daniel phiri

dev exp. | ex @weaviate_io @strapijs | indulging my creative urges | dj | saut dans la vide | the man with the axe

[daniel phiri @malgamves]

"because I'm doing this for the thrill of it, killin' it, never not chasin' a million things I want"

https://t.co/8H1bJQMECq

[LM Studio @lmstudio]

Meet LM Studio's mobile app.

Your local models, now in your pocket.

[daniel phiri @malgamves]

relevant french langauge exam prep video of the morning

[Good Morning Business @goodmorning_biz]

"Tokenmaxxing" : le présentéisme, version IA 🤳

"C’est considéré comme un marqueur d’implication."

🎙️ @AnthonyMorel

[Google Gemma @googlegemma]

Meet Gemma 4 12B!

A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license.

Bridging the gap between edge efficiency and advanced reasoning. Here is what’s new with Gemma 4 12B: 👇

[daniel phiri @malgamves]

ok i'm officially obsessed!

[daniel phiri @malgamves]

fml the home lab people have got to me, upgraded from a 6750 to this 🫨

[daniel phiri @malgamves]

@helloiamleonie @liquidai @maximelabonne @paulabartabajo_ let’s gooo!!! they’re very lucky to have you ☺️

[trash @trashh_dev]

another week at the prompt factory.

[daniel phiri @malgamves]

the pressure to be dressed to the nines when you get good seats at roland garros 😭

[daniel phiri @malgamves]

@iamthezuba @BBC_Travel ohh congratulations on the write up, and thanks for sharing, i had no idea! booking it next time i’m back

[𝗇𝗂𝖺𝗆𝗁 @niamhutd]

Me normally Me today

[daniel phiri @malgamves]

people using lm studio for local models, what main model <> draft model combinations have you been using for speculative decoding?

[daniel phiri @malgamves]

@marlene_zw we’re rooting for you 💀 invite me please

[DAIR.AI @dair_ai]

// Memory as a Model //

The paper augments any LLM with a separate trained memory model that stores, retrieves, and integrates facts on its behalf.

It decouples memory updates from base-model weight updates. It achieves continual-learning robustness without catastrophic forgetting, which is a property that RAG fails to deliver.

A vector store is a database with a learned encoder bolted on. MeMo is a learned subsystem with explicit interfaces. That distinction matters, as agents need to be able to ingest fresh knowledge weekly without retraining or vector-DB churn.

At its core, the position here is that memory in agents should be modular, learned, and gated, not a context-window hack.

Paper: https://t.co/iMrghPtxWW

Learn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c

[daniel phiri @malgamves]

@mbuyu_ paris in summer? unmatched!
you’ve gotta come back

[Mbuyu 🇿🇲 @mbuyu_]

It was cycling through Paris going back to where I was staying after a day of walking around with @malgamves . I would go back to that day any time.

[daniel phiri @malgamves]

@helloiamleonie proud and out 😂

[State Change @JoinStateChange]

The @enhanced_games open in Las Vegas this weekend.

Before the starting gun — @analog_kyle sat down with CEO @max_enhanced to ask the question everyone’s thinking: if 43% of Olympians are already doping, who’s really playing by the rules?

Full episode on YouTube — link in bio. Follow the games live on @enhanced_games

[Tomi @tomiwebstr]

not one mention of suffering in carrick’s speech

[timi. 🦥 @algo8timi]

Getting opportunities that scare the shit out of you >>>

[Blake Burge @blakeaburge]

Underrated life advice: Make yourself easy to root for. Be kind. Be reliable. Celebrate other people’s wins. Work hard without complaining. Carry good energy into rooms. You'll be shocked by how many doors open for you by making life better for others.