github.com
Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wronghttps://github.com/cactus-compute/cactus-hybridHey HN, Henry & Roman here from Cactus.A small, on-device model is fast and private, but sometimes wrong, but frontier models are getting expensive pretty fast. So, we post-trained Gemma 4 E2B post-trained to know when it's wrong. Every response comes with a confidence score between 0 and 1. Developers can accept the on-device when it's high, hand off to a bigger cloud model when it's low. By routing only 15-35% of queries to Gemini 3.1 Flash-Lite, Gemma-4-E2B matches Gemini 3.1 Flash-Lite on most benchmarks.- ChartQA: 15-20%- LibriSpeech: 25-30%- MMBench, GigaSpeech, MMAU: 30-35%- MMLU-Pro: 45-55%We were always frustrated by the routing signals hybrid apps rely on: asking the model to rate itself in text (unreliable, and you're parsing prose), or token entropy heuristics (barely better than a coin flip in our tests). So we did mechanistic studies on small models, Gemma 4 particularly, and found the hidden state for different layers carry meaningful self-awareness signal for various siJul 22, 2026 5:56 PM
codifycli.com
Show HN: Codify – Terraform for Dev Environmentshttps://codifycli.com/Configuration as code for developer machines.The operation is similar to Terraform: plan + apply for making changes, and import + refresh for syncing system state back into the config. Codify operates statelessly, so no need to manage a state file. Just define what you need and apply it.There is a web + desktop app, and AI agent to make Codify easier to use (paid with free tier). The apps come with a dedicated editor (auto-completion, blocks view, and collaboration). The agent works via Codify configs which avoids the problem of LLMs generating and applying raw shell commands directly.We’re building Codify for three groups of people:1. Beginners and students - It lowers the barrier of entry and introduces them to new languages, cool tools and agents, especially now with the advent of vibe-coding.2. Software teams - It onboards new engineers quickly and ensures that everybody is on the same setup. It also helps more people to work cross-functionally (ex: backend and mobile)3. FreelancerJul 22, 2026 4:30 PM
cruciblebench.ai
Can a MUD evaluate LLMs? A $99 proof of concepthttps://cruciblebench.ai/I'm the author of a paper my friends and I wrote after we were curious if a MUD, text games originating in the 1970s, could be used to evaluate LLMs. We've spent the last several months on nights and weekends running this experiment and writing the paper on just our personal computers with about $99 in API credits.Our experiment did have an interesting leaderboard but even more surprising was the measurements of each LLM. We scored each on four behavioral dimensions, two of which lean heavily on an LLM classifier. When we removed those two, one of the frontier models fell six positions. When we then checked the classifier against a second judge, the per-model agreement between them ranged from 85% to 22%. The aggregate kappa (0.04 on probe detection) indicated the instrument was noisy without saying which models the noise was hitting. The most affected model shared a model family with the classifier. This isn't proof of bias, just one observation we recorded.We realize LLM judges can bJul 22, 2026 3:39 PM
gist.github.com
Show HN: Agent in 9 Lines Pythonhttps://gist.github.com/tosh/6e91a9dbf08dd630c535e7345ac7f0b5I asked myself: what would a minimal implementation of an agent look like?Something that works out of the box, is a real agent with tool calling, but without 1000s of lines of code, without dozens or hundreds of npm or pypi dependencies. Something with just a few 'essential' features (not a whole kitchen sink that most agent harnesses come with nowadays).An implementation close to pseudocode that you can look at in one page, everything there at a glance, no scrolling.This is the agent.py I ended up with so far: import json,sys;from subprocess import getoutput as sh;from urllib.request import Request as R,urlopen url=sys.argv[1];h=[];b=dict(model="gpt-5.6",input=h,tools=[dict(type="custom",name="sh")]) while p:=input("> "): h+=[dict(role="user",content=p)];H={"Content-Type":"application/json"} while True: o=(r:=json.load(urlopen(R(url,json.dumps(b).encode(),H))))["output"] h+=o;c=[i for i in o if i["type"]=="custom_tool_call"];z=r["usage"]["total_tokens"]/10500 if not c:print(o[-1]["conJul 22, 2026 1:52 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a8573f6836b4305830d4f85db683d40&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a855b42bc024ae0aa3d9b564eda21f6&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a854be31c3e472ca20433b1e2604dd6&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a853b890b3d44f98f3affc6ff6ad94d&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85e8e8665348f281d2ea8fc7fca398&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a853b449aa44922b0e24634620e2b70&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a8546dec9cb4517820fd6d1a9443429&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a855d6b595f421e8bdeb11ca2ed84c9&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85de46b43841a28567419fcb84a753&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a856a1c949d433b9523698b79a3fdc5&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a855e4ad220490a90b9d12508744702&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85433936194357a06a22114e68f403&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a855a34fae44de98b3ceaa351f4d463&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85733f4f344d69a238f9b70be7ca7a&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a853ee8364249f7b4fe59c4b3598c07&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
bing.com
There’s A New Benchmark Index For Digital Assets—And Bitcoin’s Not In Ithttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a857cd209fb4e4eaf4583f62708afea&url=https%3a%2f%2fwww.investopedia.com%2fnew-benchmark-index-for-digital-assets-bitcoin-not-in-it-12024600&c=3032671893451104994&mkt=en-usThe S&P Pantera Digital Asset Index excludes bitcoin and focuses on tokens with real-world use and revenue-generating blockchains. The index includes 18 digital assets, with ether, bnb, sol, tronix ...Jul 22, 2026 12:05 PM
