0.5-0.6+ levels which is very encouraging with attention on RH eco the next week and Ozzy hinting at some new stuff being built + PONS v3, i think these numbers can easily pick right back up rn the market is still pretty hopeful that revenue will climb back based on the xRev chart. so the bet here is no longer the market underpricing a revenue resurgence, but rather a bet that PONS revenue inflect higher. xRev current read is 3.60 and has been climbing up ever since revenue started its decline the risks here are flipped as well if revenue doesnt pick up, xRev multiple should fall and because xRev = mcap/rev, and revenue has already fallen down while price stayed elevated, price should be the one that drags xRev back down to earth as of now, the market is currently pricing that PONS start to see higher revenue numbers. lets see if the market is right

BREAKING: US stock market futures surge after Pakistan announces that the US and Iran have reached a peace deal: 1. S&P 500: +0.8% 2. Nasdaq 100: +1.3% 3. Dow Jones: +0.6% 4. WTI Crude: -5.0% 5. Brent: -4.0% 6. Gold: +2.0% Pakistan says the peace deal is set to be signed on June 19th.

# Decision Points in AI Agent Development # Temperature 🎯 The Hook Are you using the same temperature for every task in your agent? Temperature isn't just a "creativity knob." In agent systems, structured outputs, tool calls, and user-facing responses each need fundamentally different temperature settings. Using one value for everything is leaving performance on the table. 📋 Overview Temperature controls how "peaked" or "flat" the probability distribution is when an LLM selects its next token. Near 0, the highest-probability token wins almost every time, producing deterministic and stable output. Higher values flatten the distribution, allowing lower-probability tokens through, increasing diversity and creativity. In AI agent systems, the optimal temperature varies dramatically across contexts: generating structured output, assembling tool call arguments, and producing free-form text each call for different settings. Temperature should be treated as a dynamic variable that shifts with task type, not a single fixed constant. 🔍 Decision Points Temperature is primarily driven by task_variability -- how routine vs. creative the task is. The decision flow is straightforward 🧭 1. Structured output (JSON / function calling)? → 0.0-0.3 2. Accuracy-first (fact extraction, classification, summarization)? → 0.2-0.5 3. Dialogue, explanation, communication? → 0.5-0.7 4. Creative writing, brainstorming, candidate generation? → 0.7-1.0 Additionally, higher failure_cost pushes the temperature ceiling down, and high cost_sensitivity environments should account for retry cost increases from higher temperatures. 💡 Key Details Reference values by task type 📊 - Structured output (JSON / function calling): 0.0-0.3. Minimizing schema violations is the priority - Classification, extraction, data transformation: 0.0-0.2. Accuracy and reproducibility are paramount - Summarization, explanation, customer support: 0.5-0.7. Balance naturalness with accuracy - Creative writing, brainstorming, candidate generation: 0.7-1.0. Diversity is the source of value - Tool argument generation: 0.0-0.2. Precise function and argument names are non-negotiable - Planning and reasoning: 0.3-0.6. Some exploration helps, but maintain logical consistency Start structured output temperature at 0. If schema violations occur at 0, the problem is your prompt or schema -- never rely on higher temperature to "accidentally" produce correct output 🚫 ⚖️ Trade-offs Too low and conversations become robotic 🤖 The model returns identical answers to identical questions, giving users a "template response" impression. Best-of-N sampling also breaks down -- candidates become near-identical, costing N times more for essentially N=1 results. Too high and structured outputs start breaking 💥 JSON field names drift, types mismatch, hallucinations increase -- especially dangerous for proper nouns, numbers, and dates. Tool call instability and loss of reproducibility compound the problem. Monitor the retry cost impact of temperature changes. If schema violation rates exceed roughly 5%, consider lowering the temperature. 🛠️ Use Cases Vary temperature by pathway within a single agent 🔀 Planning steps at 0.3-0.5, tool argument generation at 0.0-0.2, user-facing responses at 0.5-0.7. When switching models, adjust temperature simultaneously for a natural fit. Using Best-of-N? You need to raise the temperature. Generating N=5 candidates at temperature 0 produces 5 near-identical outputs. For N>1, set temperature to 0.5-0.8 and let a Judge select the best from diverse candidates. Be careful combining temperature with top_p ⚠️ Adjusting both simultaneously creates multiplicative effects with unpredictable behavior. As a rule, tune one and leave the other at its default. #AIAgents# #SoftwareArchitecture#

US stocks rose (SPX +0.5%, NDX +0.6%) as oil eased (brent crude -2.6% to $105) ahead of today’s August CPI, seen as the key signal for a possible Fed hike next week (odds now 70%). Core CPI is expected +0.2% vs headline +0.4% on higher gasoline prices. 10 year treasury yields slipped to 4.94%. Oracle jumped 6.6% on a beat and raised guidance; most chip stocks were higher. Despite higher inflation risks, I am skeptical of a Fed rate hike next week, unless today’s Aug CPI comes in above expectations. Strong 2026 S&P earnings growth of +32% y/y is fueling the current bull market but an inverted equity risk premium and a more restrictive Fed could lead to short-term equity weakness.​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​ Going forward my daily pre-market summary will only be available to Subscribers. Thanks for your continued interest and support.

Eurozone shares -0.5% US futures -0.2%, Nas futures +0.1% Ger 10 yr yld +5bp to 3.39% Oil +1.2% to $92.7..reports of hits on ships in Hormuz & on Saudi Red Sea oil infrastructure Gold -0.6% to $4404 Iron ore +0.1% to $100.45 Bitcoin $79.2k ASX futures -0.1% $A 0.7215 w $US -0.2%

German Government Forecasts Growth Of 0.6% In 2028 - Draft - Raises Forecast For Economic Growth To 1.3% In 2026, Up From 0.5% In April - Raises Forecast For Economic Growth To 1.1% In 2027, Up From 0.9% In April