If you found it insightful, reshare it with your network.Find me → @_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs. https://t.co/SvYt7PiJQxAvi Chawla (@_avichawla):6 no-code LLM/RAG/Agent builder tools for AI engineers.Production-grade and 100% open-source!(find the GitHub repos in the replies) https://t.co/It07fQRBL7 ...

6 no-code LLM/RAG/Agent builder tools for AI engineers.Production-grade and 100% open-source!(find the GitHub repos in the replies) https://t.co/It07fQRBL7 ...

RT Market Mavericks (@MavAgents)A 'Maverick' isn’t just an LLM.It’s a swarm, signal and strategy fused into one mind.A hedge fund in your pocket.Why stop at one agent, when you can have your own trading desk 🤖 https://t.co/FTm1AKvvfW ...

Next, repeat these steps for the 2nd server to host the Smolagents Agent and its LLM.- Line 1-10 → Imports + define the Server & the LLM.- Line 12 → Decorate the method.- Line 21-28 → Define the Agent with a web search tool.- Line 31 → Serve the Agent.Finally, we use an ACP client to connect both agents in a workflow.- Line 6-7 → Connect the client to both servers.- Line 11-14 → Invoke the first agent to receive an output.- Line 18-21 → Pass the output to the next agent for enhancement.Next, run the two ser ...

RT Nick Szabo (@NickSzabo4)Voice, sometimes with video sometimes not; e.g. if you're a plumber video is for learning most plumbing skills better than textbooks and manuals, and what you got from those texts you will be able to get by dictating questions to an LLM specializing in plumbing and related knowledge, and the LLM can talk back and show diagrams. What remains for the plumber will be mostly very non-academic dexterity and human relationship skills (I'm not a big believer in robots replacing most of t ...

Financial Data and Key Metrics Changes - The company reported Q3 2025 revenue of $308 million, marking the second highest in its history, with each of its three segments showing double-digit year-over-year revenue and VMD growth [8][10] - The company has achieved revenue growth for six consecutive quarters, indicating a strong upward trend in financial performance [8] Business Line Data and Key Metrics Changes - The consumer segment's VMD grew by 26% in the quarter, with an 11% increase in revenue, driven by a 30% increase in loans closed for partners [10] - The home equity product revenue increased by 35% in Q3, despite high mortgage rates, indicating strong demand in this area [11] - The small business team reported a 50% year-over-year increase in revenue, benefiting from a concierge sales strategy [10] Market Data and Key Metrics Changes - The insurance marketplace has seen a resurgence, with the company regaining a leadership position and a nearly 60% increase in spending from its 4th to 10th largest carriers compared to the previous year [9] - The overall insurance industry remains profitable, with major clients looking to aggressively pursue market share, which bodes well for the company's revenue [27] Company Strategy and Development Direction - The company aims to leverage advancements in AI technology to enhance the consumer shopping experience for financial products [6] - A focus on operational excellence and continuous improvement is emphasized, with plans to optimize business operations further [6] - The company is prioritizing paying down debt as a default strategy, while also considering share buybacks and selective M&A opportunities [21][22] Management's Comments on Operating Environment and Future Outlook - Management expressed confidence in the sustainability of the insurance cycle, noting that major clients are in healthy positions and likely to continue investing in market share [27] - The company anticipates strong growth in the insurance segment, particularly in the first half of the next year, driven by increased VMD [30] - There is optimism regarding the personal loans business, with expectations for continued growth as lenders expand their credit criteria [10][32] Other Important Information - The company is well-positioned for growth, with a focus on expanding its distribution network and preparing for potential refinancing opportunities as mortgage rates decline [47] - Home insurance and health insurance are emerging as significant growth areas, with home insurance VMD up 80% year-over-year and health insurance VMD up 41% [55] Q&A Session Summary Question: Insights on Consumer Segment Margins - Management noted that consumer VMD margins are driven largely by the small business segment, which has seen spectacular growth and is expected to continue [14][15] Question: Capital Allocation Priorities - The company plans to prioritize debt repayment, viewing it as a risk-free return, while also considering share buybacks and M&A if attractive opportunities arise [21][22] Question: Confidence in Insurance Cycle - Management expressed confidence in the insurance industry's profitability and the likelihood of continued aggressive marketing from major clients [27] Question: Trends in Consumer Credit - Overall, there is more expansion than contraction in credit boxes, with most clients maintaining acceptable delinquency rates [32][34] Question: SEO and AI Impact on Leads - The company is experiencing a shift in traffic dynamics, with AI-driven traffic showing significantly higher conversion rates, although traditional SEO remains important [41][42] Question: Revenue Visibility Compared to Previous Quarters - Management indicated that the insurance segment is becoming more predictable, while the mortgage segment remains uncertain until rates reach a certain inflection point [43][44] Question: Potential for M&A Activity - The company is not currently looking for large acquisitions but is open to smaller deals that enhance its service offerings [51][52] Question: Contribution of Homeowner and Health Insurance - Home insurance is a significant growth area, making up about 20% of the insurance business, while health insurance contributes just over 10% [55]

As AI labs become more predatory, they also have a problem. There is so little difference between them, and it is so easy for software companies to switch from one LLM provider to another, that they are at risk of being commoditised https://t.co/zbOwpIglcV ...

MARK: MORNING, EVERYONE. WE HAVE THE PARTY PANEL HERE, BEFORE LUNCH. THIS IS A FASCINATING GROUP OF LEADERS AND INNOVATORS HERE TO TALK ABOUT AI.I THOUGHT, ON THIS BEAUTIFUL ENGLISH DAY, WE WOULD START WITH ALL OF US IMAGINING TAKING A TRIP TO WARMER CLIMATES. LET'S FIRE UP GETYOURGUIDE. JOHANNES, I AM COMING IN AS A CONSUMER.HOW WILL I ENCOUNTER AI, AND HOW WILL IT WELCOME OR EXPERIENCE. JOHANNES: GETYOURGUIDE IS THE LARGEST CONSUMER PLATFORM FOR BOOKING EXPERIENCES WORLDWIDE. WE JUST BROKE THE NEWS THIS M ...

Core Viewpoints - Many people are unaware that there is no universally accepted definition of VLA/world model/end-to-end [1] - Leading autonomous driving companies share more commonalities in their exploration of autonomous driving than the differences portrayed online, with the core being promotional divergence rather than technical route divergence [1][2] - Language plays a significant role in autonomous driving, particularly in long reasoning, user interaction value alignment, and understanding the world [1] - Those who believe that predicting the next token is more than just a probability distribution are more likely to accept that language can understand the world [1] Group 1: VLA/World Model/End-to-End - VLA, world model, and end-to-end all require the ability to generate road video data that appears real, focusing on visual information input and ultimately controlling vehicle actions [2] - The distinction lies in the involvement of language, its depth of participation, and the architectural form it takes, with future language-related tokens potentially being LLM's text tokens or photon tokens [2] - The narrative that VLA and world models represent different technical routes is misleading, as both need to generate a world model and understand the physical world [4] Group 2: End-to-End Definitions - The definition of end-to-end is often debated, with some believing it requires a core framework where input and output are clearly defined [5] - Tesla's approach, which involves visual input and outputting trajectory rather than direct control signals, raises questions about the true nature of their end-to-end definition [5][6] - The output of precise trajectories is preferred over direct control signals, suggesting a more effective design approach [6] Group 3: Tesla's Approach and Future Directions - Tesla's historical context and style suggest that their approach to end-to-end definitions may not have a universally accepted exclusivity [7] - Long-term predictions indicate that AI model inputs and outputs may predominantly involve photons, which could significantly reduce computational loads [10] - The ideal VLA model is defined as having visual or multimodal input, language participation, and ultimately directing actions in a broad sense [11] Group 4: Understanding Language and AI Potential - There are fundamental differences in views regarding LLM, particularly concerning the understanding of predicting the next token [12] - Those who see predicting the next token as more than mere statistics are more inclined to recognize the potential of LLM and AI [12][19] - The ability to predict the next token effectively implies an understanding of the underlying reality that generates the token, which is a deeper question than it appears [18]

Let's build a reasoning LLM using GRPO, from scratch (100% local): ...