Ford Has Steered Its Former EV Truck and Plant Plans in to a Ditch
21 by zdw | 25 comments on Hacker News.
Humans Times
Be Upto date with Per hour news with Humanstimes
Wednesday, December 17, 2025
Tuesday, December 16, 2025
New top story on Hacker News: Show HN: Zenflow – orchestrate coding agents without "you're right" loops
Show HN: Zenflow – orchestrate coding agents without "you're right" loops
10 by andrewsthoughts | 4 comments on Hacker News.
Hi HN, I’m Andrew, Founder of Zencoder. While building our IDE extensions and cloud agents, we ran into the same issue many of you likely face when using coding agents in complex repos: agents getting stuck in loops, apologizing, and wasting time. We tried to manage this with scripts, but juggling terminal windows and copy-paste prompting was painful. So we built Zenflow, a free desktop tool to orchestrate AI coding workflows. It handles the things we were missing in standard chat interfaces: Cross-Model Verification: You can have Codex review Claude’s code, or run them in parallel to see which model handles the specific context better. Parallel Execution: Run five different approaches on a backlog item simultaneously—mix "Human-in-the-Loop" for hard problems with "YOLO" runs for simple tasks. Dynamic Workflows: Configured via simple .md files. Agents can actually "rewire" the next steps of the workflow dynamically based on the problem at hand. Project list/kanban views across all workload What we learned building this To tune Zenflow, we ran 100+ experiments across public benchmarks (SWE-Bench-*, T-Bench) and private datasets. Two major takeaways that might interest this community: Benchmark Saturation: Models are becoming progressively overtrained on all versions of SWE-Bench (even Pro). We found public results are diverging significantly from performance on private datasets. If you are building workflows, you can't rely on public benches. The "Goldilocks" Workflow: In autonomous mode, heavy multi-step processes often multiply errors rather than fix them. Massive, complex prompt templates look good on paper but fail in practice. The most reliable setups landed in a narrow “Goldilocks” zone of just enough structure without over-orchestration. The app is free to use and supports Claude Code, Codex, Gemini, and Zencoder. We’ve been dogfooding this heavily, but I'd love to hear your thoughts on the default workflows and if they fit your mental model for agentic coding. Download: https://ift.tt/mbKaw03 YT flyby: https://www.youtube.com/watch?v=67Ai-klT-B8
10 by andrewsthoughts | 4 comments on Hacker News.
Hi HN, I’m Andrew, Founder of Zencoder. While building our IDE extensions and cloud agents, we ran into the same issue many of you likely face when using coding agents in complex repos: agents getting stuck in loops, apologizing, and wasting time. We tried to manage this with scripts, but juggling terminal windows and copy-paste prompting was painful. So we built Zenflow, a free desktop tool to orchestrate AI coding workflows. It handles the things we were missing in standard chat interfaces: Cross-Model Verification: You can have Codex review Claude’s code, or run them in parallel to see which model handles the specific context better. Parallel Execution: Run five different approaches on a backlog item simultaneously—mix "Human-in-the-Loop" for hard problems with "YOLO" runs for simple tasks. Dynamic Workflows: Configured via simple .md files. Agents can actually "rewire" the next steps of the workflow dynamically based on the problem at hand. Project list/kanban views across all workload What we learned building this To tune Zenflow, we ran 100+ experiments across public benchmarks (SWE-Bench-*, T-Bench) and private datasets. Two major takeaways that might interest this community: Benchmark Saturation: Models are becoming progressively overtrained on all versions of SWE-Bench (even Pro). We found public results are diverging significantly from performance on private datasets. If you are building workflows, you can't rely on public benches. The "Goldilocks" Workflow: In autonomous mode, heavy multi-step processes often multiply errors rather than fix them. Massive, complex prompt templates look good on paper but fail in practice. The most reliable setups landed in a narrow “Goldilocks” zone of just enough structure without over-orchestration. The app is free to use and supports Claude Code, Codex, Gemini, and Zencoder. We’ve been dogfooding this heavily, but I'd love to hear your thoughts on the default workflows and if they fit your mental model for agentic coding. Download: https://ift.tt/mbKaw03 YT flyby: https://www.youtube.com/watch?v=67Ai-klT-B8
Monday, December 15, 2025
New top story on Hacker News: Show HN: A pager
Show HN: A pager
38 by keepamovin | 22 comments on Hacker News.
Hello HN, I basically don't use notifications for anything. The noise is too much. Slack is too loud. Email is too slow. But sometimes you do need a note in your face. I found myself missing 1990s pagers. I wanted a digital equivalent - something that does one thing: beep until I ack it. So I built UDP-7777. Concept: - 0% Cloud: It listens on UDP Port 7777. No accounts, no central servers. You don't need Tailscale/ZeroTier/WG/etc, it's just easy for device sets. - CAPCODES: It maps your IP address (LAN or Tailscale) to a retro 10-digit "CAPCODE" that looks like a phone number (e.g., (213) 070-6433 for loopback). - Minimalism: Bare-bones interface. Just a box, a few buttons, and a big red blinker. The Tech: It's a single binary written in Go (using Fyne). It implements "burst fire" UDP (sending packets 3x) to ensure delivery without the handshake overhead of TCP. New in v2.2.7: - Frequency Tuning: Bind specifically to your Tailscale/ZeroTier interface. - Squelch: Optional shared-secret keys to ignore unauthorized packets. - Heartbeat: Visual/Audio alerts that persist until you physically click ACK. I built this for anyone looking to cut through the noise—DevOps teams handing off the "on-call IP", or deep-work focus where you only want interruptions from a high-trust circle. I'd love to hear your thoughts on the IP-to-Phone-Number mapping logic (it's purely visual, but I'm really into it). Site & Binaries (Signed for Mac/Win): https://udp7777.com
38 by keepamovin | 22 comments on Hacker News.
Hello HN, I basically don't use notifications for anything. The noise is too much. Slack is too loud. Email is too slow. But sometimes you do need a note in your face. I found myself missing 1990s pagers. I wanted a digital equivalent - something that does one thing: beep until I ack it. So I built UDP-7777. Concept: - 0% Cloud: It listens on UDP Port 7777. No accounts, no central servers. You don't need Tailscale/ZeroTier/WG/etc, it's just easy for device sets. - CAPCODES: It maps your IP address (LAN or Tailscale) to a retro 10-digit "CAPCODE" that looks like a phone number (e.g., (213) 070-6433 for loopback). - Minimalism: Bare-bones interface. Just a box, a few buttons, and a big red blinker. The Tech: It's a single binary written in Go (using Fyne). It implements "burst fire" UDP (sending packets 3x) to ensure delivery without the handshake overhead of TCP. New in v2.2.7: - Frequency Tuning: Bind specifically to your Tailscale/ZeroTier interface. - Squelch: Optional shared-secret keys to ignore unauthorized packets. - Heartbeat: Visual/Audio alerts that persist until you physically click ACK. I built this for anyone looking to cut through the noise—DevOps teams handing off the "on-call IP", or deep-work focus where you only want interruptions from a high-trust circle. I'd love to hear your thoughts on the IP-to-Phone-Number mapping logic (it's purely visual, but I'm really into it). Site & Binaries (Signed for Mac/Win): https://udp7777.com
Subscribe to:
Comments (Atom)