Show HN: Open Jev Playground – try all the open source alternatives to Jev https://ift.tt/U9jDaY5 September 23, 2026 at 11:35PM
Hacker News लेबलों वाले संदेश दिखाए जा रहे हैं. सभी संदेश दिखाएं
Hacker News लेबलों वाले संदेश दिखाए जा रहे हैं. सभी संदेश दिखाएं
Show HN: Conway's Game of Life in boot sector Hello HN! On these weekends, I was sitting and thinking about where our industry is going, and how fun it was earlier, when we wrote more code than chat messages. The thoughts quickly turned into a wish to build something like we did earlier. In my case, it ended up as something much "earlier" than I had in mind initially... So, Conway's Game of Life running from a 512-byte x86 boot sector. Maybe you will find it interesting. I tried to comment the code as much as possible, which might be especially useful if you are learning assembly. Have fun! https://ift.tt/IOm2Mpk September 21, 2026 at 11:58PM
Show HN: I built a post-mortem debugger for native Windows x64/x86 crashes Hello HN! I've spent years debugging Windows crashes with tools that were either friendly but limited (e.g. Visual Studio) or powerful but archaic (e.g. WinDbg). I developed patterns and methods for understanding what was going on, and decided to build it into a much more effective debugging tool called ForensicDbg. I built a modern interface to minimize the friction when debugging. All of the data shown to you is analyzed, interpreted, and presented to you clearly, so you can focus on what matters. Everything is interlinked so you can quickly and intuitivly navigate through the process space. ForensicDbg comes with an MCP server which allows for agenic debugging. The work done to interpret and interlink your data also benefits AI tools. It removes the risk of hallucinations while building a stable foundation for them to work from without spending tokens. If you want to try it out you can sign up and get a free beta license here: https://ift.tt/myRCe7Z https://ift.tt/Rmf4BsT September 24, 2026 at 12:45AM
Show HN: JevBench, a reproducible benchmark for typed decision models Hi HN! I built JevBench because Jev kicks ass, and the world deserves to know how the serious open source and fake lookalike projects really perform in comparison. Jev-class models return bounded choices and probabilities instead of text, and are disruptively faster and cheaper than LLMs, while being similarly intelligent on the text input they operate on. JevBench allows looking at accuracy, latency and price all at once, in a weighted way - you can even configure the weighting. A full run asks 534 English decisions. The v1.3 score combines chance-corrected Intelligence, Calibration, Speed and Cost. Leaderboard right now: #1 - Jev 74.4
#2 - SemIf 73.1
#3 - djev 73.0
#4 - Winnow-12B Q8 71.2
#5 reflex 4B 70.3.
MIT harness, public items, frozen artifacts, scoring code and public per-task outcomes: https://ift.tt/mRt9x6E Two no-signup demos: https://ift.tt/WRthPiX https://ift.tt/U2v5oh3 Limitations: English-only; latency from one German server; local/demo latency gets a disclosed ×2 adjustment (+150 ms on my servers) which is an informed assumption; held-out prompts still reach evaluated services; ~1-point gaps can be noise. Wdyt? https://ift.tt/7BKDOZj September 22, 2026 at 06:31PM
Show HN: Combinators in Array Languages Raymond Smullyan’s "To Mock a Mockingbird" book's aviary of combinator birds implemented in APL-derived languages and the problem implementing the Sage bird (Fixed Point or Y combinator) in an eagerly evaluated language. Newer APLs support lazy evaluation. My eager language has a workaround for this. The Z combinator is the standard strict-language fix: wrap the self-application in one extra function layer (λv. x x v), so the recursion is a value (a delayed call) rather than an executing expression. sw-MLPL expresses that delay as a named partial — z_step/z_recur/applicative_sage — because the language has no anonymous lambdas. Z has no Smullyan name (and no zebra in the aviary, despite the letter). The book predates and ignores the strictness problem, so it has no applicative-order variant. "Z combinator" is programmer folklore for the eta-expanded Y https://ift.tt/DPjpNor September 21, 2026 at 11:33PM
Show HN: CUA-S1 – A System One Model for Computer Use Hello HN! We're Dillon and Francesco from Cua. We were wondering how many computer use tasks actually need a full general purpose LLM (e.g. gpt-6-astra, claude-opus-5 etc.) to think through all their decisions and steps. Some tasks require thinking about a plan, exploring different paths, recovering from failure. Other tasks are a question of making local decisions, like this value should go in this box, or should I check this box, or this element should be ignored. We wondered how far we could go with a small model trained to only make these kinds of decisions. Our inspiration was Typesafe's Jev and its System One Model framing. This is a nod to the dichotomy between thinking quickly, automatically, and intuitively (system 1) vs. thinking slowly, analytically (system 2), as described by Daniel Kahneman. The interesting question for us was: what happens if you give a model an interface of current context, and a set of possible choices, and you ask it to return a probability for each choice? This kind of model does not generate output token by token like most LLMs do, but rather scores the options you give it, which you can check, trust, and use to drive your app's behavior. CUA-S1 is our answer for narrow, specialized decision models for computer use. Our first release is CUA-S1-FORMS. We built this from ideas and code in jevlike, and then trained a second model just to handle form interactions. It has 706k parameters, and the original checkpoint is 2.8 MB. The first training iteration took less than 30 minutes on synthetic data. Given a set of structured elements and values extracted from a document, it predicts whether to use the given value, CHECK, CLICK, or SKIP for each element. It does not predict new values for text fields, and does not consider screenshots. Element decisions are scored together, and your code can order the actions, and Cua Driver will execute them one at a time. A first evaluation of this specialist vs. hosted Jev on our form task: - For the whole decision set: 99.7% correct vs 83.6%. - For the subset of steps that require an action: 100% correct vs 96%. - For the subset of steps that are just leaving already-filled fields alone: 100% correct vs 74%. The specialist was trained specifically for this task and convention (just press skip for already filled boxes), while hosted Jev has not been fine-tuned for it, so this is an experiment in scoped specialization. We measured 7-9 ms to score a form locally vs. 260-280 ms per call to hosted Jev including network latency, though those samples measure different things and are not end-to-end form completion times. Our interest here is in the space between a brittle script and a general agent loop. The content and layout of form fields vary enough that scripts get unwieldy, but the set of available decisions can remain narrow and well scoped. We want to explore the possibility of a general agent encountering something novel, and passing well understood decisions over to specialists like this. That is a direction we are looking into. The current release is for forms only. We're open sourced the synthetic data generation, training, evaluation, and Driver integration under libs/cua-s1 with an MIT license. Comments welcome! Especially if you are building computer-use agents and have run into a recurring decision that is too variable to script but is too narrow to call another LLM for. https://ift.tt/30AqktF September 19, 2026 at 09:22PM
Show HN: Koi Editor Alpha Hi, Koi Editor Alpha is now available to download for macOS 13.2+ (Apple Silicon). You can download the latest build here: https://ift.tt/l5FL4vT If you try it, feedback and bug reports are very welcome. You can also join the Koi Discord here: https://ift.tt/rwe7x2q Thanks! -- Michael https://koieditor.com/ September 18, 2026 at 09:51PM
संदेश
