你可能會喜歡
It's truly humbling and uplifting to receive a photo from someone with both of your books on their desk, along with the message: "I got my own copy of A Beginner’s Guide to LangGraph and AI Agents and found it very useful and well-written." amazon.com/LangGraph-Mana…
I've been in the industry for over 20 years. Tech is challenging, exciting, and beautiful. A great place to grow. But it's not easy at all, especially if you want to master the craft.
I just saw one of those “It’s so easy to get into tech and make a huge salary” courses. It was launched by someone who: 1. did a coding bootcamp, 2. stayed 2–3 years at a company, 3. quit, and now sells courses. If it’s so nice and easy in tech, why quit so fast?
I just saw one of those “It’s so easy to get into tech and make a huge salary” courses. It was launched by someone who: 1. did a coding bootcamp, 2. stayed 2–3 years at a company, 3. quit, and now sells courses. If it’s so nice and easy in tech, why quit so fast?
I think that RAG will be a huge market. 95% of the world's data is "private" and therefore unavailable for training foundation models. But we can feed this private data to local LLMs via RAG. In some way each organization will likely have its own LLM-RAG app.
I love it when I start a podcast recording with a stranger and end it with a new friend. Has happened many times this year.
Success isn’t just about hard work - it’s also about timing, luck, and the people you choose to share the journey with. I wrote this small rant on why the daily process, values and companions matter more than outcomes: js-craft.io/blog/on-succes…
I’m used to hearing about tech stacks (e.g. React + Python + MongoDB), but today I heard about content stacks (e.g. Twitter + Twitch + Patreon).
Luca is 100% right on this one!
The ratio (time spent studying : time spent looking for a good job) is absurdly low, too.
How to get an "unfair" advantage vs AI? Build real human connections. I've tracked that the a podcast episode takes me 8-10 hours to produce. Why do I do it? Well, learnings. But the most important is the motivation it gives me! Interacting with someone who I admire === energy++
podcasting is extremely underrated & still early. with AI slop flooding feeds & jobs, one thing that'll stick around: great podcasts. & there aren't many of them. also ppl don't want AI pods. they listen for the host, human touch, authenticity etc. bonus: if it's evergreen.
On top of that, smaller models are cheaper leading to a faster feedback loop.
Learned this the hard way! When working in dev mode, start by testing your prompts with smaller AI models. They fail quickly and often, which is exactly what you want. Larger models are so capable that they can mask mistakes, making debugging harder.
Learned this the hard way! When working in dev mode, start by testing your prompts with smaller AI models. They fail quickly and often, which is exactly what you want. Larger models are so capable that they can mask mistakes, making debugging harder.
You can’t combat “burnout” or mental fatigue through rest only—you need wild curiosity, aggressive spiritual effort, and intellectual vagabonding.
Today I did a talk on MCP in front on 30+ devs. I love writing and hate speaking. So much energy goes into how you speak instead of what you say. When writing, you can edit and refine. When speaking, it’s all real-time. But being good at speaking will always gives you a huge edge
How to make your side gig the most efficient as possible: 1. have a baby 2. Get a 9-5 job 3. Fit the side gig in the time left. In the end, constraint inspires creativity. It forces you to get real very fast.
LLMs && Coding 1. English has a more complex syntax & vocabulary than JavaScript. If an LLM can write decent English, there is a high chance it is able to write JS as well. 2. With a code interpreter, an LLM can validate its own responses & regenerate. This is unique & essential.
💡 LLMs, with their natural language processing capabilities, will become the UI. For example, you won’t need to learn Excel’s clunky interface and functions. The embedded LLM will understand commands like: 'Give me the average of the top 50% of values from the salary column'.
One of the nice parts of `langchain` 1.0 is standard content blocks for reasoning, citations, multimodal stuff, etc Has been annoying to see providers implement slightly different variants of these, this should help make it easy to treat these in a standard way
`langchain` 1.0, now in alpha, ships with improved standardization for reasoning, citations, tool calls, multimodal data, and other content across LLM providers. No more juggling APIs— just one consistent interface. Try it out now in the alpha releases ⬇️ 🐍 Python:…
Big news! Make your voices heard!
‼️LangChain & LangGraph 1.0alpha releases Today we are announcing alpha releases of v1.0 for langgraph and langchain, in both Python and JS. 🕸️LangGraph is a low-level agent orchestration framework, giving developers durable execution and fine-grained control to run complex…
“I’m an engineer. I know code. I just never learned AI.” That’s who I built my teaching for. In a new @AITinkerers interview with @jheitzeb, we discuss how to fill that gap w/o semesters of math and why I teach by building GPT-2 in a Spreadsheet. youtube.com/watch?v=xUQMg3…
youtube.com
YouTube
Building GPT-2 in a Spreadsheet — Everything You Wanted to Know About...
United States 趨勢
- 1. Columbus 169K posts
- 2. President Trump 1.14M posts
- 3. Middle East 273K posts
- 4. Brian Callahan 10.6K posts
- 5. Azzi 6,229 posts
- 6. #IndigenousPeoplesDay 12.4K posts
- 7. Titans 41.7K posts
- 8. Thanksgiving 56.2K posts
- 9. Vrabel 7,358 posts
- 10. Cape Verde 16.2K posts
- 11. Macron 222K posts
- 12. Seth 50.6K posts
- 13. Marc 50.8K posts
- 14. HAZBINTOOZ 6,112 posts
- 15. Apple TV 5,867 posts
- 16. Native Americans 13.4K posts
- 17. Sarah Strong 2,290 posts
- 18. #Isles 1,470 posts
- 19. $GIGGLE 5,395 posts
- 20. Shildt 3,009 posts
你可能會喜歡
-
Code Geek
@codek_tv -
ng-conf
@ngconf -
AngularAir
@AngularAir -
Miško Hevery (AngularJS/Angular/Qwik)
@mhevery -
ionic
@Ionicframework -
Igor Minar
@IgorMinar -
AngularConnect
@AngularConnect -
Alyssa Nicoll
@AlyssaNicoll -
John Papa
@John_Papa -
Todd Motto
@toddmotto -
Pete Bacon Darwin
@petebd -
Jurgen Van de Moere
@jvandemo -
Charles Max Wood | [email protected]
@cmaxw -
Mike Brocchi
@Brocco -
Jeff Whelpley
@jeffwhelpley
Something went wrong.
Something went wrong.