Rowan Trollope
@rowantrollope
Followers
27K
Following
17K
Media
1K
Statuses
13K
CEO Redis devs❤️ redis 🇨🇦🇺🇸
San Francisco, CA
Joined March 2007
RT @antirez: We should likely put a large LLM weights and the explanation of how to do inference in some hard-to-degradate material, inside….
0
6
0
Amen.
At this stage AI will provide a huge boost to balanced people that don't jump in any extreme hype / anti-hype train, and will create issues to the folks that don't see that judicious application of LLMs is the key. One of those historical moments when wisdom is an advantage.
0
0
1
Our seed oil-free chips are made with just three ingredients:. Potatoes,.Beef Tallow,.And Sea Salt. Order yours today to taste the tradition. 🤠.
0
62
359
Both? Hating Elon and politics are intertwined. Whatever it is; its headlines like these make me avoid outlets like CNN altogether. They are actively speaking to an increasingly smaller segment of society.
Are they really this clueless about how rocket development works, or do they hate SpaceX because of Elon? As so often happens, it's hard to distinguish incompetence from politics.
1
0
2
.AI is moving fast—join me at Redis Released in San Francisco on Sept 4. Fireside chat with Redis creator Salvatore Sanfilippo (@antirez) + leaders from LangChain, W&B, and more. 👉
redis.io
Developers love Redis. Unlock the full potential of the Redis database with Redis Enterprise and start building blazing fast apps.
0
0
2
Very cool if it works.
Fine-tuning LLM Agents without Fine-tuning LLMs. Catchy title and very cool memory technique to improve deep research agents. Great for continuous, real-time learning without gradient updates. Here are my notes:
0
0
0
RT @karpathy: Continuing the journey of optimal LLM-assisted coding experience. In particular, I find that instead of narrowing in on a per….
0
996
0
RT @rohanpaul_ai: This is that original MIT report that said 95% of AI pilots fail and which spooked investors across US Stockmarket. The….
0
537
0
Great advice.
0
0
2
TradCat Mission | Catholic Apparel.=^.^= The Mission is Good =^.^=
0
1
31
RT @AskPerplexity: 🚨 BREAKING: The United States just created its first-ever Chief Design Officer and selected Joe Gebbia, the co-founder o….
0
257
0
RT @adityastomar_: Can we break the memory wall for LLM inference via KV cache rematerialization?. 🚨 Introducing XQuant, which leverages un….
0
92
0
RT @annarmonaco: To make Paradigm possible we’ve raised $7M led by @GeneralCatalyst. Tremendous thanks to our investors and supporters inc….
0
2
0
this.
ChatGPT needs a 'fork chat' feature. I want to be able to branch a conversation from any point like git branch -> explore alternate timelines without ruining the main thread. or copy pasting like a freak.
0
0
6
RT @bgurley: This intro is such great framing for the two nations. I suspect it will be quoted for decades. Engineers and lawyers.
0
75
0
this song has been stuck in my head all day and now it's stuck in yours
0
8
41
RT @annarmonaco: Paradigm is the AI-native spreadsheet to eliminate menial work. Thousands of users have saved 10,000+ hours with Paradigm,….
0
190
0
Interesting work on long term memory for agents.
M3-Agent: A Multimodal Agent with Long-Term Memory. Impressive application of multimodal agents. Lots of great insights throughout the paper. Here are my notes with key insights:
0
0
1
The capabilities of LLMs in one shot or few-shot coding is massively impressive. But its leading to overestimation of LLM capabilities for coding in a larger code base.
1
0
4
RT @alxnderhughes: RAG is a important topic in AI that you need know about. If you don’t have time for a course to learn about RAG, this t….
0
211
0
Awesome! And very critical.
A new embedding model cuts vector DB costs by ~200x. It also outperforms OpenAI and Cohere models. Here's a complete breakdown (with visuals):.
0
0
0