132 results for Gemini

bing.com
Best AI prompts to create aesthetic birthday imageshttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85e58486dc4d1fbc38d8e41a59308a&url=https%3a%2f%2fwww.digit.in%2fnews%2fgeneral%2fbest-ai-prompts-to-create-aesthetic-birthday-images.html&c=8979304678868208044&mkt=en-usIf you’re looking to create aesthetic birthday images, follow these simple steps: 1. Open the Google Gemini app on your device. If you don’t have the app, you can use the Google Gemini website instead ...
Mar 24, 2026 5:36 AM
bing.com
Best AI prompts to create aesthetic birthday imageshttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85e3694628429c9dc963e375e1c06c&url=https%3a%2f%2fwww.digit.in%2fnews%2fgeneral%2fbest-ai-prompts-to-create-aesthetic-birthday-images.html&c=8979304678868208044&mkt=en-usIf you’re looking to create aesthetic birthday images, follow these simple steps: 1. Open the Google Gemini app on your device. If you don’t have the app, you can use the Google Gemini website instead ...
Mar 24, 2026 5:36 AM
bing.com
Best AI prompts to create aesthetic birthday imageshttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85df265ebd499e8571a577b6d61ce9&url=https%3a%2f%2fwww.digit.in%2fnews%2fgeneral%2fbest-ai-prompts-to-create-aesthetic-birthday-images.html&c=8979304678868208044&mkt=en-usIf you’re looking to create aesthetic birthday images, follow these simple steps: 1. Open the Google Gemini app on your device. If you don’t have the app, you can use the Google Gemini website instead ...
Mar 24, 2026 5:36 AM
bing.com
Best AI prompts to create aesthetic birthday imageshttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85dae9078d44df9fdc8c4bee8eb2ee&url=https%3a%2f%2fwww.digit.in%2fnews%2fgeneral%2fbest-ai-prompts-to-create-aesthetic-birthday-images.html&c=8979304678868208044&mkt=en-usIf you’re looking to create aesthetic birthday images, follow these simple steps: 1. Open the Google Gemini app on your device. If you don’t have the app, you can use the Google Gemini website instead ...
Mar 24, 2026 5:36 AM
bing.com
Best AI prompts to create aesthetic birthday imageshttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85e7a9da5f446696d6078e384cccbe&url=https%3a%2f%2fwww.digit.in%2fnews%2fgeneral%2fbest-ai-prompts-to-create-aesthetic-birthday-images.html&c=8979304678868208044&mkt=en-usIf you’re looking to create aesthetic birthday images, follow these simple steps: 1. Open the Google Gemini app on your device. If you don’t have the app, you can use the Google Gemini website instead ...
Mar 24, 2026 5:36 AM
bing.com
Best AI prompts to create aesthetic birthday imageshttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85c87b4ab9494f803cae29a1103e17&url=https%3a%2f%2fwww.digit.in%2fnews%2fgeneral%2fbest-ai-prompts-to-create-aesthetic-birthday-images.html&c=8979304678868208044&mkt=en-usIf you’re looking to create aesthetic birthday images, follow these simple steps: 1. Open the Google Gemini app on your device. If you don’t have the app, you can use the Google Gemini website instead ...
Mar 24, 2026 5:36 AM
bing.com
Best AI prompts to create aesthetic birthday imageshttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85cc4817c54643826ad9356c3daa26&url=https%3a%2f%2fwww.digit.in%2fnews%2fgeneral%2fbest-ai-prompts-to-create-aesthetic-birthday-images.html&c=8979304678868208044&mkt=en-usIf you’re looking to create aesthetic birthday images, follow these simple steps: 1. Open the Google Gemini app on your device. If you don’t have the app, you can use the Google Gemini website instead ...
Mar 24, 2026 5:36 AM
bing.com
Best AI prompts to create aesthetic birthday imageshttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85ebf535b74d8a9c068770c14e8105&url=https%3a%2f%2fwww.digit.in%2fnews%2fgeneral%2fbest-ai-prompts-to-create-aesthetic-birthday-images.html&c=8979304678868208044&mkt=en-usIf you’re looking to create aesthetic birthday images, follow these simple steps: 1. Open the Google Gemini app on your device. If you don’t have the app, you can use the Google Gemini website instead ...
Mar 24, 2026 5:36 AM
science.nasa.gov
Dim Delights in Cancerhttps://science.nasa.gov/solar-system/skywatching/night-sky-network/dim-delights-in-cancer/Cancer the Crab is a dim constellation, yet it contains one of the most beautiful and easy-to-spot star clusters in our sky: the Beehive Cluster. Cancer also possesses one of the most studied exoplanets: the superhot super-Earth, 55 Cancri e. Find Cancer’s dim stars by looking in between the brighter neighboring constellations of Gemini and […]
Mar 17, 2026 7:41 PM
news.ycombinator.com
Ask HN: AI Agents vs. Gateways vs. Harnesseshttps://news.ycombinator.com/item?id=47397737Hi,I'd like to get everyone's take on the different components in the AI Agents ecoysystem. I find the current terminology quite confusing as it's not always obvious what I'll be actually getting when I examine the available options.A lot of things get called Agents, but that term seems hard to define as it often refers to overlapping functionality. To me, agents seem to be currently composed of the following components:## Harnesses- Adds UI and system instructions around an LLM and may also augment it with tools such as memory, tool calls, etc...- Examples are Claude Code, Code, Gemini CLI, pi.dev, ...## Gateways- These connect agents to your communication tool of choice, e.g. Whatsapp, Telegram, Slack, Discord, ...- Examples are OpenClaw and Nanoclaw## Sandboxes- Isolated environments where Agents can run with limited or auditable capabilities- Examples can be from physical ones like separate Mac Minis to docker-agent, agent-sandbox, localsandbox, ...This then takes us to *Agents*:##
Mar 16, 2026 11:43 AM
github.com
Show HN: Reviewd – A free, local alternative to Claude Code Review(no API costs)https://github.com/simion/reviewdAnthropic just launched their official Claude Code Review tool, pricing it at $15–$25 per PR. If your team is shipping 10+ PRs a day, that model scales terribly.Even before their launch, I was running a custom local Claude agent for my team to review PRs. The feedback was great and it caught real bugs, but the workflow was a massive time sink. I was manually invoking "claude --agent .. branch_name", grab the output, filter it and post the relevant comments.So I built reviewd to automate the local execution: https://github.com/simion/reviewdIt is a Python-based background daemon that runs on your machine or a VPS.How it works: 1. It polls GitHub/BitBucket for open PRs. 2. Creates a near-instant git worktree (no re-cloning). 3. Optionally runs your actual local test/lint commands (the AI gets the stdout/stderr). 4. Pipes the context into the Claude, Gemini, or Codex CLI you already have installed. 5. Parses the JSON output and automatically posts structured inline and summary comments to
Mar 11, 2026 4:43 PM
spacedaily.com
Apollo Cosplay on a 21st-Century Clock - Why Artemis Keeps Slipping Toward 2029 - Part 3https://www.spacedaily.com/reports/Apollo_Cosplay_on_a_21st_Century_Clock_Why_Artemis_Keeps_Slipping_Toward_2029_Part_3_999.htmlLos Angeles CA (SPX) Mar 09, 2026 NASA's latest reboot of the Artemis Moon program comes with familiar language: 'back to basics,' 'muscle memory,' 'step-by-step,' and an explicit nod to the Mercury-Gemini-Apollo playbook. The agency wants to fly more often, change hardware less, and build up capability incrementally, just like the 1960s. The problem is that Artemis is trying to cosplay Apollo in a world with very different politics, partners and rivals - and the gaps are showing.
Mar 9, 2026 5:07 AM
news.ycombinator.com
Ask HN: How are you structuring Markdown-based context for AI coding agents?https://news.ycombinator.com/item?id=47231386I’ve recently transitioned from using LLMs in-browser to a local agentic workflow in VS Code (Gemini Code Assist). I can approve/disapprove changes which is nice, but I’ve hit a wall regarding context management. Initially, I provided all the whole repo as context to the non-agentic version of Gemini code assist and it performed well.I read the agentic mode is "better" so to keep the agent aligned with my project's architecture, I’ve manually built 7 dense Markdown files that serve as the system instructions for the project. I require Gemini to update these files as we implement features.gemini.md (instructs gemini to read the other md files and handle updating) project_overview.md, architecture.md, features.md, database.md, api.md, security.mdEach file is between 500–1,500 words so I’m concerned if f this is the right way to go. There seems to be no consensus on context file best practices. I’m seeing strong arguments for both minimalist, lean instructions and dense, project-wide spec
Mar 3, 2026 12:29 PM
github.com
Show HN: Aethene – Open-source AI memory layerhttps://github.com/akhilponnada/aetheneHey HN, I'm shipping my first open-source project and I'm pretty nervous about it. Aethene is an AI memory API – it gives your AI apps persistent memory. Store conversations, extract facts automatically, search semantically, handle contradictions gracefully. It works well thank most of the memory projects available on the market currently.Why I built this: I was building AI agents and kept running into the same problem – they forget everything. Every conversation starts from zero. I wanted something that could: - Auto-extract facts from conversations (not just store raw text) - Handle "user moved from SF to NYC" without keeping both as true - Search by meaning, not just keywords - Version everything (who said what, when) Tech stack: - TypeScript + Hono (fast, edge-ready) - Convex (real-time DB + vector search) - Gemini (embeddings + extraction) What it does: # Store memory curl -X POST /v1/content -d '{"content": "User loves hiking, lives in SF"}' # Recall naturally curl -X POST /v1/re
Feb 22, 2026 1:57 PM
mindweave.space
Show HN: Mindweave – AI-powered personal knowledge hub with semantic searchhttps://www.mindweave.space/Hi HN,I built Mindweave to solve a problem I kept running into — I'd save bookmarks, notes, and links across different apps, then never find them again when I actually needed them.Mindweave lets you capture notes, links, and files in one place. The interesting part is what happens after: - Semantic search — find content by meaning, not just keywords. "That article about improving deep work" finds it even if those words don't appear in the content. Powered by pgvector cosine similarity on Gemini embeddings. - AI auto-tagging — Gemini generates tags on save, so you don't have to organize anything manually. - Knowledge Q&A — ask questions about your saved content using RAG. Retrieves relevant pieces, feeds them as context to Gemini, returns a grounded answer. Stack: Next.js 15 (App Router, Server Actions), PostgreSQL 16 + pgvector, Google Gemini (text-embedding-004, 768d), Drizzle ORM, Auth.js v5, Tailwind/shadcn. Deployed on Cloud Run. A few things I found interesting while building this
Feb 16, 2026 5:20 AM
news.ycombinator.com
Show HN: I extract recipes from TikTok, Instagram, and the messy webhttps://news.ycombinator.com/item?id=46974890I kept losing recipes. You know how it goes — you're scrolling TikTok at midnight, see an amazing pasta dish, save it, and never find it again. So I built TasteBuddy to fix that for myself. What I didn't expect: parsing recipes from the internet is a rabbit hole that goes deep.The thing is, recipe content is scattered everywhere in completely different formats. A food blog might have nice JSON-LD markup. A TikTok? Just someone talking over a video. An Instagram reel? Recipe buried in the comments. Pinterest? Links to blogs that died three years ago.So I ended up building specialized extractors for each platform.*Websites* are the "easy" case. I look for JSON-LD with `@type: Recipe` first — most food blogs have it, thanks to SEO plugins. But the real world is messy. I've seen duration fields as `PT30M`, `30 minutes`, `0:30`, and my personal favorite, just `half an hour`. About 30% of recipe URLs have no structured data at all, so I fall back to Gemini to make sense of the raw HTML.*TikT
Feb 11, 2026 1:45 PM
carousel-ai.intellisell.ai
Show HN: I Built a Free AI LinkedIn Carousel Generatorhttps://carousel-ai.intellisell.ai/LinkedIn Carousel posts have the highest engagement rate, but as an engineer, instead of spending hours on Canva, I wanted to build a tool that can generate LinkedIn carousels automatically.built this for my own startup and would like to give it to the HN community for free.Feel free to try it out—no email or signup required!How it works:[1] Provide a prompt. [2] Pick a theme (Professional, Creative, Tech, Minimalist, or Casual). [3] Adjust settings (colors, number of slides, etc.) and add branding.Tech-Stack Built using Firebase Studio LLM: Gemini 2.5 Flash lite (all I can afford to keep it free, and I found it was capable enough for the task. If there's interest, maybe I can add a pro version with stronger LLMs, and perhaps generate background images using Nano Banana)
Feb 8, 2026 1:38 AM
github.com
Show HN: Implementation of Google's PaperBanana (diagram generation from text)https://github.com/llmsresearch/paperbananaThe original authors haven't released code yet, so I built it from the paper. It takes a methodology section as input and generates a publication-style diagram.The pipeline uses five agents: a retriever selects reference diagrams via in-context learning, a planner drafts the layout, a stylist adjusts for conference aesthetics, a visualizer renders with Gemini, and a critic evaluates and refines over three rounds.The part that took the most effort was the reference dataset. The paper curates 292 (text, diagram, caption) tuples from 2,000 NeurIPS papers, filtering by aspect ratio and human review. Reproducing that required PDF layout extraction with MinerU, positional heuristics to identify methodology sections (paper headings are wildly inconsistent), and manual verification of each example.Output quality depends heavily on reference set quality. Requesting community to submit their papers via issues so we can add them. Quality examples in, quality output out!Runs on Gemini's free tier.
Feb 4, 2026 4:16 PM
depthsight.pro
Show HN: Solo trader built algo trading platform via AI – no dev experiencehttps://www.depthsight.pro/Hey HN,I'm Artem, a trader from Ukraine. I tried learning to code 15 years ago and failed—I wanted to build trading systems, not fight with syntax.8 months ago, I decided to try again using Claude/GPT/Gemini as my "pair programmers." I built DepthSight by describing what I needed in plain language. No prior dev experience.What it does: • Native AI strategy generation from plain text • Visual logic builder with weighted conditions • Dual backtesting: vector engine for speed, event-driven for accuracy • Genetic algorithms to evolve strategy parameters • Order book + tape analysis (market depth, open interest) • Full mobile PWAThe Twist: Instead of a signup page, I built a terminal ARG.Type "help" in the terminal at the bottom of depthsight.pro to start. You'll need to: - Decrypt hidden shards (Base64, HEX) - Find files in fake logs - Crack sudo access - Solve the final puzzleRewards: First solve: Lifetime Pro (unlimited compute) Top 10: 3 months free Everyone else: Beta access + 30% life
Dec 30, 2025 5:07 PM
news.ycombinator.com
LLM Benchmark: Frontier models now statistically indistinguishablehttps://news.ycombinator.com/item?id=46336990TL;DR: Claude Opus 4.5, Grok 4.1, and Gemini 3 scored within 2.4% of each other (96-98%). All refused to hallucinate and resisted every adversarial attack. Choose your LLM based on price and ecosystem, not benchmarks.## The ExperimentI was tired of synthetic benchmarks like MMLU and HumanEval—they measure something, but not what I actually care about when using an LLM daily. So I built TRIATHLON-LLM: 50 questions across 10 cognitive dimensions including logic puzzles with tricky wording, real math problems (Bayes, combinatorics), code debugging and system design, science explanations with constraints, causal reasoning, language nuance, creativity under constraints, applied ethics, hallucination traps, and adversarial prompts. Tested December 20, 2025.## Results| Model | Score || Gemini 3 | 123/125 (98.4%) || Claude Opus 4.5 | 120/125 (96.0%) || Grok 4.1 | 120/125 (96.0%) |Range: just 3 points (2.4%).On 7/10 categories, all three scored identically—perfect parity on mathematics, code &
Dec 20, 2025 3:49 PM