Antoine Lizée (@A_Lizee) profile picture

Engineering, data, ai. Family stuff. Random thoughts.

Joined December 2012
Photo by Antoine Lizée (@A_Lizee)Photo by Antoine Lizée (@A_Lizee)Photo by Antoine Lizée (@A_Lizee)Photo by Antoine Lizée (@A_Lizee)Photo by Antoine Lizée (@A_Lizee)Photo by Antoine Lizée (@A_Lizee)Photo by Antoine Lizée (@A_Lizee)Photo by Antoine Lizée (@A_Lizee)Photo by Antoine Lizée (@A_Lizee)Photo by Antoine Lizée (@A_Lizee)
Ppl ask why Claude Code > Cursor. As an IDE > vim guy, I was surprised too. My take after 1m: - CC is linear, takes less mental load. You're in the driver seat but it's on autopilot. Much easier to follow. - Cursor's edit models are sh*t and will introduce random changes that you don't need. - Cursor's "accept" flow is broken, and gets you confused fast. - CC has planning mode, forces you to frame your needs well and puts the agent on a good track. I personally don't think CC is def. > Cursor, and still go back to Cursor often. And to my good ol' PyCharm too!!
105
Coding with AI makes me want more than 88 characters per line
139
🧵 Is AI ready for patients? Today we're publishing the first ever large-scale study of conversational medical AI in real-world conditions. Meet Mo, our AI medical assistant, deployed in our medical advice chat with GPs A thread on what we learned 👇
2
13
3
24
7,726
Read the research paper for: Detailed methodology Safety protocols Real-world deployment learnings Future research priorities Check it out here: arxiv.org/abs/2411.12808
1
1
2
375
Yes. I've seen the pattern over and over. People who rightly point to over hype and jump to the conclusion that AI is nothing new. It will be a tech revolution like the mobile, the web, the PC....
Many people have been recognizing that AGI won't be coming from mere scaling of current tech, and that generative AI has been severely overhyped. This is all true. But those people often conclude, "therefore AI is not going to be transformative -- this is a nothingburger". Absolutely not. AI (both current and near-future tech) *will* transform nearly every industry, and we're still only in the very first steps of that process. Generative AI may be a bubble, but AI is going to be bigger in the long run than what almost all observers currently anticipate.
1
138
2024 is gearing up to be a big year for Alan! Read our shareholders letter if you're interested 👇
1/ Exciting news, Alan community! 🚀 Our Q2 has been our best quarter ever. The unique "one-stop health partner" model we envisioned years ago is now paying off big time. Let's dive into the highlights!
1
96
Who else believe there is a secret competition in their head when they are mounting ikea furniture? (with a jury on time AND quality 🤣)
1
71
Tfw you unearth your @Ledger after a couple of years, find the password, update everything and realize that you have no account anymore. I know I had money, but I don't remember in which crypto! Damn it.
3
1
1
234
First, we were all peasants. Then, factory workers. Now, we're all at a desk working for services. Next, our kids will all be scientists.
57
This is a great recap of what Apple is building for AI. (usual Apple-Colgate smile included) teapawt.org/MaxWinebach/status/180…
This is from Apple's State of the Union The local model is a 3B parameter SLM that uses adapters trained for each specific feature. Diffusion model does the same thing, adapter for each style. Anything running locally or Apple's Secure Cloud is an Apple model, not OpenAI.
1
98
- small models with task-specific adapters - "private cloud" to run bigger models - built into the OS to take actions across apps, with context The latter make the difference.
45
The crazy thing is that GPT-4o is better on our (hard, specific) benchmarks than GPT-4. In addition to being faster and multimodal 🤯
1
97
The bliss of working in a French company during French holidays is hard to describe. The world finally hit the pause button for a couple of days.
2
74