Life | Technology | Investing

cropped header 2.jpeg

Category: Twitter Page 2 of 63

1:1’s is an ext imp tool in mgrs box which needs to be toned up or down depending on the pulse of the member or team morale – knowing this is the skill of the manager. Cutting the middle layer in the current times is just a testament that teams need to be self organised..

Agree at so many levels. As a manager one would not need a weekly checkin if they are “really” involved working with the team. Folks mindlessly obsess over 1:1’s and try to ape some culture book.

Managed to setup my own Autonomous RAG with llama3 on Groq in less than 20mins, looks like it is going to be awesome. Hooking it with gpt-4o would be next! Thanks ⁦@ashpreetbedi⁩

Autonomous RAG with llama3 on Groq

I’ve had building a RAG on my to-do list for a while. Lately, I’ve been experimenting with Groq, which has consistently impressed me with its inference speed. It’s been over four months since I cancelled my ChatGPT Plus subscription and switched to BoltAI, where I can access leading models like GPT-4, Llama-3.70B, Claude Opus, and Mistral-8x7b at a fraction of the cost. What I appreciate about BoltAI is its well-designed graphical user interface, which allows me to easily connect with multiple foundational models via API.

My current stack LLM/AI products I use everyday – Cursor ide to write code – BoltAI for writing and brainstorming (gpt4, llama3, claude, mistral) – perplexity for research

RT @laurenbalik: ClickHouse is very good. It has the power to disrupt much of the SIEM/cyber space, not to mention many Snowflake $SNOW an…

RT @zimmskal: Llama 3 70B takes the king’s crown 👑 from GPT-4 Turbo – 100% in coverage and 70% in quality of code – 💵 most cost-effective…

– Looking at their balance sheet, their dry powder will deplete. So new acquisitions will likely come with equity. Win-win for acquiree and shareholders. – Organic innovation still seems unaddressed, as with the buyback they might not be able to take moon shots

– With the democratization of open-source foundational models, monetization will likely come from their utilization, which Apple will enable with their devices’ ecosystem.

– Their silicon strength and fab supply chain influence will likely give them an edge over Nvidia – GenAI / OpenAI is not a threat to them. Just a matter of time to allocate enggs and they can do it. Apple might partner with OpenAI

Page 2 of 63