Always On, Always Connected, Always Searching, Always Distracted
13 by leejo | 1 comments on Hacker News.
13 by leejo | 1 comments on Hacker News.
Intentional math errors in David Foster Wallace's work (2009)
14 by rafaepta | 3 comments on Hacker News.
14 by rafaepta | 3 comments on Hacker News.
Launch HN: BitBoard (YC X25) – AI agents for healthcare back-offices
5 by arcb | 1 comments on Hacker News.
Hi HN! We’re Connor and Ambar, and we’re working on BitBoard ( https://bitboard.work ). We build AI agents that handle repetitive administrative tasks in healthcare clinics like filling out intake forms, prepping charts, or managing referrals. We were early employees at Forward, which provided primary care across the US. To scale this, we relied on thousands of remote contractors to do repetitive administrative work like reconciling patient records, and scheduling follow-ups based on care plans. It was a huge bottleneck—expensive, error-prone, and always pulling attention away from clinical care. Our software solutions were always too brittle, never managing to handle the variance of clinical data we oversaw. AI, when applied well, is capable of performing a lot of the tasks we manually did. So we decided to take another crack at the problem by building today what we would have liked to have back then, and to help clinics use it. Clinics send us their SOPs (Standard Operating Procedures—for example, “prep a patient chart from these records before a visit”), and we turn them into AI agents that do the work. These agents act like remote contractors: they log into EHRs, navigate internal tools, and do the work in the background. Unlike classical RPA, we build in verification and deterministic checks, so customers can confirm it was done right. Unlike low-code tools, there’s nothing new to learn. Customers don’t have to touch a UI or maintain logic. They just hand us the task, and we do it. Clinicians don’t want more screens! They erode attention and cause weird bottlenecks in operations because someone has to drive them. Our product is built to address this. Here’s a demo video: https://www.youtube.com/watch?v=t_tQ0fYo85g . We’re not self-serve yet, but we deploy with customers in days after onboarding them. We’re working on speeding that up. One of our early customers is a fast-growing obesity medicine group. Their MAs were spending 15 to 20 minutes per patient just entering intake form data into the EHR. That one task was taking up 30% of their MA time. We took it over in a week. It’s now fully automated, and they’ve cleared the backlog and sped up visits. A few technical problems are specifically relevant to building healthcare agents: - Unreliable interfaces: many EHRs and clinic tools don’t follow modern web standards, making automation brittle. We’ve forked browser-use to solve some of these challenges. We’re working on analogous infrastructure to let agents operate on desktops and across a wide range of APIs. - Verification: in healthcare, tasks need to be provably correct. We embed deterministic checks into each workflow so agents can confirm the task was completed as expected and the output is accurate. - Workflow generation: clinic SOPs are written in natural language and vary widely, yet still describe the actual process that works for clinics. We charge per task, based on complexity. We’re HIPAA compliant, audit-logged, and operate in a zero-retention environment unless auditing requires otherwise. A meaningful part is building trust in a high-stakes environment like healthcare. Part of that is making the product reliable. But another educational part is learning how to introduce a new concept like “agents” to clinics. We’re working on the right ways to describe them, to onboard them, to measure them. Endearingly, one of our customers’ agents is named “Robert Ott”, and they refer to him by name in their weekly updates like he’s a member of the team :) We’re learning a lot and have a long way to go. We’d love to meet other folks who 1. work in medical groups or health systems and want to offload repetitive work, and 2. are building in this space and want to trade notes. We’re happy to share everything we’ve learned so far. And this is a big space, with a lot of learnings from personal stories, from clinicians, technologists, administrators, and more. What do…
5 by arcb | 1 comments on Hacker News.
Hi HN! We’re Connor and Ambar, and we’re working on BitBoard ( https://bitboard.work ). We build AI agents that handle repetitive administrative tasks in healthcare clinics like filling out intake forms, prepping charts, or managing referrals. We were early employees at Forward, which provided primary care across the US. To scale this, we relied on thousands of remote contractors to do repetitive administrative work like reconciling patient records, and scheduling follow-ups based on care plans. It was a huge bottleneck—expensive, error-prone, and always pulling attention away from clinical care. Our software solutions were always too brittle, never managing to handle the variance of clinical data we oversaw. AI, when applied well, is capable of performing a lot of the tasks we manually did. So we decided to take another crack at the problem by building today what we would have liked to have back then, and to help clinics use it. Clinics send us their SOPs (Standard Operating Procedures—for example, “prep a patient chart from these records before a visit”), and we turn them into AI agents that do the work. These agents act like remote contractors: they log into EHRs, navigate internal tools, and do the work in the background. Unlike classical RPA, we build in verification and deterministic checks, so customers can confirm it was done right. Unlike low-code tools, there’s nothing new to learn. Customers don’t have to touch a UI or maintain logic. They just hand us the task, and we do it. Clinicians don’t want more screens! They erode attention and cause weird bottlenecks in operations because someone has to drive them. Our product is built to address this. Here’s a demo video: https://www.youtube.com/watch?v=t_tQ0fYo85g . We’re not self-serve yet, but we deploy with customers in days after onboarding them. We’re working on speeding that up. One of our early customers is a fast-growing obesity medicine group. Their MAs were spending 15 to 20 minutes per patient just entering intake form data into the EHR. That one task was taking up 30% of their MA time. We took it over in a week. It’s now fully automated, and they’ve cleared the backlog and sped up visits. A few technical problems are specifically relevant to building healthcare agents: - Unreliable interfaces: many EHRs and clinic tools don’t follow modern web standards, making automation brittle. We’ve forked browser-use to solve some of these challenges. We’re working on analogous infrastructure to let agents operate on desktops and across a wide range of APIs. - Verification: in healthcare, tasks need to be provably correct. We embed deterministic checks into each workflow so agents can confirm the task was completed as expected and the output is accurate. - Workflow generation: clinic SOPs are written in natural language and vary widely, yet still describe the actual process that works for clinics. We charge per task, based on complexity. We’re HIPAA compliant, audit-logged, and operate in a zero-retention environment unless auditing requires otherwise. A meaningful part is building trust in a high-stakes environment like healthcare. Part of that is making the product reliable. But another educational part is learning how to introduce a new concept like “agents” to clinics. We’re working on the right ways to describe them, to onboard them, to measure them. Endearingly, one of our customers’ agents is named “Robert Ott”, and they refer to him by name in their weekly updates like he’s a member of the team :) We’re learning a lot and have a long way to go. We’d love to meet other folks who 1. work in medical groups or health systems and want to offload repetitive work, and 2. are building in this space and want to trade notes. We’re happy to share everything we’ve learned so far. And this is a big space, with a lot of learnings from personal stories, from clinicians, technologists, administrators, and more. What do…
Denmark: Minister for Digitalization wants to phase out Microsoft
64 by doener | 11 comments on Hacker News.
64 by doener | 11 comments on Hacker News.
Show HN: Chili3d – A open-source, browser-based 3D CAD application
34 by xiange | 5 comments on Hacker News.
I'm currently developing Chili3D, an open-source, browser-based 3D CAD application. By compiling OpenCascade to WebAssembly and integrating Three.js, Chili3D delivers near-native performance for powerful online modeling, editing, and rendering—all without local installation. Access it here: https://ift.tt/SqglBHu Features: Modeling Tools: Create basic shapes (boxes, cylinders, cones, etc.), 2D sketches (lines, arcs, circles, etc.), and perform advanced operations (boolean operations, extrusion, revolution, etc.). Snapping and Tracking: Precisely snap to geometric features, workplanes, and track axes for accurate alignment. Editing Tools: Modify (chamfer, fillet, trim, etc.), transform (move, rotate, mirror), and perform advanced edits (feature removal, sub-shape manipulation). Measurement Tools: Measure angles and lengths, and calculate sums of length, area, and volume. Document Management: Create, open, and save documents, with full undo/redo history and support for importing/exporting STEP, IGES, BREP formats. User Interface: Office-style interface with contextual command organization, hierarchical assembly management, dynamic workplanes, and 3D viewport controls. Multi-Language Support: Built-in i18n support with current languages including Chinese and English.
34 by xiange | 5 comments on Hacker News.
I'm currently developing Chili3D, an open-source, browser-based 3D CAD application. By compiling OpenCascade to WebAssembly and integrating Three.js, Chili3D delivers near-native performance for powerful online modeling, editing, and rendering—all without local installation. Access it here: https://ift.tt/SqglBHu Features: Modeling Tools: Create basic shapes (boxes, cylinders, cones, etc.), 2D sketches (lines, arcs, circles, etc.), and perform advanced operations (boolean operations, extrusion, revolution, etc.). Snapping and Tracking: Precisely snap to geometric features, workplanes, and track axes for accurate alignment. Editing Tools: Modify (chamfer, fillet, trim, etc.), transform (move, rotate, mirror), and perform advanced edits (feature removal, sub-shape manipulation). Measurement Tools: Measure angles and lengths, and calculate sums of length, area, and volume. Document Management: Create, open, and save documents, with full undo/redo history and support for importing/exporting STEP, IGES, BREP formats. User Interface: Office-style interface with contextual command organization, hierarchical assembly management, dynamic workplanes, and 3D viewport controls. Multi-Language Support: Built-in i18n support with current languages including Chinese and English.
JavelinGuard: Low-Cost Transformer Architectures for LLM Security
4 by sharathr | 0 comments on Hacker News.
We present JavelinGuard, a suite of low-cost, high-performance model architectures designed for detecting malicious intent in Large Language Model (LLM) interactions, optimized specifically for production deployment. Recent advances in transformer architectures, including compact BERT(Devlin et al. 2019) variants (e.g., ModernBERT (Warner et al. 2024)), allow us to build highly accurate classifiers with as few as approximately 400M parameters that achieve rapid inference speeds even on standard CPU hardware. We systematically explore five progressively sophisticated transformer-based architectures: Sharanga (baseline transformer classifier), Mahendra (enhanced attention-weighted pooling with deeper heads), Vaishnava and Ashwina (hybrid neural ensemble architectures), and Raudra (an advanced multi-task framework with specialized loss functions). Our models are rigorously benchmarked across nine diverse adversarial datasets, including popular sets like the NotInject series, BIPIA, Garak, ImprovedLLM, ToxicChat, WildGuard, and our newly introduced JavelinBench, specifically crafted to test generalization on challenging borderline and hard-negative cases. Additionally, we compare our architectures against leading open-source guardrail models as well as large decoder-only LLMs such as gpt-4o, demonstrating superior cost-performance trade-offs in terms of accuracy, and latency. Our findings reveal that while Raudra's multi-task design offers the most robust performance overall, each architecture presents unique trade-offs in speed, interpretability, and resource requirements, guiding practitioners in selecting the optimal balance of complexity and efficiency for real-world LLM security applications.
4 by sharathr | 0 comments on Hacker News.
We present JavelinGuard, a suite of low-cost, high-performance model architectures designed for detecting malicious intent in Large Language Model (LLM) interactions, optimized specifically for production deployment. Recent advances in transformer architectures, including compact BERT(Devlin et al. 2019) variants (e.g., ModernBERT (Warner et al. 2024)), allow us to build highly accurate classifiers with as few as approximately 400M parameters that achieve rapid inference speeds even on standard CPU hardware. We systematically explore five progressively sophisticated transformer-based architectures: Sharanga (baseline transformer classifier), Mahendra (enhanced attention-weighted pooling with deeper heads), Vaishnava and Ashwina (hybrid neural ensemble architectures), and Raudra (an advanced multi-task framework with specialized loss functions). Our models are rigorously benchmarked across nine diverse adversarial datasets, including popular sets like the NotInject series, BIPIA, Garak, ImprovedLLM, ToxicChat, WildGuard, and our newly introduced JavelinBench, specifically crafted to test generalization on challenging borderline and hard-negative cases. Additionally, we compare our architectures against leading open-source guardrail models as well as large decoder-only LLMs such as gpt-4o, demonstrating superior cost-performance trade-offs in terms of accuracy, and latency. Our findings reveal that while Raudra's multi-task design offers the most robust performance overall, each architecture presents unique trade-offs in speed, interpretability, and resource requirements, guiding practitioners in selecting the optimal balance of complexity and efficiency for real-world LLM security applications.
Malleable software: Restoring user agency in a world of locked-down apps
19 by jessmartin | 0 comments on Hacker News.
19 by jessmartin | 0 comments on Hacker News.
Ask HN: What cool skill or project interests you, but feels out of reach?
16 by akktor | 34 comments on Hacker News.
This question's for all those cool projects or skills you're secretly fascinated by, but haven't quite jumped into. Maybe you feel like you just don't have the right "brain" for it, or you're not smart enough to figure it out, or even worse, you simply have no clue how or where to even start. The idea here is to shine a light on these hidden interests and the little (or big!) mental blocks that come with them. If you're already rocking in those specific areas – or you've been there and figured out how to get past similar hurdles – please chime in! Share some helpful resources, dish out general advice, or just give a nudge of encouragement on how to take that intimidating first step. Let's help each other get unstuck!
16 by akktor | 34 comments on Hacker News.
This question's for all those cool projects or skills you're secretly fascinated by, but haven't quite jumped into. Maybe you feel like you just don't have the right "brain" for it, or you're not smart enough to figure it out, or even worse, you simply have no clue how or where to even start. The idea here is to shine a light on these hidden interests and the little (or big!) mental blocks that come with them. If you're already rocking in those specific areas – or you've been there and figured out how to get past similar hurdles – please chime in! Share some helpful resources, dish out general advice, or just give a nudge of encouragement on how to take that intimidating first step. Let's help each other get unstuck!
Launch HN: Vassar Robotics (YC X25) – $219 robot arm that learns new skills
14 by charleszyong | 3 comments on Hacker News.
Hi HN — I’m Charles from Vassar Robotics. We are bringing an upgraded version of the long beloved SO-101 robot arms to a $219 price point with improved mechanical design and added intelligence. See what it can do here: https://youtube.com/shorts/xNyPKJZI400 (demos are sped up as shown in the video) I’ve spent a few years building RC planes ( https://cyo.ng/hangar/ ) and micro gas turbines ( https://set.mit.edu ), and I’ve always wished hardware were cheaper so more people could experiment. I’m now launching a $219 desktop robot-arm kit that keeps LeRobot SO-101’s kinematics, swaps key parts for sturdier, more precise SLA prints, and adds two integrated 480 p cameras. After plenty of supplier haggling, the whole kit costs less than the twelve servos alone. I’ll release the updated mechanical design under an MIT license by June 30. On the software side, I'll also release an MIT-licensed MCP server by June 30 that exposes the local robot policy as tools for agentic LLMs (Opus 4, o3, etc.) to use in long-horizon tasks. Here's how it works: You can teach the robot new skills through teleoperation. During inference, you simply talk to the agentic LLM using natural language instructions. The LLM then calls the local robot policy through MCP, automatically decomposing your high-level requests into executable robot commands. Thanks to the LeRobot community for making such an amazing robot accessible. If you’ve contributed to the LeRobot GitHub repo, email hello@vassarrobotics.com for a 20% discount coupon as a small thank-you. I’d love your feedback! Beyond manufacturing, cleaning up the codebase, and writing docs, I’m considering: a force-controlled gripper, a parallel-jaw gripper, an extra wrist DOF (matching the new Trossen and ARX arms), full force feedback on the leader arm (though that may triple the price), a more affordable version with lower resolution each joint, and a longer-reach variant. Which of these—or something else—would be most useful to you? Looking forward to any and all comments!
14 by charleszyong | 3 comments on Hacker News.
Hi HN — I’m Charles from Vassar Robotics. We are bringing an upgraded version of the long beloved SO-101 robot arms to a $219 price point with improved mechanical design and added intelligence. See what it can do here: https://youtube.com/shorts/xNyPKJZI400 (demos are sped up as shown in the video) I’ve spent a few years building RC planes ( https://cyo.ng/hangar/ ) and micro gas turbines ( https://set.mit.edu ), and I’ve always wished hardware were cheaper so more people could experiment. I’m now launching a $219 desktop robot-arm kit that keeps LeRobot SO-101’s kinematics, swaps key parts for sturdier, more precise SLA prints, and adds two integrated 480 p cameras. After plenty of supplier haggling, the whole kit costs less than the twelve servos alone. I’ll release the updated mechanical design under an MIT license by June 30. On the software side, I'll also release an MIT-licensed MCP server by June 30 that exposes the local robot policy as tools for agentic LLMs (Opus 4, o3, etc.) to use in long-horizon tasks. Here's how it works: You can teach the robot new skills through teleoperation. During inference, you simply talk to the agentic LLM using natural language instructions. The LLM then calls the local robot policy through MCP, automatically decomposing your high-level requests into executable robot commands. Thanks to the LeRobot community for making such an amazing robot accessible. If you’ve contributed to the LeRobot GitHub repo, email hello@vassarrobotics.com for a 20% discount coupon as a small thank-you. I’d love your feedback! Beyond manufacturing, cleaning up the codebase, and writing docs, I’m considering: a force-controlled gripper, a parallel-jaw gripper, an extra wrist DOF (matching the new Trossen and ARX arms), full force feedback on the leader arm (though that may triple the price), a more affordable version with lower resolution each joint, and a longer-reach variant. Which of these—or something else—would be most useful to you? Looking forward to any and all comments!
You Can Drive but Not Hide: Detection of Hidden Cellular GPS Vehicle Trackers
14 by gnabgib | 1 comments on Hacker News.
14 by gnabgib | 1 comments on Hacker News.
Another Crack in the Chain of Trust: Uncovering (Yet Another) Secure Boot Bypass
4 by vitplister | 0 comments on Hacker News.
4 by vitplister | 0 comments on Hacker News.