Busting the Myth That the Canadian Federal Govt Has Hurt Alberta's Oil Industry
6 by Geekette | 3 comments on Hacker News.
6 by Geekette | 3 comments on Hacker News.
AI Weather Model Is More Accurate, Less Expensive Than Traditional Forecasting
3 by rmason | 0 comments on Hacker News.
3 by rmason | 0 comments on Hacker News.
SkyRoof: New Ham Satellite Tracking and SDR Receiver Software
4 by rmason | 0 comments on Hacker News.
4 by rmason | 0 comments on Hacker News.
Converge (YC S23) Well-capitalized New York startup seeks product developers
1 by thomashlvt | 0 comments on Hacker News.
1 by thomashlvt | 0 comments on Hacker News.
APL Interpreter – An implementation of APL, written in Haskell
1 by ofalkaed | 0 comments on Hacker News.
1 by ofalkaed | 0 comments on Hacker News.
Show HN: Grab a Random ArXiv Paper
7 by jegp | 0 comments on Hacker News.
I needed a way to grab a random paper from arXiv, so I built one and wanted to share it with you. It 1) picks a random topic (of all the cs. , econ. , math.* etc. topics)2) finds the maximum amount of papers in that topic, and 3) queries for a random paper in that topic. Note that this skews the distribution heavily in favor of topics that are less common, but it should get the job done.Suggestions for improvements are welcome.
7 by jegp | 0 comments on Hacker News.
I needed a way to grab a random paper from arXiv, so I built one and wanted to share it with you. It 1) picks a random topic (of all the cs. , econ. , math.* etc. topics)2) finds the maximum amount of papers in that topic, and 3) queries for a random paper in that topic. Note that this skews the distribution heavily in favor of topics that are less common, but it should get the job done.Suggestions for improvements are welcome.
Myanmar's chinlone ball sport threatened by conflict and rattan shortages
6 by YeGoblynQueenne | 0 comments on Hacker News.
6 by YeGoblynQueenne | 0 comments on Hacker News.
Tokasaurus: An LLM Inference Engine for High-Throughput Workloads
28 by rsehrlich | 1 comments on Hacker News.
28 by rsehrlich | 1 comments on Hacker News.
Show HN: String Flux – Simplify everyday string transformations for developers
6 by eaglepeak | 1 comments on Hacker News.
I built https://stringflux.io/ to make everyday string transformations a little less painful. It’s similar to CyberChef in the sense that it supports multiple string operations, but with a cleaner, more focused UI and smart suggestions based on your input. You can also chain transformations — for example: decode base64 string which was base64 encoded from minified json → then json format (pretty-print) it — all in one flow. This is helpful when dealing with complex or nested strings, like encoded API responses or log data, where you need to apply multiple steps to make the content readable. The idea came from the frustration of jumping between different tools just to handle common string tasks. There’s a short GIF demo in the GitHub README: https://ift.tt/AovKVIB Would love to hear your thoughts and feedback!
6 by eaglepeak | 1 comments on Hacker News.
I built https://stringflux.io/ to make everyday string transformations a little less painful. It’s similar to CyberChef in the sense that it supports multiple string operations, but with a cleaner, more focused UI and smart suggestions based on your input. You can also chain transformations — for example: decode base64 string which was base64 encoded from minified json → then json format (pretty-print) it — all in one flow. This is helpful when dealing with complex or nested strings, like encoded API responses or log data, where you need to apply multiple steps to make the content readable. The idea came from the frustration of jumping between different tools just to handle common string tasks. There’s a short GIF demo in the GitHub README: https://ift.tt/AovKVIB Would love to hear your thoughts and feedback!
Show HN: Claude Composer
11 by mikebannister | 7 comments on Hacker News.
Central feature is a something like "yolo mode" but with fine grained controls over how yolo you're feeling. Also makes it easy to use "presets" of tools and permissions. Let me know if you have any questions and feel free to contact me on X at https://ift.tt/LziB2l9
11 by mikebannister | 7 comments on Hacker News.
Central feature is a something like "yolo mode" but with fine grained controls over how yolo you're feeling. Also makes it easy to use "presets" of tools and permissions. Let me know if you have any questions and feel free to contact me on X at https://ift.tt/LziB2l9
Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
16 by echollama | 5 comments on Hacker News.
While building my startup i kept running into the issue where ai agents in cursor create endpoints or code that shouldn't exist, hallucinates strings, or just don't understand the code. ask-human-mcp pauses your agent whenever it’s stuck, logs a question into ask_human.md in your root directory with answer: PENDING, and then resumes as soon as you fill in the correct answer. the pain: your agent screams out an endpoint that never existedit makes confident assumptions and you spend hours debugging false leads the fix: ask-human-mcp gives your agent an escape hatch. when it’s unsure, it calls ask_human(), writes a question into ask_human.md, and waits. you swap answer: PENDING for the real answer and it keeps going. some features: - zero config: pip install ask-human-mcp + one line in .cursor/mcp.json → boom, you’re live- cross-platform: works on macOS, Linux, and Windows—no extra servers or webhooks.- markdown Q\&A: agent calls await ask_human(), question lands in ask_human.md with answer: PENDING. you write the answer, agent picks back up- file locking & rotation: prevents corrupt files, limits pending questions, auto-rotates when ask_human.md hits ~50 MB the quickstart pip install ask-human-mcpask-human-mcp --help add to .cursor/mcp.json and restart:{ "mcpServers": { "ask-human": { "command": "ask-human-mcp" } }} now any call like: answer = await ask_human( "which auth endpoint do we use?", "building login form in auth.js") creates: ### Q8c4f1e2ats: 2025-01-15 14:30q: which auth endpoint do we use?ctx: building login form in auth.jsanswer: PENDING just replace answer: PENDING with the real endpoint (e.g., `POST /api/v2/auth/login`) and your agent continues. link: github -> https://ift.tt/cD3VGsL feedback: I'm Mason a 19yo solo-founder at Kallro. Happy to hear any bugs, feature requests, or weird edge cases you uncover - drop a comment or open an issue!buy me a coffee -> coff.ee/masonyarbrough
16 by echollama | 5 comments on Hacker News.
While building my startup i kept running into the issue where ai agents in cursor create endpoints or code that shouldn't exist, hallucinates strings, or just don't understand the code. ask-human-mcp pauses your agent whenever it’s stuck, logs a question into ask_human.md in your root directory with answer: PENDING, and then resumes as soon as you fill in the correct answer. the pain: your agent screams out an endpoint that never existedit makes confident assumptions and you spend hours debugging false leads the fix: ask-human-mcp gives your agent an escape hatch. when it’s unsure, it calls ask_human(), writes a question into ask_human.md, and waits. you swap answer: PENDING for the real answer and it keeps going. some features: - zero config: pip install ask-human-mcp + one line in .cursor/mcp.json → boom, you’re live- cross-platform: works on macOS, Linux, and Windows—no extra servers or webhooks.- markdown Q\&A: agent calls await ask_human(), question lands in ask_human.md with answer: PENDING. you write the answer, agent picks back up- file locking & rotation: prevents corrupt files, limits pending questions, auto-rotates when ask_human.md hits ~50 MB the quickstart pip install ask-human-mcpask-human-mcp --help add to .cursor/mcp.json and restart:{ "mcpServers": { "ask-human": { "command": "ask-human-mcp" } }} now any call like: answer = await ask_human( "which auth endpoint do we use?", "building login form in auth.js") creates: ### Q8c4f1e2ats: 2025-01-15 14:30q: which auth endpoint do we use?ctx: building login form in auth.jsanswer: PENDING just replace answer: PENDING with the real endpoint (e.g., `POST /api/v2/auth/login`) and your agent continues. link: github -> https://ift.tt/cD3VGsL feedback: I'm Mason a 19yo solo-founder at Kallro. Happy to hear any bugs, feature requests, or weird edge cases you uncover - drop a comment or open an issue!buy me a coffee -> coff.ee/masonyarbrough