HeyJaredLearn AI Together
The Learn AI Together community by Towards AI newsletter! Sharing opportunities, news, memes, projects, collaborations, learning resources and more.
- Indexed issues, last 90 days
- 12
- Latest publication
- Sep 24, 2026
- Audience
- Checking…
- Earliest in this view
- Jul 23, 2026
Latest issues
LAI #144: Your Eval Improved. Did Your AI? (opens the original)
Read excerpt
Good morning, AI enthusiasts!Your eval score went up. That does not necessarily mean your AI got better.If you change the generation prompt and the judge prompt in the same run, you no longer know what caused the improvement. The generated answers may be better, or your new judge may simply prefer them. This week’s AI tip shows a simple way to separate the two and keep your evals useful.We also have some great technical reads this week. You’ll learn:How models can be modified to reduce refusal b
LAI #143: DeepSeek V4.1 Flash, Tested (opens the original)
Read excerpt
Good morning, AI enthusiasts!This week, I tested DeepSeek V4.1 Flash, including its changes to KV-cache memory and how well it performs on our own writing benchmark.There is also a strong set of engineering reads this week, particularly around reducing the amount of unnecessary work happening inside AI systems.You’ll learn:How prompt caching can cut long-session input costs by roughly 85%Why LLM load balancing should account for tokens and cached prefixesHow Nemotron reduces KV-cache requirement
LAI #142: My AI Setup in 2026 (opens the original)
Read excerpt
Good morning, AI enthusiasts!This week, I’m opening up the AI setup I use every day: how I work across Claude Code and Codex, keep context and skills portable, run agents while I’m away from my computer, and turn repeated corrections into knowledge I can reuse. I’ve also shared the Obsidian vault behind it as an open-source template.We also finally have some news we’ve been waiting to share: we wrote a second book. AI Engineering for Production launches October 20.Plus, this week’s reads get int
AI Engineering for Production is coming October 20 (opens the original)
Read excerpt
Good morning, AI enthusiasts!I am very excited to finally share this with you: Louie Peters and I are launching a new book, AI Engineering for Production, on October 20.For years, a lot of AI engineering has been about squeezing more capability out of the model. Now the models are getting good enough that the harder failures are showing up around them.The book gets into that: context, retrieval, agents, evaluation, observability, recovery, fine-tuning, deployment, and the engineering decisions t
LAI #141: The Questions AI Can't Answer (opens the original)
Read excerpt
Good morning, AI enthusiasts!A lot of AI engineering comes down to decisions that do not have one clean answer. Which trade-off matters more here? Is this system actually failing because of the model, the context, the retrieval layer, or the infrastructure around it? When should you optimize, and when should you leave something alone?This week’s issue is full of those kinds of decisions.You’ll learn:Why continuous batching changes LLM serving efficiencyWhich vLLM settings actually matter and wha
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.