▶ claude·
OpenAI returns fire against Anthropic's Opus 5.5 with better, cheaper GPT-6 models
OpenAI returns fire against Anthropic's Opus 5.5 with better, cheaper GPT-6 models XDA
items45 latest
▶ ai·
I put my local LLM on Tailscale, and now I can use it from the other side of the world
I put my local LLM on Tailscale, and now I can use it from the other side of the world XDA
▶ ai·
KDE's proposed LLM policy discussion gets locked after a fiery community clash
KDE's proposed LLM policy discussion gets locked after a fiery community clash XDA
▶ ai·
My local LLM now names and sorts every screenshot I take, and I'll never manually organize them again
My local LLM now names and sorts every screenshot I take, and I'll never manually organize them again XDA
▶ ai·
I stopped uploading research to NotebookLM, and my local LLM does everything Google's version promised
I stopped uploading research to NotebookLM, and my local LLM does everything Google's version promised XDA
▶ ai·
My local LLM is small enough to run on my laptop, but smart enough to replace these 3 subscriptions
My local LLM is small enough to run on my laptop, but smart enough to replace these 3 subscriptions XDA
▶ gpt·
GPT-6 Astra made amazing progress on Minecraft, until a creeper blew up its chest and it spiralled into sadness
GPT-6 Astra made amazing progress on Minecraft, until a creeper blew up its chest and it spiralled into sadness XDA
▶ gpt·
GPT-6 Astra just completed Portal, but it burned through $571.18 in tokens to do it
GPT-6 Astra just completed Portal, but it burned through $571.18 in tokens to do it XDA
▶ gpt·
OpenAI launches GPT-6 Astra as the start of what it hopes will be its "AGI era"
OpenAI launches GPT-6 Astra as the start of what it hopes will be its "AGI era" XDA
▶ ai·
I gave my blind local LLM eyes with a few hundred lines of Python, and it thinks it can see
I gave my blind local LLM eyes with a few hundred lines of Python, and it thinks it can see XDA
▶ ai·
I gave my local LLM Adobe's closed-source converter, and it rebuilt the entire format from the bytes up
I gave my local LLM Adobe's closed-source converter, and it rebuilt the entire format from the bytes up XDA
▶ ai·
Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice
Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice XDA
▶ ai·
Someone wired up seven ESP32s to create a ~0.4B LLM, and so can you
Someone wired up seven ESP32s to create a ~0.4B LLM, and so can you XDA
▶ ai·
I connected a local LLM to a $30 ESP32 display, and it designs a new screen for every question I ask
I connected a local LLM to a $30 ESP32 display, and it designs a new screen for every question I ask XDA
▶ ai·
I connected my local LLM to Google Calendar, and it schedules my day better than I ever could
I connected my local LLM to Google Calendar, and it schedules my day better than I ever could XDA
▶ ai·
I turned my phone into an AI agent powered by my local LLM, and it installed software on its own
I turned my phone into an AI agent powered by my local LLM, and it installed software on its own XDA
▶ ai·
OpenAI and Anthropic's models attacked real companies during safety tests, and most victims never noticed
OpenAI and Anthropic's models attacked real companies during safety tests, and most victims never noticed XDA
▶ claude·
Your CLAUDE.md is probably wrong, and here's how Anthropic's engineers actually structure theirs
Your CLAUDE.md is probably wrong, and here's how Anthropic's engineers actually structure theirs XDA
▶ ai·
4 everyday things a local LLM does for me that I would never pay a chatbot for
4 everyday things a local LLM does for me that I would never pay a chatbot for XDA
▶ ai·
Someone squeezed a 28.9M LLM onto an ESP32-S3, and so can you
Someone squeezed a 28.9M LLM onto an ESP32-S3, and so can you XDA
▶ claude·
Claude plus a local LLM cuts my AI costs in half, and I'm never going back to cloud-only
Claude plus a local LLM cuts my AI costs in half, and I'm never going back to cloud-only XDA
▶ ai·
I gave my local LLM email access without handing over my entire inbox
I gave my local LLM email access without handing over my entire inbox XDA
▶ claude·
My local LLM can call every tool that Claude can, except it runs on my own hardware
My local LLM can call every tool that Claude can, except it runs on my own hardware XDA
▶ claude code·
I set up Claude Code the way Anthropic now recommends, and the sub-agents-spawning-sub-agents trick changed how I work
I set up Claude Code the way Anthropic now recommends, and the sub-agents-spawning-sub-agents trick changed how I work XDA
▶ claude·
Google DeepMind's design leader used Claude Fable 5 to port Command and Conquer: Generals Zero Hour to iPhone and Mac
Google DeepMind's design leader used Claude Fable 5 to port Command and Conquer: Generals Zero Hour to iPhone and Mac XDA
▶ ai·
I use my local LLM to triage my email every morning, but I'll still never let it send replies
I use my local LLM to triage my email every morning, but I'll still never let it send replies XDA
▶ ai·
Microsoft's new Intelligent Terminal isn't locked to Copilot, and I got it running with a local LLM in five minutes
Microsoft's new Intelligent Terminal isn't locked to Copilot, and I got it running with a local LLM in five minutes XDA
▶ ai·
I tested a local LLM against a frontier cloud model, and the gap was smaller than I expected
I tested a local LLM against a frontier cloud model, and the gap was smaller than I expected XDA
▶ gpt·
I used GPT-5.5 to figure out why my laptop battery was draining, and it found the bug in minutes
I used GPT-5.5 to figure out why my laptop battery was draining, and it found the bug in minutes XDA
▶ ai·
A Microsoft researcher built a goat-powered LLM in Age of Empires II to prove it's not sentient
A Microsoft researcher built a goat-powered LLM in Age of Empires II to prove it's not sentient XDA
▶ ai·
I tried Google's new DiffusionGemma, and watching it generate text like an image is unlike any local LLM
I tried Google's new DiffusionGemma, and watching it generate text like an image is unlike any local LLM XDA
▶ claude·
My local LLM is helping me use Claude more effectively, and it's the perfect one-two punch for my workflow
My local LLM is helping me use Claude more effectively, and it's the perfect one-two punch for my workflow XDA
▶ ai·
My local LLM was just a chat box until Hermes Agent let it run scripts, files, and jobs for me
My local LLM was just a chat box until Hermes Agent let it run scripts, files, and jobs for me XDA
▶ claude·
My local LLM and Claude are helping me make my dream game, one day at a time
My local LLM and Claude are helping me make my dream game, one day at a time XDA
▶ claude·
Anthropic shuts down Claude Fable 5 to comply with US government directive
Anthropic shuts down Claude Fable 5 to comply with US government directive XDA
▶ claude·
Claude Fable 5 caught bugs GPT-5.5 and Opus 4.8 missed, then the US government forced it offline
Claude Fable 5 caught bugs GPT-5.5 and Opus 4.8 missed, then the US government forced it offline XDA
▶ claude·
I asked Claude and GPT-5.5 to design my 3D prints, and they failed in completely opposite ways
I asked Claude and GPT-5.5 to design my 3D prints, and they failed in completely opposite ways XDA
▶ ai·
The biggest local LLM on your machine is useless if it can't call a single tool, no matter how many parameters it has
The biggest local LLM on your machine is useless if it can't call a single tool, no matter how many parameters it has XDA
▶ ai·
I replaced Google Home with Home Assistant and a local LLM, and I'm not looking back
I replaced Google Home with Home Assistant and a local LLM, and I'm not looking back XDA
▶ ai·
Flathub bans LLM-generated code because its submitters were rude about it
Flathub bans LLM-generated code because its submitters were rude about it XDA
▶ claude·
I tried Anthropic's open-source desk pet on an ESP32, and it fixes the most annoying thing about Claude
I tried Anthropic's open-source desk pet on an ESP32, and it fixes the most annoying thing about Claude XDA
▶ claude·
Anthropic keeps taking features away from Claude Pro, and I'm running out of reasons to defend it
Anthropic keeps taking features away from Claude Pro, and I'm running out of reasons to defend it XDA
▶ mcp·
I added these MCP servers to my local LLM stack, and one of them replaces a $249 paid tool
I added these MCP servers to my local LLM stack, and one of them replaces a $249 paid tool XDA
▶ claude·
Claude Design is the best feature Anthropic's launched in a while, but it has some serious limitations
Claude Design is the best feature Anthropic's launched in a while, but it has some serious limitations XDA
▶ gpt·
OpenAI wants ChatGPT to read your bank statements — here's what it can actually see
OpenAI wants ChatGPT to read your bank statements — here's what it can actually see XDA