Suvash Thapaliya

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?

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. 😅

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.

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.

The second post is by @abhi9u.bsky.social on some common CPU architecture concepts (instruction pipelining, memory caching &speculative execution). Abhi has done a great job with the analogies in this one. blog.codingconfessions.com/p/hardware-a...

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.

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...

I probably read this blog multiple times today. You can really tell that it's written by a team that cares about helping engineers build simple & reliable systems. Thanks again to the authors Erik Schluntz and Barry Zhang. I wish more of the @anthropic.com team would be here on Bsky.

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...

And then, there's a pretty good coverage on building agents. Once again, after a good amount of warning that most systems don't need to be designed this way. Sure, agentic systems sound more fun. But, from what I see, most real world problems don't need autonomous plan-attempt-verify loops.

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...

I appreciate that they've introduced names for some common workflows. I've already been using Prompt Chaining & Routing, considering Parallelization next. More importantly, notice that they're not new hypey names, these flows already existed in the data engineering world.

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.