The best Hacker News stories from Show from the past day

from

All Show

from the past*

day week month

with these search terms:

Create follow Go back

Latest posts:

Show HN: Open-sourcing our text-to-CAD app

Hey HN! I'm Zach from Adam (<a href="https://adam.new/">https://adam.new/</a>). We’re building an AI co-pilot for mechanical CAD software.<p>As part of our broader research, we built a browser-based Text-to-CAD app (<a href="https://news.ycombinator.com/item?id=44182206">https://news.ycombinator.com/item?id=44182206</a>) and are now open sourcing it. This is a React SPA with a Supabase backend.<p>What it does:<p>* Generates parametric 3D models from natural language descriptions, with support for both text prompts and image references<p>* Outputs OpenSCAD code with automatically extracted parameters that surface as interactive sliders for instant dimension tweaking<p>* Exports as .STL or .SCAD<p>Under the hood:<p>* Separate agents for conversation and code generation; simple parameter tweaks bypass AI entirely using deterministic regex-based updates<p>* Runs fully in-browser by compiling OpenSCAD to WebAssembly and integrating Three.js with React Three Fiber for 3D rendering<p>* Supports BOSL, BOSL2, MCAD libraries and custom font support (Geist) for text in models<p>We’ve seen many developers trying to replicate this kind of functionality, so we’re releasing this to give the community a solid foundation to build on.<p>Future improvements:<p>* Expand geometry support - Move beyond CSG primitives to support curved surfaces, fillets, lofts, and constraint-driven modeling through CadQuery/Build123D<p>* Better spatial context - UI for face/edge selection and viewport image integration to give LLMs spatial understanding<p>* Enhanced capabilities - RAG on documentation and integration with more OpenSCAD libraries for features like proper threading<p>You can clone the repo and run it locally! Contributions are welcome, and we’ll keep merging PRs as they come in.

Show HN: Swimming in Tech Debt

This is the first half of my book, “Swimming in Tech Debt”. It is available at a pre-launch sale price of $0.99 (<a href="https://loufranco.com/tech-debt-book" rel="nofollow">https://loufranco.com/tech-debt-book</a>).<p>I have been working on it since January 2024. It is based on some posts in my blog, but expands on my ideas quite a bit.<p>In September 2024, excerpts appeared in Gergely Orosz’s Pragmatic Engineer newsletter, which helped me get a lot of feedback that expanded the book from my initial idea. This half is about what I expected to do before that —- the rest of the book goes into team and CTO practices.

Show HN: Swimming in Tech Debt

This is the first half of my book, “Swimming in Tech Debt”. It is available at a pre-launch sale price of $0.99 (<a href="https://loufranco.com/tech-debt-book" rel="nofollow">https://loufranco.com/tech-debt-book</a>).<p>I have been working on it since January 2024. It is based on some posts in my blog, but expands on my ideas quite a bit.<p>In September 2024, excerpts appeared in Gergely Orosz’s Pragmatic Engineer newsletter, which helped me get a lot of feedback that expanded the book from my initial idea. This half is about what I expected to do before that —- the rest of the book goes into team and CTO practices.

Show HN: Swimming in Tech Debt

This is the first half of my book, “Swimming in Tech Debt”. It is available at a pre-launch sale price of $0.99 (<a href="https://loufranco.com/tech-debt-book" rel="nofollow">https://loufranco.com/tech-debt-book</a>).<p>I have been working on it since January 2024. It is based on some posts in my blog, but expands on my ideas quite a bit.<p>In September 2024, excerpts appeared in Gergely Orosz’s Pragmatic Engineer newsletter, which helped me get a lot of feedback that expanded the book from my initial idea. This half is about what I expected to do before that —- the rest of the book goes into team and CTO practices.

Show HN: Swimming in Tech Debt

This is the first half of my book, “Swimming in Tech Debt”. It is available at a pre-launch sale price of $0.99 (<a href="https://loufranco.com/tech-debt-book" rel="nofollow">https://loufranco.com/tech-debt-book</a>).<p>I have been working on it since January 2024. It is based on some posts in my blog, but expands on my ideas quite a bit.<p>In September 2024, excerpts appeared in Gergely Orosz’s Pragmatic Engineer newsletter, which helped me get a lot of feedback that expanded the book from my initial idea. This half is about what I expected to do before that —- the rest of the book goes into team and CTO practices.

Show HN: Shimmy – 5MB privacy-first, local alternative to Ollama (680MB)

Show HN: I built FlipCards – a flashcard app with variations to improve learning

Hi HN, I’m Felipe, a 9-5 developer aiming to become a full-time indie hacker. I struggled with flashcard apps that focus on decorating cards instead of learning concepts, so I built FlipCards to solve that problem.<p>What it does: FlipCards lets you:<p>- Create cards for any concept (math, language, coding, etc.) - Add multiple variations per card – the more variations, the better your understanding - Study smarter – the algorithm randomly selects variations so you can’t just memorize Q→A patterns<p>Why it’s different:<p>- Most apps use reverse cards (Q→A, A→Q). FlipCards uses variations to reinforce concepts in multiple contexts. - Powered by the SM2 spaced repetition algorithm, scientifically proven for long-term retention.<p>Pricing:<p>- Free – 1 deck, 3 cards, 1 study session - Annual – $20/year for unlimited decks and cards - Lifetime – $50 one-time for unlimited everything<p>I built FlipCards because I kept getting stuck decorating cards in other apps. Now I can create as many variations as I want, and the algorithm mixes them for me.<p>I’d love feedback from the HN community:<p>- Does this approach to flashcards make sense? - Would you use an app like this for learning?<p>Try it here: <a href="https://flipcardsapp.vercel.app" rel="nofollow">https://flipcardsapp.vercel.app</a><p>Thanks, Felipe

Show HN: I built FlipCards – a flashcard app with variations to improve learning

Hi HN, I’m Felipe, a 9-5 developer aiming to become a full-time indie hacker. I struggled with flashcard apps that focus on decorating cards instead of learning concepts, so I built FlipCards to solve that problem.<p>What it does: FlipCards lets you:<p>- Create cards for any concept (math, language, coding, etc.) - Add multiple variations per card – the more variations, the better your understanding - Study smarter – the algorithm randomly selects variations so you can’t just memorize Q→A patterns<p>Why it’s different:<p>- Most apps use reverse cards (Q→A, A→Q). FlipCards uses variations to reinforce concepts in multiple contexts. - Powered by the SM2 spaced repetition algorithm, scientifically proven for long-term retention.<p>Pricing:<p>- Free – 1 deck, 3 cards, 1 study session - Annual – $20/year for unlimited decks and cards - Lifetime – $50 one-time for unlimited everything<p>I built FlipCards because I kept getting stuck decorating cards in other apps. Now I can create as many variations as I want, and the algorithm mixes them for me.<p>I’d love feedback from the HN community:<p>- Does this approach to flashcards make sense? - Would you use an app like this for learning?<p>Try it here: <a href="https://flipcardsapp.vercel.app" rel="nofollow">https://flipcardsapp.vercel.app</a><p>Thanks, Felipe

Show HN: A Map of All YC Companies (5,300 Startups by Batch and Location)

Show HN: A Map of All YC Companies (5,300 Startups by Batch and Location)

Show HN: A roguelike game that runs inside Notepad++

Show HN: A roguelike game that runs inside Notepad++

Show HN: A roguelike game that runs inside Notepad++

Show HN: Chibi, AI that tells you why users churn

Hey HN,<p>I’ve been a PM for 3 years, and one hard part was always understanding why users churn, drop off and behave the way they do!<p>Session replays had the answer, but watching hours of them was painful.<p>I chatted with a bunch of founder friends and PMs and they too had similar troubles.<p>So I built Chibi an AI that watches replays and tells you what’s broken, confusing, or causing drop-off.<p>Long Term: I'm thinking if Chibi could evolve into an AI product manager co-worker that can detect and prioritize issues, think through features and even run A/B tests.<p>Tech Stack: Elixir + Phoenix, rrweb and gemini<p>Would love to know what you think :)<p>Happy to answer any questions too

Show HN: Chibi, AI that tells you why users churn

Hey HN,<p>I’ve been a PM for 3 years, and one hard part was always understanding why users churn, drop off and behave the way they do!<p>Session replays had the answer, but watching hours of them was painful.<p>I chatted with a bunch of founder friends and PMs and they too had similar troubles.<p>So I built Chibi an AI that watches replays and tells you what’s broken, confusing, or causing drop-off.<p>Long Term: I'm thinking if Chibi could evolve into an AI product manager co-worker that can detect and prioritize issues, think through features and even run A/B tests.<p>Tech Stack: Elixir + Phoenix, rrweb and gemini<p>Would love to know what you think :)<p>Happy to answer any questions too

Show HN: Entropy-Guided Loop – How to make small models reason

TLDR: A small, vendor-agnostic inference loop that turns token logprobs/perplexity/entropy into an extra pass and reasoning for LLMs.<p>- Captures logprobs/top-k during generation, computes perplexity and token-level entropy.<p>- Triggers at most one refine when simple thresholds fire; passes a compact “uncertainty report” (uncertain tokens + top-k alts + local context) back to the model.<p>- In our tests on technical Q&A / math / code, a small model recovered much of “reasoning” quality at ~⅓ the cost while refining ~⅓ of outputs.<p>I kept seeing “reasoning” models behave like expensive black boxes. Meanwhile, standard inference already computes useful signals both before softmax normalization and after it(logprobs), which we usually throw away. This loop tries the simplest thing that you could think of: use those signals to decide when (and where) to think again.<p>GitHub (notebook + minimal code): <a href="https://github.com/monostate/weave-logprobs-reasoning-loop" rel="nofollow">https://github.com/monostate/weave-logprobs-reasoning-loop</a><p>Paper (short & engineer made): <a href="https://arxiv.org/abs/2509.00079" rel="nofollow">https://arxiv.org/abs/2509.00079</a><p>Blog (more context): <a href="https://monostate.ai/blog/entropy-refinement-blog" rel="nofollow">https://monostate.ai/blog/entropy-refinement-blog</a><p>Requirements: Python, API that exposes logprobs (tested with OpenAI non reasoning 4.1). OPENAI_API_KEY and WEAVE for observability. Run the notebook; it prints metrics and shows which tokens triggered refinement.<p>- Python, simple loop (no retraining).<p>- Uses Responses API logprobs/top-k; metrics: perplexity, max token entropy, low-confidence counts.<p>- Weave for lightweight logging/observability (optional).<p>- Passing alternatives (not just “this looks uncertain”) prevents over-correction.<p>- A simple OR rule (ppl / max-entropy / low-confidence count) catches complementary failure modes.<p>- Numbers drift across vendors; keeping the method vendor-agnostic is better than chasing fragile pairings.<p>- Needs APIs that expose logprobs/top-k.<p>- Results are indicative—not a leaderboard; focus is on within-model gains (single-pass vs +loop).<p>- Thresholds might need light tuning per domain.<p>- One pass only; not a chain-of-thought replacement.<p>- Run it on your models and ideas (e.g., 4o-mini, v3, Llama variants with logprobs) and share logs in a PR for our README in GitHub if you'd like, PRs welcome - I’ll credit and link.<p>Overall let me know if you find making small models reason like this useful!

Show HN: Entropy-Guided Loop – How to make small models reason

TLDR: A small, vendor-agnostic inference loop that turns token logprobs/perplexity/entropy into an extra pass and reasoning for LLMs.<p>- Captures logprobs/top-k during generation, computes perplexity and token-level entropy.<p>- Triggers at most one refine when simple thresholds fire; passes a compact “uncertainty report” (uncertain tokens + top-k alts + local context) back to the model.<p>- In our tests on technical Q&A / math / code, a small model recovered much of “reasoning” quality at ~⅓ the cost while refining ~⅓ of outputs.<p>I kept seeing “reasoning” models behave like expensive black boxes. Meanwhile, standard inference already computes useful signals both before softmax normalization and after it(logprobs), which we usually throw away. This loop tries the simplest thing that you could think of: use those signals to decide when (and where) to think again.<p>GitHub (notebook + minimal code): <a href="https://github.com/monostate/weave-logprobs-reasoning-loop" rel="nofollow">https://github.com/monostate/weave-logprobs-reasoning-loop</a><p>Paper (short & engineer made): <a href="https://arxiv.org/abs/2509.00079" rel="nofollow">https://arxiv.org/abs/2509.00079</a><p>Blog (more context): <a href="https://monostate.ai/blog/entropy-refinement-blog" rel="nofollow">https://monostate.ai/blog/entropy-refinement-blog</a><p>Requirements: Python, API that exposes logprobs (tested with OpenAI non reasoning 4.1). OPENAI_API_KEY and WEAVE for observability. Run the notebook; it prints metrics and shows which tokens triggered refinement.<p>- Python, simple loop (no retraining).<p>- Uses Responses API logprobs/top-k; metrics: perplexity, max token entropy, low-confidence counts.<p>- Weave for lightweight logging/observability (optional).<p>- Passing alternatives (not just “this looks uncertain”) prevents over-correction.<p>- A simple OR rule (ppl / max-entropy / low-confidence count) catches complementary failure modes.<p>- Numbers drift across vendors; keeping the method vendor-agnostic is better than chasing fragile pairings.<p>- Needs APIs that expose logprobs/top-k.<p>- Results are indicative—not a leaderboard; focus is on within-model gains (single-pass vs +loop).<p>- Thresholds might need light tuning per domain.<p>- One pass only; not a chain-of-thought replacement.<p>- Run it on your models and ideas (e.g., 4o-mini, v3, Llama variants with logprobs) and share logs in a PR for our README in GitHub if you'd like, PRs welcome - I’ll credit and link.<p>Overall let me know if you find making small models reason like this useful!

Show HN: Entropy-Guided Loop – How to make small models reason

TLDR: A small, vendor-agnostic inference loop that turns token logprobs/perplexity/entropy into an extra pass and reasoning for LLMs.<p>- Captures logprobs/top-k during generation, computes perplexity and token-level entropy.<p>- Triggers at most one refine when simple thresholds fire; passes a compact “uncertainty report” (uncertain tokens + top-k alts + local context) back to the model.<p>- In our tests on technical Q&A / math / code, a small model recovered much of “reasoning” quality at ~⅓ the cost while refining ~⅓ of outputs.<p>I kept seeing “reasoning” models behave like expensive black boxes. Meanwhile, standard inference already computes useful signals both before softmax normalization and after it(logprobs), which we usually throw away. This loop tries the simplest thing that you could think of: use those signals to decide when (and where) to think again.<p>GitHub (notebook + minimal code): <a href="https://github.com/monostate/weave-logprobs-reasoning-loop" rel="nofollow">https://github.com/monostate/weave-logprobs-reasoning-loop</a><p>Paper (short & engineer made): <a href="https://arxiv.org/abs/2509.00079" rel="nofollow">https://arxiv.org/abs/2509.00079</a><p>Blog (more context): <a href="https://monostate.ai/blog/entropy-refinement-blog" rel="nofollow">https://monostate.ai/blog/entropy-refinement-blog</a><p>Requirements: Python, API that exposes logprobs (tested with OpenAI non reasoning 4.1). OPENAI_API_KEY and WEAVE for observability. Run the notebook; it prints metrics and shows which tokens triggered refinement.<p>- Python, simple loop (no retraining).<p>- Uses Responses API logprobs/top-k; metrics: perplexity, max token entropy, low-confidence counts.<p>- Weave for lightweight logging/observability (optional).<p>- Passing alternatives (not just “this looks uncertain”) prevents over-correction.<p>- A simple OR rule (ppl / max-entropy / low-confidence count) catches complementary failure modes.<p>- Numbers drift across vendors; keeping the method vendor-agnostic is better than chasing fragile pairings.<p>- Needs APIs that expose logprobs/top-k.<p>- Results are indicative—not a leaderboard; focus is on within-model gains (single-pass vs +loop).<p>- Thresholds might need light tuning per domain.<p>- One pass only; not a chain-of-thought replacement.<p>- Run it on your models and ideas (e.g., 4o-mini, v3, Llama variants with logprobs) and share logs in a PR for our README in GitHub if you'd like, PRs welcome - I’ll credit and link.<p>Overall let me know if you find making small models reason like this useful!

Show HN: We built an open-source alternative to expensive pair programming apps

My friend and I grew frustrated with the high cost of existing pair programming tools, and of course of grainy screens when we used Huddle or similar tools.<p>We believe core developer collaboration shouldn't be locked behind an expensive subscription.<p>So for the past year we spent our nights and weekend building Hopp, an open-source alternative.<p>We would love your feedback and we are here to answer any and all questions.

Show HN: We built an open-source alternative to expensive pair programming apps

My friend and I grew frustrated with the high cost of existing pair programming tools, and of course of grainy screens when we used Huddle or similar tools.<p>We believe core developer collaboration shouldn't be locked behind an expensive subscription.<p>So for the past year we spent our nights and weekend building Hopp, an open-source alternative.<p>We would love your feedback and we are here to answer any and all questions.