Sachin Gadia

[Sachin Gadia @thesachingadia]

If the sailers are happy they will sail the ship in the right direction right speed and will make it reach the destination #team #teamgrowth

[Sachin Gadia @thesachingadia]

So true and quite important to keep your mental well being intact.

[Sachin Gadia @thesachingadia]

@aaditsh AI

[Sachin Gadia @thesachingadia]

Ridiculous

[Satyajeet Mishra @DecodeSatya]

We have RESERVATION in Air Traffic control team!😡😡
In the name of social equality, we are putting human lives in danger..

Just so that they want votes, they are allow less competent people in such crucial roles.
This nothing less than a sin.
#planecrash

[Shubham Saboo @Saboo_Shubham_]

OpenAI literally dropped a practical guide to building AI Agents.

An AI Agent is LLM + Tools + Instructions

[Sachin Gadia @thesachingadia]

#Grok 3 just levelled up with memory.
@thealexbanks just shared a prompt - Act as my personal strategic advisor. Based on your memory, identify critical blind spots holding me back and create an action plan to address these gaps

[Artificial Analysis @ArtificialAnlys]

o4-mini independent evals: o4-mini (high) claims the highest Artificial Analysis Intelligence Index score to date (o3 evals in-progress) and shows strong gains in coding ability

Key takeaways:
➤ o4-mini is a clear upgrade to o3-mini, while not as dramatic as the leap from o1-mini to o3-mini (+12pts), the model, with reasoning effort set to high, achieves a +4pt gain the Artificial Analysis Intelligence Index

➤ o4-mini (high) made particular gains in coding intelligence, achieving the #1 position in our Coding Index. This was supported by a +7%pts gain in both LiveCodeBench and SciCode whereby o4-mini is now the clear leader

➤ Pricing: o4-mini is priced in-line with o3-mini ($1.10/$4.40 per 1M Input/Output tokens), though cached inputs are 1/2 the price of o3-mini ($0.275/1M Input tokens vs $0.55/1M)

➤ Context window: o4-mini’s context window of 200k tokens is the same as o3-mini. This is now notably smaller than 4.1’s massive 1M token context window

➤ Token usage: As a reasoning model, the model used a high amount of tokens compared to other models broadly, but marginally lower than o3-mini (72M for o4-mini (high), 77M for o3-mini (high))

Evals for o3 are in progress. While we expect o3 to offer greater intelligence, o3-mini may be the more practical choice for most developers considering the substantially lower price and lower end-to-end latency

[Sachin Gadia @thesachingadia]

#Meta to train AI using public EU user content, excluding private messages & minors' data. Users will receive notifications with opt-out options.

Meta claims greater transparency than competitors while aiming for culturally relevant AI.
#Aiupdate

[Alex Banks @thealexbanks]

When will the "=AI" function be available to UK Google Workspace teams @GeminiApp @Google?

[Aurimas Griciūnas @Aurimas_Gr]

Weekend project: my 𝗢𝗽𝗲𝗻 𝗦𝗼𝘂𝗿𝗰𝗲 implementation of 𝗗𝗲𝗲𝗽 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗔𝗴𝗲𝗻𝘁 from scratch 👇

Few weeks ago I released an episode of my Newsletter and an update to the 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝘀 𝗛𝗮𝗻𝗱𝗯𝗼𝗼𝗸 GitHub repository.

There I implemented a Deep Research Agent from scratch without using any LLM Orchestration frameworks (using DeepSeek-R1 for some planning tasks).

In the project we implement the following Agentic topology:

𝟭. A user provides a query or topic to be researched.
𝟮. A LLM creates an outline of the final report that it will be aiming for. It will be instructed to produce not more than a certain number of paragraphs.
𝟯. Each of the paragraph description is fed into a research process separately to produce a comprehensive set of information to be used in report construction. Detailed description of the research process will be outlined in the next section.
𝟰. All of the information will be fed into a summarisation step that will construct the final report including conclusion.
𝟱. The report will then be delivered to the user in MarkDown form.

Each of the research steps are following given flow:

���. Once we have the outline of each paragraph, it will be passed to a LLM to construct Web Search queries in an attempt to best enrich the information needed.
𝟮. The LLM will output the search query and the reasoning behind it.
𝟯. We will execute Web search against the query and retrieve top relevant results.
𝟰. The results will be passed to the Reflection step where a LLM will reason about any missed nuances to try and come up with a search query that would enrich the initial results.
𝟱. This process will be repeated for n times in an attempt to get the best set of information possible.

Detailed walkthrough Blog Post: https://t.co/Xl36Qu3zPv
GitHub with implementation code and Notebooks to follow: https://t.co/qHfhwRb669

Happy Building!

Be sure to leave a like or star if you find the content useful!

#LLM #AI #MachineLearning

[Sumanth @Sumanth_077]

Google just launched the Agent2Agent (A2A) protocol for multi-agent communication!

A2A is a new open standard protocol that lets AI agents securely collaborate across ecosystems regardless of framework or vendor.

100% Open Source

[Alex Banks @thealexbanks]

It's incredible we get to watch the oAI vs xAI battle unfold in real time on this platform.

A tech war of the ages.

[Sumanth @Sumanth_077]

AI Agent built for developers working with large codebases!

Augment Agent can go from issue to PR in minutes

It comes with a 200K context, persistent memory, and deep tool integrations and MCP servers.

[Sachin Gadia @thesachingadia]

#𝗔𝗜’�� 𝗴𝗿𝗲𝗮𝘁𝗲𝘀𝘁 𝗽𝗼𝘁𝗲𝗻𝘁���𝗮𝗹 ��𝗶𝗲𝘀 𝗶𝗻 𝘀𝗼𝗹𝘃𝗶𝗻𝗴 𝘁𝗵𝗲 𝗽𝗿𝗼𝗯𝗹𝗲𝗺𝘀 𝘁𝗵𝗮𝘁 𝗸𝗲𝗲𝗽 𝗽𝗲𝗼𝗽𝗹𝗲 𝘂𝗽 𝗮𝘁 𝗻𝗶𝗴𝗵𝘁, 𝗯𝘂𝘁 𝗼𝗻𝗹𝘆 𝗶𝗳 𝘄𝗲 𝗱𝗼 𝗶𝘁 𝘄𝗶𝘁𝗵 𝗶𝗻𝘁𝗲𝗴𝗿𝗶𝘁𝘆.'

#Aiagent #LLMs #AIinmanufacturing

[Alex Banks @thealexbanks]

If you're building on the AI application layer right now, I see enduring moats being built across 4 key areas.

(1) Connecting workflows together where the sum is incredibly more useful than its parts e.g., orchestrating and calling different tools/agents that augment a specific workflow,

(2) Infusing specific domain knowledge that's scarce and valuable into a tool that others can benefit from,

(3) Deep proprietary data sets, and

(4) A beautiful UX of the underlying product.

What else?

[Sachin Gadia @thesachingadia]

All things aside, #OpenAI’s 4o image generation is the best in the market right now.

The barriers to creativity have never been lower when it comes to being an artist.

What's your take?
#AiAgent #

[Akshay 🚀 @akshay_pachaar]

Learn how LLMs work under the hood!

This is the best place to visually understand the internal workings of a transformer-based LLM.

Explore tokenization, self-attention, and more in an interactive way:

[OpenAI @OpenAI]

The updated GPT-4o is available now to all paid users. Free users will see it over the next few weeks.

[Sachin Gadia @thesachingadia]

Give the internet 72 hours, and they will summarize the last 20 years of historic events, memes and pop culture with AI 🫡

#ChatGPT's new image generation just launched

[Sachin Gadia @thesachingadia]

The best companies aren't asking “How can we add AI?”

They're asking “Should we?”

Technology should simplify, not complicate.

AI should enhance, not obstruct.

#aiagentinnovation #AIAgent

[OpenAI @OpenAI]

4o image generation has arrived.

It's beginning to roll out today in ChatGPT and Sora to all Plus, Pro, Team, and Free users.