Edidiong

👨🏾‍💻

[Dr Asa @ureguyguy]

Done 🙂‍↔️

[Your Friendly Neighborhood Bakman @TiemmaBakare]

Here's to #GEMFOREVER

[Gideon @gideon_eb]

Today @chidiwilliams__ and I are launching Sentinel. AI-driven quality assurance for CX teams in financial services.

TLDR: We’re building https://t.co/GSo0MUt7xX to help financial services companies automate their compliance and QA with 100% coverage. We review your calls, emails, and customer support conversations for compliance violations, track performance, and create personalized AI coaching for your customer service reps.

Want to get early access, send me a DM or email [email protected] to get your team onboard.

[Gideon @gideon_eb]

Let’s gooooo - still a lot to do but excited.

[Your Friendly Neighborhood Bakman @TiemmaBakare]

It's my birthday, got nothing motivational to say except spread good vibes and stay above the poverty line.

[Your Friendly Neighborhood Bakman @TiemmaBakare]

Yesterday, my girlfriend and I broke up. Although, we did get back together as husband and wife so happy days regardless.

[Edidiong @a_d_dyung]

It’s been a busy few years 😮‍💨

[Gideon @gideon_eb]

Okay Let's just open source our YC application.

No more bringing pencils to a sword fight. We're automating back-office processes to enable fintechs and financial firms to expand compliantly. CC @t_blom @daltonc

[Edidiong @a_d_dyung]

@TiemmaBakare Congratulations boss 🥳🥳

[Your Friendly Neighborhood Bakman @TiemmaBakare]

I proposed to my girlfriend this weekend. 💍

Here's what it taught me about systemd run0 LPE 🧵

[Edidiong @a_d_dyung]

@_ritaokonkwo Love it 😍

[AK @_akhaliq]

Google presents Patchscopes

A Unifying Framework for Inspecting Hidden Representations of Language Models

paper page: https://t.co/12ucvQGmn9

Inspecting the information encoded in hidden representations of large language models (LLMs) can explain models' behavior and verify their alignment with human values. Given the capabilities of LLMs in generating human-understandable text, we propose leveraging the model itself to explain its internal representations in natural language. We introduce a framework called Patchscopes and show how it can be used to answer a wide range of research questions about an LLM's computation. We show that prior interpretability methods based on projecting representations into the vocabulary space and intervening on the LLM computation, can be viewed as special instances of this framework. Moreover, several of their shortcomings such as failure in inspecting early layers or lack of expressivity can be mitigated by a Patchscope. Beyond unifying prior inspection techniques, Patchscopes also opens up new possibilities such as using a more capable model to explain the representations of a smaller model, and unlocks new applications such as self-correction in multi-hop reasoning.

[merve @mervenoyann]

all the books I accumulated 2 years ago 🫰🏼
most of them I bought myself and 3 of them were gifted by lovely authors 🥹

[Google AI @GoogleAI]

Outside of the mathematical setting, large language models can be prone to making logical mistakes. Today we present an evaluation benchmark for mistake identification across settings and examine how LLMs might learn to correct their own logical errors. →https://t.co/U6U5D7Libb

[Celebration Church International @cci__global]

The most anticipated creative conference is here! 🤩🎉🎉

Algorithm 2024 is here and it's going to be as thirlling as ever! 🚀

This is where brilliance meets innovation, creatives from diverse fields will get the opportunity to collaborate, influence and occupy their space.

Brace yourself for the impact it's about to have on you as a creative.🔥

Mark your calendars and get ready to be part of Algorithm 2024.
Do not miss out on the creative event of the year!💃🏾

Secure your spot now by visiting the website in our bio for tickets.

See you there!

#cciikeja #ccilagos #algorithm

[ayo (padawan) @_alternatewolf]

I’ll be hosting an AMA with my friend @MoVonLagos next Saturday by 6 pm WAT (via @sysdsgn).

Moses is a Staff Engineer at Google who has been promoted 3 times in 4 years — an incredible feat, given the commonly accepted rate.

https://t.co/GnKRKhYYdU

[Edidiong @a_d_dyung]

@TiemmaBakare congrats boss

[Your Friendly Neighborhood Bakman @TiemmaBakare]

As word had it, it did take me 3 years. New beginnings and grateful to start off the year as a true senior man.

[Olivia Moore @omooretweets]

2023 was a big year for AI agents - but 2024 will be even bigger.

My market map + a spreadsheet of the 60 products I'm tracking👇

[Edidiong @a_d_dyung]

@_ritaokonkwo @abigail_sleek Who’s the Oga ooo ? I’m chief bridesmaid for both of you 😁