823 results for seeing · 3.043s

News for “seeing”
18 results • 3037 ms server time
Moozonian News
news.ycombinator.com• Jul 27, 2026• 1 min read
Show HN: ProofLeague – friends can ask for proof when you start a workoutHi HN!My friends and I used to do a rough version of this over text. We’d tell the group when we were starting a workout, and someone could ask for a selfie to keep us honest.It was simple, slightly ridiculous, and surprisingly effective. It was also clumsy to manage in a group chat, so I built ProofLeague:https://proofleague.comThe rule is basically the same: create a private league and choose a weekly goal. When someone starts a workout, everyone else has 30 minutes to ask for a selfie. If nobody asks, the workout counts. If someone does, the person takes a fresh selfie in the app before the response deadline.I’ve found that seeing friends work out is motivating, and seeing their exhausted post-workout selfies is often pretty entertaining.What started with a few friends has grown into six different leagues for me. I can start one workout across several leagues, and each one gets its own chance to ask for proof. If multiple leagues ask, I can share the same selfie with the leagues tha
Moozonian News
news.ycombinator.com• Jul 23, 2026• 1 min read
Show HN: Echo – Fable-level results at 1/3 the cost using open-weight modelsI’ve been building Echo (https://echo.tracerml.ai/), an experiment in making one AI system out of a pool of open-weight models rather than choosing a single model and using it for every task.It started with a simple experiment. I took a group of models, including GLM-5.2, Kimi K2.7 and others, and ran them on the same evaluations. Then I measured what would happen if, for each problem, you somehow knew in advance which models would be useful and how their outputs should be combined.That hypothetical system performed substantially better than any individual model in the pool. Of course, it is not something you can actually deploy because it relies on knowing which decisions were good after seeing the result. Echo is my attempt to recover some of that advantage without having that information in advance.For each request, Echo decides how much computation to allocate, which models should participate, and how their work should be combined. Some prompts may only need a relatively small amou
Moozonian News
news.ycombinator.com• Jul 23, 2026• 1 min read
Are we in the era of AI slop landing pages?Sorry for making it sound like a rant, but is anyone else actually tired of seeing the same AI slop landing pages? Those same card layouts and color shcemes? And those fake metrics, "Trusted by 10,000+ professionals", no bro my SimilarWeb extension shows 0 traffic on your site for the past 3 months..I mean yeah I get it that you need to ship fast but maybe like delay your launch for 12-24 hrs and make at least a half decent and appealing landing page. These landing pages remind me of that scene from Toy Story where there was a shelf full of Buzz lightyear figurines. Do people actually have 0 taste?Do you guys trust such apps especially in B2B space? With a landing page that screams 0% trust and 100% AI generated, you bet I'm not gonna give you access to my credentials or repos etc..Your landing page is the first impression of your app, at least make it count..This concludes my rant Anyone else feels the same?
Advertisement
Moozonian News
news.ycombinator.com• Jul 22, 2026• 1 min read
Ask HN: Where is NFTs as a technology or investment?As I’m working through reports, I realized that with AI-everything taking all the air in the room, I hadn’t heard about tokens of the non-fungible kind for a hot second.As an artist, I was excited about the implications of getting paid for your work each time it sold, but have not seen that facet explored in the tech news I follow here and elsewhere.Of those still in the space, what does the landscape look like? Did it pan out better or worse than you expected? Has the technology led to any unforeseen problems or solutions that came from time spent on the tech?Truly curious, seeing as we are in what I would call a similar cultural moment with what I’ve been seeing made and written about “agentic” AI.
Moozonian News
bing.com• Jul 22, 2026• 1 min read
61 NFL predictions ahead of the 2026 seasonJarrett Bailey Has been covering the NFL at SB Nation since 2023. We are so close to football being back, and Lord do we need it. If you’re on Twitter right now, you’re probably seeing every person ...
Moozonian News
threadfork.com• Jul 21, 2026• 1 min read
Show HN: threadfork – AI meeting notes that run on your MacHi HN, I built threadfork. It's an AI notetaker where the whole pipeline runs locally on Apple Silicon. Your microphone and system audio gets captured without a meeting bot and most importantly your meeting data doesn’t get sent or saved anywhere.I've been building in the privacy + local LLM space for the past several years (I started DataFog, an OSS PII detection library with 300K+ downloads); keeping all the processing and data on-device was a day 0 condition for me when building this out. Granola's updated privacy policy, effective later this week, keeps non-enterprise users opted into model training on "de-identified" data by default. Having built PII detection for a living, I'll say plainly: de-identifying meeting transcripts is really hard. Names are the easy part; deal terms, client details, and health disclosures are the transcript. For the lawyers, consultants, and therapists I've been talking to, the only version of this that holds up is the model never seeing the data at all
Moozonian News
worx.aeonax.com• Jul 21, 2026• 1 min read
Show HN: Aeon.WorX – A generic object lifecycle management system (like PLM/PDM)Hi All,In the past I used to make games as an hobby. I wanted do something different this time. After having spent ~10Y working on SmarTeam, ENOVIA and 3DExperience Platform. And recently using Azure Devops and Salesforce. Seeing all the complexity, engineering that went into it, I was itching to create something similar of my own. Now that we have LLM assisted coding, big projects should be doable by a single person, right? This is my attempt (v0) doing the same.1.9B Tokens and 28 Dollares Later, We have a working demo.Since this was a big endeavour, I wanted to have structured knowledge base. Discussion with various LLMs suggested (OpenSpec)[https://openspec.dev/] is a good way to store this info and make changes to it. LLMs also suggested that I track workitems using (beads)[https://github.com/gastownhall/beads]I initially modeled the RFLP (Requirements, Functional, Logical, Physical) framework from my early days of working on 3Dx. But I didn't have much sample data to seed. 3 days
Moozonian News
puckstory.com• Jul 21, 2026• 1 min read
Show HN: An interactive network graph of every Stanley Cup championI built a network of all 1306 players and 110 rosters engraved on the Cup since 1915.Surprisingly there's no islands, every team has somehow had at least one player who's won it again, there's several close calls where the connection almost broke. A few times where a winner starts off as an island and then gets connected later on. Most recently St. Louis almost got marooned in 2019. Same thing happened before in '89, '80', '74, etc.You can six degrees of Kevin Bacon anybody; just search a name and click 6-degree icon next to it to choose another. It takes 9 handshakes to go from the first cup to the last.You can move between eras or set a specific range, search and select any player, team, or connection, recolour by dynasty, switch between a network view and a year-by-year timeline, filter by multi-Cup winners or player positions.Nodes are draggable, selections can be isolated and cut as subgraphs, reset, or resized. Copy pastable urls to save or share what you're seeing and story mode
Moozonian News
bing.com• Jul 19, 2026• 1 min read
Food Recalls Are Rising. Here's What Consumers Need To KnowFrom fresh produce and eggs to packaged foods and deli meats, food recalls are rising across the U.S. Here’s why, what they mean for consumers, and how to reduce your risk. Consumers are seeing more ...
Advertisement
Moozonian News
news.ycombinator.com• Jul 16, 2026• 1 min read
Vector search isn't the hard part. Deciding what should be searched isOver the last few weeks I've been redesigning the retrieval pipeline for an AI knowledge system.Initially, the architecture was fairly typical:User Question │ ▼ Vector Search │ ▼ Top K Chunks │ ▼ LLMIt worked well while the knowledge base was small.As more documents were added, I started seeing a few recurring problems:More irrelevant chunks being retrieved.Larger prompts and increasing token costs.Multiple documents discussing the same topic competing with each other.Vector search returning semantically similar chunks from documents that weren't actually the best source of truth.I realized the problem wasn't vector search itself.It was deciding what should be searched before semantic retrieval even began.Instead of treating every document equally, I separated the system into two independent stages.IngestionDuring document upload, every document is processed once.The pipeline extracts structured metadata including:document typebusiness roledepartmentstopicsplanner summaryretrieval keyw
Moozonian News
nestforge.dauerschicht.com• Jul 14, 2026• 1 min read
Show HN: NestForge, true-shape nesting in the browser, every layout re-verifiedI come at this from the software side, not the workshop side. I kept seeing laser and plasma people complain about nesting tools that crash on real-world DXF exports or quietly produce layout they didn't fully trust, so I built NestForge: a true-shape nesting studio that runs entirely client-side (Rust compiled to WASM), with one design decision I'd like feedback onThe core idea: the optimizer is never trusted. After nesting, a second, independently implemented validator re-checks the layout from scratch (no-overlap, sheet containment, kerf and spacing distances, grain constraints) using robust geometric predicates, Shewchuk-style orientation tests, with borderline distance comparisons re-derived in double-double arithmetic from the og inputs. The two components share no geometry code, so the validator can't inherit the optimizer's bugs. A layout that fails validation is discarded and never shown. Failures produce witnesses: the exact pair of parts and the measured vs. required gap.Oth
Moozonian News
bing.com• Jul 14, 2026• 1 min read
Google brings Gemini in Chrome to UK usersGoogle has just rolled out Gemini for Chrome in the UK. The integration doesn't sit well with everybody — and Gemini isn't the most popular AI assistant out there — but you will start seeing an "Ask ...
Moozonian News
news.ycombinator.com• Jul 13, 2026• 1 min read
Ask HN: AI Agent and harness containerization/security recommendationsHello HN crew -I am seeing the tendency for people to allow AI agents to access local project & user folders, and beyond (operating system files).I thought to ask the question: How can we best use AI tools safely - where the workflow often runs local system commands and network commands - to protect the integrity of our systems & data AND be easy enough to use productively?Comment structure idea:Operating system / Agent harness / Agent / Security strategy & tool stack / WorkflowTo give some examples: I am currently using OpenCode (+DeepSeek) on Linux Mint Debian Edition (LMDE), and I notice that the Agent & harness is frequently asking to create files in /tmp/ - I usually forbid this, and instruct it to only use files in the current folder. I would rather that the tool ONLY have access to a given project folder (~/Projects/PROJECT-NAME) in a system-enforced way. However, I see that the agent often wants to run system commands (like `ps` to debug a local dev server, `pandoc` or `ffmpeg`
Moozonian News
github.com• Jul 13, 2026• 1 min read
Show HN: I implemented a neural network in SQLTwo weeks ago I was on my babymoon in Corfu, Greece. While in transit, I was overseeing a GSoC intern submit an important feature to my array database library, Xarray-SQL. He added `to_dataset()`, which completed the roundtrip between thinking of array data in a tabular model simultaneously as gridded rasters (the premise of the project is that every Nd array can be mapped to 2d, where orthogonal dims of the Nd array are just primary keys of a tabular representation). We discussed in chat, now that this feature existed, what demos could we make that would prove this data model works?With down time on a warm beach during a heatwave, cool salty water giving me fresh ideas, I had an idea: what if we used Coiled's Geospatial benchmark discussion as a comprehensive overview of geo and climate queries. Are all of these common operations secretly relational, just with the wrong data model? Using Claude Code on the beach, I can confirm that this seemed to be the case: Claude and I publish a be
Moozonian News
news.ycombinator.com• Jul 10, 2026• 1 min read
Ask HN: Do we need a support group for developers alienated by LLMs?Surely I must not be the only one developer that doesn't recognize this field any more, and would rather do anything else than become a glorified code reviewer for machine generated code.Seeing my career crumble in front of my eyes, seeing my identity as software engineer questioned in the span of a few years has been, to me, traumatic, and utterly alienating because non-tech people are not unaware of how world-shattering this technology is to our niche, and many of our fellow peers either collectively shrug, or are ecstatic not to have to write code any more.I have been trying to reinvent myself, to set out on a path where I'm no longer a professional software engineer; where I will still enjoy coding software for myself, by hand, but the emotional turmoil at this radical change has not lessened, and I have been wondering if other people are feeling the same kind of alienation, and just feel lost and a bit aimless these days.(Please, this is meant to be a serious post about emotions s
Advertisement
Moozonian News
whitematterlabs.ai• Jul 6, 2026• 1 min read
Show HN: PAI, a Linux-y personal-assistant for MacHi HN!I've been spending the past month on PAI, a Linux-esque harness for a personal assistant AI for your Mac. Instead of giving a chatbot a bunch of tools, I wanted to just drop the LLM into a terminal and see how it'd fare.I've been using it to manage my calendar, 5+ email accounts, and engaging with / responding to people in a timely manner (casus belli for this entire project).After seeing how other always-on assistants were designed, I thought the Unix / Linux philosophy of system design could be applied to AI harnesses, and I wanted to experiment with how it'd hold up compared to them. So, I built PAI with the following things in mind:1. Engaging "code mode" in the LLM (LLMs are natural SDEs / SysAdmins) - If you remember the [code mode](https://blog.cloudflare.com/code-mode/) post from a while ago, I wanted to try and utilize those capabilities within the model for it to naturally interface with the harness rather than trying to load it up with a bunch of exposition. An LLM nat