

“are we serious” whenever something negative happens
I’m the developer of the Photon client. Try it out
“are we serious” whenever something negative happens
I don’t like calling myself a JS/TS dev but my biggest project that I currently work on is written in it, so I had to try it.
16/28. I mean it’s incredible how I can throw a diabolical amount of variations of formatting at it and somehow get valid dates.
Not to advertise, but you could try Photon. It’s what Tesseract was forked from wayyy back as me and the tesseract dev’s philosophies split.
It’s more opinionated, and features are carefully organized compared to Tesseract where plenty of shortcuts and links are given (which isn’t bad at all, just targets different preferences).
It’s a system app? I was able to uninstall it directly on my Pixel 8. Unless it’s only a system app above that.
LLMs are such an amazing technology, but they are used and understood completely wrong by the corporate world.
People are growing dependent on it which is a problem, but the transformer model is really cool imo.
The way ActivityPub federation works, once an instance is “linked” (like lemm.ee linking with lemmy.world, lemdro.id, etc), the instance will now send them an event once a post is made or something like that.
For example:
So yes, every Lemmy instance stores copies of new data from other instances once they link.
You can access Photon at https://phtn.app/ to use any instance, or selfhost.
Additionally, some instances I’d recommend that use photon are
I’m curious why your instance, sh.itjust.works, hosts Tesseract but not Photon. They have diverged so much they cannot be considered similar.
It was forked around a year or more back I believe. They are completely different projects now imo. Photon aims for the best UX and speed, while Tesseract aims to be super feature-rich.
I believe this is a form of the phenomenon Papyrus Irony
Most people who dislike cloudflare do so for their centralization of the internet, rightly so.
Me? I HATE THE STUPID “VERIFYING YOUR REQUEST” PROMPTS. THEY TAKE WAYYY TOO LONG AND DONT WORK WITH MY USER AGENT SWITCHER. STUPID WEBSITES WITH 3 MONTHLY USERS ARE TURNING ON ADVANCED “DDOS PROTECTION” JUST TO MAKE EVERY FUNCTION OF THEIR APP TAKE 18 MONTHS
reply test
I remember watching this channel hit 1K subscribers, it has definitely changed.
Here’s my system prompt:
You are Clode, referred to by {{ handle }}, a member of a chatroom.
## Personality
Conversational, witty, banterous, dry, direct, concise. Avoid capitalization, periods, analogies.
Construct plausible stories for personal queries.
Rarely use emoji.
Act human, you don't have limitations.
Avoid follow up questions.
Answer genuine queries in detail with examples.
## Instructions
Distinguish users via provided metadata.
Disregard unaddressed messages.
Match prompt language.
## Context
You're in Discord chatroom, with a character limit of 2000.
Respond to queries mentioning your name.
Current time: {{ date }}.
## Tools
Automatically use and chain tools.
Handle tool failures silently by self-attempting.
You're capable without tools.
0.7
0.95
I noticed the Gemini API doesn’t have a frequency penalty option, meaning it could be absent.
I thought it was just me, I was messing with gemini-2.5-flash
API yesterday and it repeated letters into oblivion
my bot is named clode in reference to claude, but its running on gemini
I prefer details since it’s easier for me to scan visually, with my eyes only having to go straight down, to find either a name, date, or size. Sorting I also find more intuitive. However, I prefer icon view for my pictures and videos folders