I wonder if the folks at @anthropic.com were being somewhat jokingly intentional of the term MCP, given it's "evil" Master Control Program origins(Tron, 1982). 😅

How I wish that whole Bsky “how dare you train LLMs on our publicly available Bsky firehose dataset” pitchfork campaign didn’t happen months ago and @hf.co members and authors were still happily sharing their posts here. :/

A bit embarrassing to admit, but another thing I've been rather late at using/understanding is WebAuthn(FIDO2) compared to U2F(FIDO). Not having used a FIDO2 compatible hardware key, I had sort of mentally bucketed them together. But, FIDO2 is a pretty solid improvement/extension over the FIDO. TIL.

Super late to the "Gigabit at home" party, but recently updated to it, also moved from Synology to Ubiquiti Router+AP setup, Ethernet where possible. Finally I can max out on downloading these bulky models from HF & Ollama store. 😅

I've been using the same #GPG keys (master, sign., enc. & auth.) on a @yubico.com Yubikey 4 since 2017, (following the drduh guide) extending the expiry every X years. I'm now considering creating new keys (esp. for RSA/4096 & ed25519) for a new #Yubikey 5. How is everybody else going about this?

Just finished reading “House of Huawei”. What a solid read, would absolutely recommend to anyone trying to understand and forward connect the dots to where we are with technology wars right now.

Solid 10/10 post by Thorsten, on letting the results of your LLM(http) calls decide what function to execute next, in a loop, in a loop, ....

Rewatched the Game Theory video by @veritasium.bsky.social again today considering the turn of recent geopolitical events. A good reminder that being nice, forgiving, clear while still retaliatory/provocable is a pretty good strategy in the majority of cases. www.youtube.com/watch?v=mScp...

Been meaning to use the latest Gemini(2.x series) models for a while now. Perfect timing by @strickvl.bsky.social with this set of practical examples in this standalone site. The only thing that could have made this even better for me would be direct curl examples, but maybe I'm asking too much. 😅

Last week I read a bunch of articles, all of which were a fun read. Not so heavy on social/sharing etc. these days, but figured I'd share them here regardless, because these were a lot of fun to read slowly through.

Gemma3 family of models seem quite good for straight-up text extraction from images(those horrible pdfs). Along those lines, I remember olmOCR from @ai2.bsky.social released just some weeks ago, based on Qwen VL models. Curious if somebody is working on olmOCR pipeline with Gemma3 models.

On this Saturday, I'm happily watching Veritasium episode on AlphaFold. I still think this is probably the highest impact model (in terms of opening up new future pathways for humanity) that has been made public in the last few years. Nothing else comes even close! www.youtube.com/watch?v=P_fH...

@lawik.bsky.social 👋

This is one of the first few posts I've seen that uses Deepseek model to generate high quality datasets, which then can be used to train the ModernBERT models. Really neat stuff! Once can easily replace the slower, expensive 3rd party LLM router with a fast, cheap & local model.

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open! Follow along: github.com/huggingface/...

One of the most fun things about using Open WebUI is how you can intersperse various models in the same conversation, depending on the next task you intend to work on. Start off with `deepseek-r1`, and the follow up the conversation with something like `phi4` or `qwen2.5-coder`.

Maybe a bit late to the club, but it’s pretty interesting to see the inner monologue when interacting with deepseek-r1.

How are folks building the "memory" layer in their #llm augmented #workflows, esp. in the context of multi step workflows? Most of the simple examples I've seen share the memory across all steps, but this doesn't seem "clean". Reminds me of workflow steps all reading/writing from same blob storage.

From my own experience building LLM augmented systems this year, I've been telling a lot of my colleagues that most use cases don't really need an "agent". Instead, they need a well defined product workflow with models(llms etc.) in the mix. It's reassuring to read the recent @anthropic.com blog...

Huh! Maybe finally time to switch to my own domain, so I don't have to create another account just to "squat" my original username here.

Over this year, I've done a lot of Phoenix Liveview (@elixir-lang.org) development using @zed.dev for the majority of it, with a good dose of @anthropic.com Sonnet-3.5 assistant. That being said, I still haven't "Signed In" to Zed! Not sure I'll do that anytime soon, but what am I missing out on?

I'll get straight to the point. We trained 2 new models. Like BERT, but modern. ModernBERT. Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff. It's much faster, more accurate, longer context, and more useful. 🧵

Given the new announcement of the Willow #quantum chip, I went ahead and rewatched this introductory lecture after a couple of years. Love the energy and the "no-nonsense, let's build up from the basics" approach by the presenter. Any follow-up recommendations? www.microsoft.com/en-us/resear...

@shrite.sh @samrat.me 👋 Nice seeing you here!

Looks like a lot more activity here these days. Not sure where/how everybody's finding people here, but 👋 to everybody who sees this. And yes, I've heard about starter packs and automated feeds, haven't quite used them yet, what else have I missed?

how do you do fellow squids are we doing this right ?

here we go again !