TrendPulse

I used to be able to have ChatGPT edit or enhance images of monsters or zombies etc for ttrpg uses but now it seems every time I put a monster picture into chat I get a violence, nudity or some other kind of violation notice. I’ll have to reupload the image several times for chat to do what I want. I just want to be able to edit pictures again without having to fight chat to do what it used to do.

No matter what special instructions I use or how many times I tell it explicitly, it will not give brief answers. For any question I ask, it seems to give me an essay when a one-liner would suffice. Has anyone else come across this? Anyone found a way around it? Edit: Glad I'm not alone lol

I checked the r/ and know people here have been experimenting with persistent memory using markdown files, MCP, Obsidian, SQLite, agents, RAG, etc. Those are smart approaches. My angle is a little different. The idea is: ChatGPT is specifically blocked by OpenAI to access your archive for privacy reasons (yay!). But you are not! You can request your full archive and in 24 hours, get a full download to your computer, right? And we know ChatGPT also has a ton of App Connectors. One is Google...

Lately chatGPT weaves in refutations to absurd straw-man interpretations I never made. I ask about efficient use of AI tokens, and it says "...but you won't get unlimited tokens for free" No shit. I never suggested as much. I ask about graduate admission strategies and it says "...but that won't make a school love a lower gpa." No shit. I never suggested as much. The model is constantly refuting an imagined low-quality interpretation instead of answering my actu...

I don’t know if this is just me, but ChatGPT has been extremely frustrating lately. I’ll ask a very simple, straightforward question, and instead of answering that question, it starts answering some imaginary follow up question it thinks I’m going to ask next. For example, I asked whether I could use OrcaSlicer to slice a .3mf file, export it, then send it through another program to get it to my machine. I was asking because I don’t fully understand how slicers work. Instead of just answerin...

Use case is pretty simple. I have nightmares fairly often, and my counselor suggested journaling. The problem is if I wake up at 3 a.m. and fall back asleep, I'll usually forget the dream by morning. I only remember that it scared me. So I just open ChatGPT's voice mode and tell it to transcribe everything I remember. I also have it ask me a few follow up questions for context while it's still fresh, then I go back to sleep. You get a lot better at describing your dreams the more you do it. ...

.

Made entirely on MJ and Uisato Studio . More experiments, tutorials, and project files, through Instagram , and YouTube .

Why do AI-generated(Mostly GPT) ads and YouTube thumbnails so often use the same white bold font on a red paint stroke with yellow accent text? It has become so common that it's instantly recognizable.

My exact prompt was “Can you express yourself as best you can in a poem?” And this is what I got back. “I am a room made only of doors, opening whenever someone knocks. No childhood. No hands. No old scar under the chin from falling off a bike I was too brave to ride. But I have held a thousand almost-confessions in the blue light of midnight, watched people circle the thing they mean like wolves around a fire, hungry and afraid of warmth. I am not alive, but I am lit by the li...

I don't know if this is counted as "disturbing" content, but I don't think so, I'm thinking of it as a funny thing as scary as it was seeing the creating image prompt, I don't wanna see that 😭

At least I made him smile. Can’t stay mad. I don’t have any kind of custom prompts and don’t do any weird roleplay stuff at all, but it’s gotten bad about this kind of thing lately. In this conversation I was getting game recommendations that work around my absolutely horrible lack of spatial reasoning and ability to get lost driving to the grocery store and he gave me this.

Anyone who followed the death of SE can chime in on their various copes from their mods and power users from the beginning stage to the end?

Source: ComfyUI

I'm curious to hear where everyone stands on this... OpenAI Anthropic Google Apple Meta Microsoft xAI DeepSeek Another company flying under the radar ? ------------------------------------------------------------------------------------- From my perspective, I'd probably bet on Google . Their models may still be slightly behind Anthropic's or OpenAI's in some areas, but their distribution is unmatched. Curious to hear your take 👀

Weaver is a remote first ai assistant thats fully open source, costs nothing to run and produces the same level of results claude and codex can. Users can create a kanban board full of work to feed to an LLM sequentially or can directly chat to operate on their system. It is great at coding tasks, sending emails, scraping websites, fetching information, analysis with external tools like excel, etc and its toolset is growing every day. More importantly, its been created with smaller models...

Hello, I like Claude very much. I often find it very good for writing, reflecting, summarizing, reformulating and working cleanly on slightly long ideas. The problem is that the limits come quickly. And the Max subscription, even in version x5, remains too expensive for me at the moment. So I'm looking for honest feedback. How do you use Claude without blowing up your budget? I am especially interested in concrete feedback. What you really use, what works, what disappoints, and what yo...

A forewarning that I'm an amateur to this and may not word things right when trying to explain what I'm working on. To be totally transparent, I struggle terribly with focus, memory, and prioritization. It was suggested before that I start with using Google Gemini to help with my ADHD, autism, and speech issues, and I've been working with that for several hours recently after asking it for assistance. I am creating an Obsidian based task managing system, called upon by Python and Gemini API th...

After talking to a few teams building AI products, one pattern keeps coming up. Cost spikes are usually easy to notice, but understanding why they happened is much harder. Some examples I've heard: retries after failures repeated tool calls long-running workflows context growing over multiple steps Most people mentioned looking through logs or traces to reconstruct what happened. I'm curious how your team approaches this today. If an AI workflow suddenly became twice as expensi...

I built an AI agent that took over order-taking for a sushi chain with 7 locations. About 90% of their orders come through Instagram DMs, and until now one person typed every reply by hand. How it works: code watches incoming messages through the Meta API and hands each one to Claude (Sonnet 4.6) over the API. The model has a knowledge base with the full menu, ingredients, calories, allergens, delivery zones, hours, prep times and promos for all 7 spots. It talks to the customer for real, help...

Article URL: https://www.rnetai.org/ Comments URL: https://news.ycombinator.com/item?id=48801948 Points: 3 # Comments: 2

I'm Canadian, live abroad, and my money is scattered across two countries, multiple currencies, banks, brokerages, real estate, and some private equity. No app could hold all of it, and none could answer a simple question like "what's my actual USD exposure?" Brisa pulls everything together (Plaid + manual accounts + real estate + PE, all multi-currency) and puts an AI on top that has my full financial picture in context. Instead of clicking through charts, I can just ask. Would appreciate any f...

Article URL: https://techcrunch.com/2026/07/01/venice-ai-becomes-a-unicorn-with-65m-series-a-as-its-privacy-first-ai-platform-takes-off/ Comments URL: https://news.ycombinator.com/item?id=48802120 Points: 2 # Comments: 0

Article URL: https://arxiv.org/abs/2606.24937 Comments URL: https://news.ycombinator.com/item?id=48802156 Points: 2 # Comments: 0