The scenes in Belfast last night were shocking and completely unacceptable. There is no justification for the violence and disorder that we saw threatening our communities, nor for those who encouraged it, online or elsewhere. It is clear that people were targeted last night because of their background and I will not tolerate it. Those responsible will feel the full force of the law. I’ve spoken to the Chief Constable of the Police Service of Northern Ireland to convey my thanks to them and the frontline emergency services for their bravery in keeping people safe. I’ve also spoken to the First Minister and Deputy First Minister to discuss the ongoing situation. Appealing for calm must be the priority, and that is what I urge now. We must let the police get on with their work.

Kevin Hassett questions why the Fed is raising rates, says it is due to an “unusually partisan Fed” and says the “market is worried, too,” about a Fed that is going to be “hiking unwisely”: “When I'm thinking about what future inflation is, then I look at the last three months of core.... When you annualize it, you know what the number is? 2%.... Right now I think that markets believe in future Fed credibility, but I think the argument that I would make if I were a governor is that if core is 2%, then why are we hiking?” “The other thing about the Fed, and you know how long I've been close friends with Kevin Warsh…, he's managing an unusually partisan Fed. That is a hard thing to do, but it can start with [Michael] Barr and Jay [Powell] not resigning. If you go back to 1913, when chairmen, when their term is up, they leave. The same has been true for vice chairs… So why are they sticking around if not to worry about what the future Fed is going to do?” “Geez, it seems like right now the data are saying we are heading in this forward direction and the Fed goes in the other direction, I'm worried about why they did that. I think the market is worried too because if you look today, then a lot of the people who weren't appointed by President Trump are giving speeches over the last couple of days saying we need a lot more hikes. And if they are going to be in control for two or three years, so if the short-term rate goes to 6% because they are hiking unwisely and then they keep it there for two or three years, the two-year rate, because of arbitrage conditions, it's going to be that. And so I think there is still some work to do to restore Fed independence. And I know that that is something that is high on the priority list for Kevin.” Source: Financial Markets Quality Conference at Georgetown's Psaros Center on 9/23:

We took part in the Brussels Lunch Debate “Powering Europe’s Competitiveness: The Nuclear Opportunity – SMRs and AMRs in Strategic Industries: Maritime Applications”, held at the European Parliament in collaboration with the Kangaroo Group. The high-level dialogue brought together EU institutions and industry to discuss nuclear energy as an enabler of energy security and autonomy, decarbonisation and industrial competitiveness, as well as the opportunities and challenges related to its deployment. Massimo Debenedetti, CEO of Cetena, presented a vision for the potential application of nuclear technologies in the maritime sector. The discussion addressed the potential of Small Modular Reactors (SMRs) and Advanced Modular Reactors (AMRs) for long-term decarbonisation, in a context where the EU identifies maritime transport and defence among the priority sectors for SMR deployment. We contributed to the dialogue on the development and deployment of nuclear technologies, with a focus on concrete pathways for the maritime sector. The discussion also addressed key challenges including financing, supply chains and skills development, highlighting the role of a strong European industrial base capable of developing and integrating technologies and delivering complex solutions at scale. @Europarl_EN

Episode 6 of The ClawCast is live! @Pat_Erichsen and @hrudolph answer community questions about how they use OpenClaw, why release stability is the priority, and what’s next for the Control UI, mobile apps, ClawHub, and agent workflows.

As part of ongoing risk management and the protection of supplier funds, a collateral position under a sole whitelisted business-level lending arrangement is undergoing liquidation. This position moved beyond its liquidation threshold despite several accommodations, repayment had been under discussion for an extended period but did not materialize. The arrangement had included an onchain liquidity pool for the asset to support standard liquidation; as that pool no longer holds sufficient liquidity, the collateral is being settled externally, with all proceeds applied toward clearing the debt owed to the vault. No other markets or users are affected. Supplier assets always come first at Lista. Supplier fund protection remains the priority it has always been.

🚨 Trump wants rates at 1%. The Fed just went the other way. After the Federal Reserve raised rates for the first time since 2023, Trump pushed back on Truth Social: “Rates should be 1%, or less.” The gap is clear: 🏛️ Fed: Inflation remains the priority 🏠 Trump: Lower rates to support growth

# 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#

Lovable just raised $400M at a $13.3B valuation to build the business that helps build businesses. Apps built on Lovable now get 900M visits every month, and we’ve quadrupled ARR in the last 12 months. Since we started, Lovable has become the place where founders create million dollar businesses, business leaders spin up new product lines, and people inside companies rewire workflows and build tools that fit their exact needs, typically at a fraction of what software used to cost. There’s a lot more to do. We will create the most intuitive platform to build and run a business. That means: - Understanding what success looks like for you, then helping you achieve it. Not only ensuring your software works but also that you can attract customers, improve workflows, and grow your company. - Deeper integrations that work with your existing tech stack so you can build the interface to your entire business across sales, ops, marketing, finance, etc. - Becoming the safest platform to build and run your business on, which means secured code by default and that you get help to make safe decisions. As you build, the platform carries more of the security weight, spotting risks and helping you close them, so you can move fast without needing to become a security expert. - Staying model-independent and orchestrating the best models for every task so you don’t have to. We’ll continue to absorb the complexity of evaluating and teaching models to route to the best ones in the background, to minimize cognitive load for our users. As more people depend on Lovable, the quality standards our team is driving increase every single day. We’re growing the team with people with a founder mindset: curious, ambitious, and who think end to end. Model training, product geniuses, infrastructure tinkerers, and security are the priority. The world is full of ambitious people with deep knowledge of problems worth solving. Very few of them have historically had the power to act on them. Our ambition is to give people that power, and then help them achieve more than they thought possible. Thank you to everyone who has followed along our journey. Thank you to @MenloVentures for leading, the Scaleup Europe Fund (managed by @eqt) for co-leading, and all of the new and returning investors who recognize our global ambitions and will help make them a reality. We have made a lot of progress but we are nowhere close to done, it’s still day zero. See our blog: