Abacus.AI @abacusai Twitter profile

Last Seen Profiles

@SeanConvery

@FCC

@AuditorSorrell

@oshoring38

@mikicas__

@newrocketinc

@cuttsp

@cloudera

@review_J0514

@aavvilla

@ssbu_o

@_scsl

@VipRoseTr

@NuAxis

@ChagrinShorty

@bokeplokalmalam

@zoonoidart

@Dean_00K

@SplunkGov

@AAhmd14943

@cicuvoet

@brady_tk

@panjabimc

@ROniXgt

@asagiri_bp

@badluckclubnft

@seikoushita

@rileycannon63

@harikratos

@memekesde998

@TheParkerB_

@tiktok18x

@shinopp

@POferries

@Rajdeep36854295

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

1 day

Now That SB-1047 Is Dead... We Have To Celebrate 🥂🥂 We can move on to dropping more open-source LLMs :) A new coding dragon is coming this week!!

11

1

56

Abacus.AI

@abacusai

1 day

Join our webinar to explore the power of our AI Engineer! Learn how to build an AI Brain for your org, connect to all your systems, automate pipelines, and work with all kinds of data. RSVP today!

0

2

11

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

4 days

Generate short videos and animate memes! I have been playing with this all day on ChatLLM

18

8

150

Abacus.AI

@abacusai

4 days

You can transform a simple PDF earnings report into an interactive dashboard! Play around with different LLMs to see which works but we found that LLama-400B and Sonnet 3.5 does this task the best.

3

5

29

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

6 days

RouteLLM - Automatically routes your query to the best LLM Combines the chops of o1, Sonnet 3.5, GPT-4o and Gemini! Super Intelligence in the making 😄

42

399

Abacus.AI

@abacusai

6 days

LLMs now have step-by-step reasoning! Smaller models like Llama-70B and Smaug can tackle complex problems by breaking them down. This is only the beginning – they will be able to handle even more complicated tasks with ease!

1

2

23

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

7 days

Architecture For An AI Brain for Organizations A real-time permission-aware index that connects to all your services An AI brain that can access the index and can build agents, chatbots and models

17

18

162

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

7 days

Gemini's Real Superpower - It's 10x Cheaper Than o1! The new Gemini is live on ChatLLM teams if you want to play with it. Predictably, the new version is better than the old version, and Gemini now trails behind o1, Sonnet, and gpt-4o but is significantly better than

34

44

416

Abacus.AI

@abacusai

8 days

This survey paper (link provided in alt/image description) is a great read on GraphRAG, improving standard RAG systems' accuracy. Graph RAG uses relationships between enttiies to improve information retrieval, leading to more accurate and context-aware responses!

4

0

20

Abacus.AI Retweeted

Jesús Adriel Avilés

@AdrielAviles

10 days

ChatLLM by @abacusai is my best kept Ai 'secret'; Which only my close friends and course members knew. And now you do too.

1

2

12

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

11 days

Realistically AI does not contribute more than 10% to a code base of medium complexity today By the end of next year it will be almost 30% That’s a very big leap forward! 🚀

12

9

122

Abacus.AI

@abacusai

11 days

Autonomous agents are automatically performing these tasks: •Reading and responding to email •Generating reports and posting them on Slack •Generating legal and HR documents •Basic code reviews •Tackling tech and support desk requests AI is beginning to do more and more

8

3

55

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

12 days

To CoT or Not CoT? Great paper that shows chain-of-thought mainly helps math and symbolic reasoning It only has marginal benefit on other tasks On MMLU, directly generating the answer without CoT leads to almost identical accuracy as CoT unless the question or model's

14

61

226

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

13 days

This is how I read AI papers, and it can be a lot of fun... Turn it into interactive graphs!

10

118

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

13 days

Today’s AI is missing thinking at different layers of abstraction and memory It’s insanely hard to actually use AI to fix bugs in a complex code base Good human SWEs can do it with ease LLMs can’t explore, think, and remember at different levels of abstraction AI can get

42

15

172

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

13 days

Qwen 2.5 72B Is The Best Open-Source Model In The World The Qwen 2.5 models dropped today, and they have some excellent scores. It beat Llama-405b on Livebench AI (August questions). We will soon release its performance on the September challenge. With an excellent score of

15

73

411

Abacus.AI

@abacusai

13 days

With our Matrix Agent, you can perform complex analysis. Here’s what you can do: •Portfolio analysis •Stock analysis •Customer and leads analysis •Decision science

3

2

28

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

14 days

The best way to apply o1 models is through an LLM router that automatically routes your query based on task and difficulty level. Here is the best LLM router that you can design sonnet - writing, coding gpt4 - web search, doc generation gemini - video understanding o1 - complex

43

63

580

Abacus.AI Retweeted

Bindu Reddy

@bindureddy

15 days

Google has dropped this, and several CoT papers in the past, and this one speaks to o1's performance. This proves that transformers can solve most problems by generating intermediate reasoning tokens during inference time. It is remarkable that they do A++ research and are

53

164

1K

Abacus.AI

@abacusai

15 days

LLMs can write code to automate business processes or create chatbots/AI agents, but how would you run this code? Our AI engineer can host code, run pipelines, connect to hundreds of apps, and understand structured and unstructured data.

5

6

45