Deva
Simplifying AI for everyone. Stay up to date with relevant models, frameworks, and more.
| Platform |  | Pricing | Only free issues | Publishes | Daily |
|---|---|---|---|---|---|
| Issues | 27 | Founded | 5 months ago | Last Issue | 11 days ago |
| Active | |||||
Read this Newsletter
arihantdeva.substack.comLatest Issues
How LLMs Are Built: Pretraining, SFT and RLHF
A language model is not one training run. It is a pipeline of stages that produce different artefacts, and almost every confused argument about model behaviour comes from collapsing them together. The base model that finishes pretraining is...
DeepSeek V4.1 Flash 1017: The Flash Tier's Verbosity Tax
The flash tier stopped being a compromise this year. GLM 5.3 Flash, GPT-6 Luna, Claude Haiku 5.5, and now DeepSeek V4.1 Flash 1017 are all roughly frontier-adjacent small models at prices that used to buy nothing, and the interesting questi...
How to Use Jev in 2026
Most agent loops spend tokens explaining themselves before they do anything. The model reads a ticket, writes three paragraphs justifying a decision, emits it as JSON, and then a parser tries to recover the one value the application actuall...
Routing Through Free-Tier LLM Providers Without Hitting a Wall
Understanding Free-Tier Rate Limits Across Providers
Engineers today rely on free-tier LLM endpoints to prototype quickly and keep costs low. Those tiers impose strict per‑minute or per‑hour quotas that can halt a pipeline when a single...
Claude Sonnet 5.5 vs Opus 5.5: Cheaper Per Token, Same Per Task
Many teams look at the headline price per token when choosing between Claude Sonnet 5.5 and Opus 5.5, assuming the cheaper model will always reduce the bill. This view ignores how token consumption changes with model behavior. The real cost...
![AI [re]Generation](https://substackcdn.com/image/fetch/$s_!L6aZ!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd316565c-2791-4f13-a334-efcf2499510d_768x768.png)
Audience Metrics
Subscribers, engagement, traffic and sponsorship for Deva.
| Subscribers | Engagement | 73 | Monthly Web Visits | ||
|---|---|---|---|---|---|
| Accepts Sponsors | Estimated Cost per Ad | ||||
Explore More
Authors
The writers behind this newsletter.
Simplifying AI for everyone. Stay up to date with relevant models, frameworks, and more.
Frequently Asked Questions
How can I access the email archive for Deva?
You can find recent issues that have been published by Deva on Reletter by scrolling up to where it says Latest Issues. Tap on the link for any of the most recent emails or hit More Issues to see older ones.
How many subscribers does Deva have?
To see how many people subscribe to Deva, simply upgrade your Reletter account. We provide readership numbers and lots of other stats for this newsletter so you can decide if it's worth reaching out to.
How can I advertise in Deva?
Newsletter advertising can be extremely effective when it's done right. Before you pitch Deva as a potential sponsor or partner, make sure that you've done your research and checked its newsletter stats with Reletter.
Then, personalize one of our winning pitching templates and send it to the right person using the contact info provided.
How much does it cost to sponsor a publication like Deva?
Newsletter ad rates (or CPM) vary depending on many factors, including industry, number of subscribers, open rate, ad placement and more.
To find out how much an ad will cost, contact Deva using the contact information provided and ask for a copy of their media kit.
How can I find newsletters related to Deva?
Scroll up to where it says Related Newsletters to see other publications like Deva. You can also search our email newsletter directory to discover other newsletters that cover the topics you're interested in.
How do I contact Deva?
Reletter provides this newsletter's website URL above, where you will often find their contact information. We also provide links to associated social media accounts and pitching templates so you can reach out fast.