Watch highlights from a rain-affected opening game of the Women's World Cup as India fight back following a middle-order collapse to defeat Sri Lanka by 59 runs.
from BBC News https://ift.tt/mGIZ5R2
from BBC News https://ift.tt/mGIZ5R2
Tuesday, 30 September 2025
Monday, 29 September 2025
Luke Donald will "think about" being European Ryder Cup captain again, but says he will not "rush into a decision" after Sunday's victory in New York.
from BBC News https://ift.tt/xmE78LX
from BBC News https://ift.tt/xmE78LX
Sunday, 28 September 2025
Gabriel scores a 96th-minute winner as Arsenal come from behind to beat Newcastle United in the Premier League at St James' Park.
from BBC News https://ift.tt/W0hXzdv
from BBC News https://ift.tt/W0hXzdv
Saturday, 27 September 2025
Friday, 26 September 2025
BBC News
IFTTT
Arena bomb-maker used five makeshift knives in attack on prison officers, court hears
Hashem Abedi appears in court over an alleged attack on prison officers earlier this year.
from BBC News https://ift.tt/9JYxe15
from BBC News https://ift.tt/9JYxe15
Thursday, 25 September 2025
Wednesday, 24 September 2025
Joshua Meadows also admits to possessing cannabis at a protest about asylum seekers at The Bell Hotel.
from BBC News https://ift.tt/ej8zTht
from BBC News https://ift.tt/ej8zTht
Tuesday, 23 September 2025
England have got the hostile bowling attack of their dreams for this winter's Ashes series in Australia, writes Stephan Shemilt.
from BBC News https://ift.tt/XSsbkHB
from BBC News https://ift.tt/XSsbkHB
Monday, 22 September 2025
Sunday, 21 September 2025
Friends of the stabbed 21-year-old Kenyan woman recount to the BBC events on the night she went missing.
from BBC News https://ift.tt/Uj9kyWX
from BBC News https://ift.tt/Uj9kyWX
Saturday, 20 September 2025
McLaren have work to do after a chaotic Azerbaijan Grand Prix qualifying session in which more than a quarter of the field crashed.
from BBC News https://ift.tt/PqtGZwh
from BBC News https://ift.tt/PqtGZwh
Friday, 19 September 2025
Mahmoud Khader Abed Adra is suspected of leading an antisemitic terrorist attack in the centre of Paris in 1982.
from BBC News https://ift.tt/6nACfiQ
from BBC News https://ift.tt/6nACfiQ
Thursday, 18 September 2025
Israel said it was targeting Hezbollah positions, while Lebanon's PM called for pressure on Israel to stop attacks.
from BBC News https://ift.tt/ls193AB
from BBC News https://ift.tt/ls193AB
The Bank of England governor warns "we're not out of the woods yet" in terms of rising inflation.
from BBC News https://ift.tt/inJ7YFE
from BBC News https://ift.tt/inJ7YFE
Wednesday, 17 September 2025
Tuesday, 16 September 2025
Monday, 15 September 2025
LATEST NEWS
New top story on Hacker News: Show HN: AI-powered web service combining FastAPI, Pydantic-AI, and MCP servers
Show HN: AI-powered web service combining FastAPI, Pydantic-AI, and MCP servers
10 by Aherontas | 2 comments on Hacker News.
Hey all! I recently gave a workshop talk at PyCon Greece 2025 about building production-ready agent systems. To check the workshop, I put together a demo repo: (I will add the slides too soon in my blog: https://ift.tt/4kDqLoR ) https://ift.tt/IVwcymo... The idea was to show how multiple AI agents can collaborate using FastAPI + Pydantic-AI, with protocols like MCP (Model Context Protocol) and A2A (Agent-to-Agent) for safe communication and orchestration. Features: - Multiple agents running in containers - MCP servers (Brave search, GitHub, filesystem, etc.) as tools - A2A communication between services - Minimal UI for experimentation for Tech Trend - repo analysis I built this repo because most agent frameworks look great in isolated demos, but fall apart when you try to glue agents together into a real application. My goal was to help people experiment with these patterns and move closer to real-world use cases. It’s not production-grade, but would love feedback, criticism, or war stories from anyone who’s tried building actual multi-agent systems. Big questions: Do you think agent-to-agent protocols like MCP/A2A will stick? Or will the future be mostly single powerful LLMs with plugin stacks? Thanks — excited to hear what the HN crowd thinks!
10 by Aherontas | 2 comments on Hacker News.
Hey all! I recently gave a workshop talk at PyCon Greece 2025 about building production-ready agent systems. To check the workshop, I put together a demo repo: (I will add the slides too soon in my blog: https://ift.tt/4kDqLoR ) https://ift.tt/IVwcymo... The idea was to show how multiple AI agents can collaborate using FastAPI + Pydantic-AI, with protocols like MCP (Model Context Protocol) and A2A (Agent-to-Agent) for safe communication and orchestration. Features: - Multiple agents running in containers - MCP servers (Brave search, GitHub, filesystem, etc.) as tools - A2A communication between services - Minimal UI for experimentation for Tech Trend - repo analysis I built this repo because most agent frameworks look great in isolated demos, but fall apart when you try to glue agents together into a real application. My goal was to help people experiment with these patterns and move closer to real-world use cases. It’s not production-grade, but would love feedback, criticism, or war stories from anyone who’s tried building actual multi-agent systems. Big questions: Do you think agent-to-agent protocols like MCP/A2A will stick? Or will the future be mostly single powerful LLMs with plugin stacks? Thanks — excited to hear what the HN crowd thinks!
Sunday, 14 September 2025
LATEST NEWS
New top story on Hacker News: Eye drops could replace glasses or surgery for longsightedness, study says
Eye drops could replace glasses or surgery for longsightedness, study says
14 by giuliomagnifico | 1 comments on Hacker News.
14 by giuliomagnifico | 1 comments on Hacker News.
Manchester City beat rivals Manchester United 3-0, with a goal from Phil Foden followed by two from Erling Haaland at Etihad Stadium.
from BBC News https://ift.tt/RbuDQlY
from BBC News https://ift.tt/RbuDQlY
Saturday, 13 September 2025
Friday, 12 September 2025
Thursday, 11 September 2025
Wednesday, 10 September 2025
LATEST NEWS
New top story on Hacker News: Launch HN: Recall.ai (YC W20) – API for meeting recordings and transcripts
Launch HN: Recall.ai (YC W20) – API for meeting recordings and transcripts
13 by davidgu | 3 comments on Hacker News.
Hey HN, we're David and Amanda from Recall.ai ( https://www.recall.ai ). Today we’re launching our Desktop Recording SDK, a way to get meeting data without a bot in the meeting: https://ift.tt/CGLcyeh . It’s our biggest release in quite a while so we thought we’d finally do our Launch HN :) Here’s a demo that shows it producing a transcript from a meeting, followed by examples in code: https://www.youtube.com/watch?v=4croAGGiKTA . API docs are at https://docs.recall.ai/ . Back in W20, our first product was an API that lets you send a bot participant into a meeting. This gives developers access to audio/video streams and other data in the meeting. Today, this API powers most of the meeting recording products on the market. Recently, meeting recording through a desktop form factor instead of a bot has become popular. Many products like Notion and ChatGPT have added desktop recording functionality, and LLMs have made it easier to work with unstructured transcripts. But it’s actually hard to reliably record meetings at scale with a desktop app, and most developers who want to add recording functionality don’t want to build all this infrastructure. Doing a basic recording with just the microphone and system audio is fairly straightforward since you can just use the system APIs. But it gets a lot harder when you want to capture speaker names, produce a video recording, get real-time data, or run this in production at large scale: - Capturing speaker names involves using accessibility APIs to screen-scrape the video conference window to monitor who is speaking at what time. When video conferencing platforms change their UI, we must ship a change immediately, so this keeps working. - Producing a video recording that is clean, and doesn’t capture the video conferencing platform UI involves detecting the participant tiles, cropping them out, and compositing them together into a clean video recording. - Because the desktop recording code runs on end-user machines, we need to make it as efficient as possible. This means writing highly platform-optimized code, taking advantage of hardware encoders when available, and spending a lot of time doing profiling and performance testing. Meeting recording has zero margin for failure because if anything breaks, you lose the data forever. Reliability is especially important, which dramatically increases the amount of engineering effort required. Our Desktop Recording SDK takes care of all this and lets developers build meeting recording features into their desktop apps, so they can record both video conferences and in-person meetings without a bot. We built Recall.ai because we experienced this problem ourselves. At our first startup, we built a tool for product managers that included a meeting recording feature. 70% of our engineering time was taken up by just this feature! We ended up starting Recall.ai to solve this instead. Since then, over 2000 companies use us to power their recording features, e.g. Hubspot for sales call recording, Clickup for their AI note taker. Our users are engineering teams building commercial products for financial services, telehealth, incident management, sales, interviewing, and more. We also power internal tooling for large enterprises. Running this sort of infrastructure has led to unexpected technical challenges! For example, we had to debug a 1 in 36 million segfault in our audio encoder ( https://ift.tt/XKMVWgT... ), we encountered a Postgres lock-up that only occurs when you have tens of thousands of concurrent writers ( https://ift.tt/8yhP9rE ), and we saved over $1M a year on AWS by optimizing the way we shuffle data around between our processes ( https://ift.tt/O1Z4Ynj ). You can try it here: https://www.recall.ai . It's self-serve with $5 of free credits. Pricing starts at $0.70 for every hour of recording, prorated to the second. We offer volume discounts with scale. All data recorded through Recall.ai is the property of our customers, we support 0-day retention, and we don’t train models on customer data. We would love your feedback!
13 by davidgu | 3 comments on Hacker News.
Hey HN, we're David and Amanda from Recall.ai ( https://www.recall.ai ). Today we’re launching our Desktop Recording SDK, a way to get meeting data without a bot in the meeting: https://ift.tt/CGLcyeh . It’s our biggest release in quite a while so we thought we’d finally do our Launch HN :) Here’s a demo that shows it producing a transcript from a meeting, followed by examples in code: https://www.youtube.com/watch?v=4croAGGiKTA . API docs are at https://docs.recall.ai/ . Back in W20, our first product was an API that lets you send a bot participant into a meeting. This gives developers access to audio/video streams and other data in the meeting. Today, this API powers most of the meeting recording products on the market. Recently, meeting recording through a desktop form factor instead of a bot has become popular. Many products like Notion and ChatGPT have added desktop recording functionality, and LLMs have made it easier to work with unstructured transcripts. But it’s actually hard to reliably record meetings at scale with a desktop app, and most developers who want to add recording functionality don’t want to build all this infrastructure. Doing a basic recording with just the microphone and system audio is fairly straightforward since you can just use the system APIs. But it gets a lot harder when you want to capture speaker names, produce a video recording, get real-time data, or run this in production at large scale: - Capturing speaker names involves using accessibility APIs to screen-scrape the video conference window to monitor who is speaking at what time. When video conferencing platforms change their UI, we must ship a change immediately, so this keeps working. - Producing a video recording that is clean, and doesn’t capture the video conferencing platform UI involves detecting the participant tiles, cropping them out, and compositing them together into a clean video recording. - Because the desktop recording code runs on end-user machines, we need to make it as efficient as possible. This means writing highly platform-optimized code, taking advantage of hardware encoders when available, and spending a lot of time doing profiling and performance testing. Meeting recording has zero margin for failure because if anything breaks, you lose the data forever. Reliability is especially important, which dramatically increases the amount of engineering effort required. Our Desktop Recording SDK takes care of all this and lets developers build meeting recording features into their desktop apps, so they can record both video conferences and in-person meetings without a bot. We built Recall.ai because we experienced this problem ourselves. At our first startup, we built a tool for product managers that included a meeting recording feature. 70% of our engineering time was taken up by just this feature! We ended up starting Recall.ai to solve this instead. Since then, over 2000 companies use us to power their recording features, e.g. Hubspot for sales call recording, Clickup for their AI note taker. Our users are engineering teams building commercial products for financial services, telehealth, incident management, sales, interviewing, and more. We also power internal tooling for large enterprises. Running this sort of infrastructure has led to unexpected technical challenges! For example, we had to debug a 1 in 36 million segfault in our audio encoder ( https://ift.tt/XKMVWgT... ), we encountered a Postgres lock-up that only occurs when you have tens of thousands of concurrent writers ( https://ift.tt/8yhP9rE ), and we saved over $1M a year on AWS by optimizing the way we shuffle data around between our processes ( https://ift.tt/O1Z4Ynj ). You can try it here: https://www.recall.ai . It's self-serve with $5 of free credits. Pricing starts at $0.70 for every hour of recording, prorated to the second. We offer volume discounts with scale. All data recorded through Recall.ai is the property of our customers, we support 0-day retention, and we don’t train models on customer data. We would love your feedback!
Tuesday, 9 September 2025
Monday, 8 September 2025
Sunday, 7 September 2025
Jacob Bethell's maiden century and Jofra Archer's 4-18 with the ball help England to a men's One Day International record win of 342 runs in the third match of the series against South Africa in Southampton.
from BBC News https://ift.tt/KQTDjf3
from BBC News https://ift.tt/KQTDjf3
Saturday, 6 September 2025
Friday, 5 September 2025
About 450 jobs will also go after the value chain said it was making losses as costs continue to rise.
from BBC News https://ift.tt/KNEfl8s
from BBC News https://ift.tt/KNEfl8s
Thursday, 4 September 2025
Jacob Bethell hits Keshav Maharaj for four boundaries off one over as he and Joe Root lead England's chase of 331 against South Africa in the second ODI at Lord's.
from BBC News https://ift.tt/jY7iI4c
from BBC News https://ift.tt/jY7iI4c
LATEST NEWS
New top story on Hacker News: AI Not Affecting Job Market Much So Far, New York Fed Says
AI Not Affecting Job Market Much So Far, New York Fed Says
41 by speckx | 19 comments on Hacker News.
41 by speckx | 19 comments on Hacker News.
A high schooler writes about AI tools in the classroom
88 by dougb5 | 74 comments on Hacker News.
https://ift.tt/rBjMOtV
88 by dougb5 | 74 comments on Hacker News.
https://ift.tt/rBjMOtV
Wednesday, 3 September 2025
The comeback in February 2026 will come five years after the chain closed its stores.
from BBC News https://ift.tt/eJMuiR8
from BBC News https://ift.tt/eJMuiR8
LATEST NEWS
New top story on Hacker News: Vector search on our codebase transformed our SDLC automation
Vector search on our codebase transformed our SDLC automation
17 by antonybrahin | 2 comments on Hacker News.
Hey HN, In software development, the process of turning a user story into detailed documentation and actionable tasks is critical. However, this manual process can often be a source of inconsistency and a significant time investment. I was driven to see if I could streamline and elevate it. I know this is a hot space, with big players like GitHub and Atlassian building integrated AI, and startups offering specialized platforms. My goal wasn't to compete with them, but to see what was possible by building a custom, "glass box" solution using the best tools for each part of the job, without being locked into a single ecosystem. What makes this approach different is the flexibility and full control. Instead of a pre-packaged product, this is a resilient workflow built on Power Automate, which acts as the orchestrator for a sequence of API calls: Five calls to the Gemini API for the core generation steps (requirements, tech spec, test strategy, etc.). One call to an Azure OpenAI model to create vector embeddings of our codebase. One call to Azure AI Search to perform the Retrieval-Augmented Generation (RAG). This was the key to getting context-aware, non-generic outputs. It reads our actual code to inform the technical spec and tasks. A bunch of direct calls to the Azure DevOps REST API (using a PAT) to create the wiki pages and work items, since the standard connectors were a bit limited. The biggest challenge was moving beyond simple prompts and engineering a resilient system. Forcing the final output into a rigid JSON schema instead of parsing text was a game-changer for reliability. The result is a system that saves us hours on every story and produces remarkably consistent, high-quality documentation and tasks. The full write-up with all the challenges, final prompts, and screenshots is in the linked blog post. I’m here to answer any questions. Would love to hear your feedback and ideas!
17 by antonybrahin | 2 comments on Hacker News.
Hey HN, In software development, the process of turning a user story into detailed documentation and actionable tasks is critical. However, this manual process can often be a source of inconsistency and a significant time investment. I was driven to see if I could streamline and elevate it. I know this is a hot space, with big players like GitHub and Atlassian building integrated AI, and startups offering specialized platforms. My goal wasn't to compete with them, but to see what was possible by building a custom, "glass box" solution using the best tools for each part of the job, without being locked into a single ecosystem. What makes this approach different is the flexibility and full control. Instead of a pre-packaged product, this is a resilient workflow built on Power Automate, which acts as the orchestrator for a sequence of API calls: Five calls to the Gemini API for the core generation steps (requirements, tech spec, test strategy, etc.). One call to an Azure OpenAI model to create vector embeddings of our codebase. One call to Azure AI Search to perform the Retrieval-Augmented Generation (RAG). This was the key to getting context-aware, non-generic outputs. It reads our actual code to inform the technical spec and tasks. A bunch of direct calls to the Azure DevOps REST API (using a PAT) to create the wiki pages and work items, since the standard connectors were a bit limited. The biggest challenge was moving beyond simple prompts and engineering a resilient system. Forcing the final output into a rigid JSON schema instead of parsing text was a game-changer for reliability. The result is a system that saves us hours on every story and produces remarkably consistent, high-quality documentation and tasks. The full write-up with all the challenges, final prompts, and screenshots is in the linked blog post. I’m here to answer any questions. Would love to hear your feedback and ideas!