
Mechanistic Interpretability and Artificial Psycholinguistics in LLMs
| Platform | Pricing | Only free issues | Publishes | Weekly | |
|---|---|---|---|---|---|
| Issues | 32 | Founded | 9 months ago | Last Issue | 10 days ago |
| Active | |||||

Most AI governance programs start with a reasonable instinct: tell the model what it is allowed to do.
You add a system prompt and a policy. You write rules about fairness, human review, appeal rights, escalation, and sensitive data. You t...
Figure 1: Internal × output scatter for 12 LoRA experiments. At 70B, the four corpora separate into three distinct regimes. Within-70B Spearman ρ = −0.80.
When organizations fine-tune AI models using LoRA adapters, a natural assumption is...
The first piece in this series documented what fluency-as-validity looks like across a spectrum from naive to sophisticated (see Lawson Berstein). The second explained why it works — a reinforcing loop of cognitive heuristics, each pre-cons...
The first piece in this series, Fluency as Validity, documented a specific failure: mistaking the linguistic fluency of LLM output for evidence of soundness, understanding, or mind. The examples ranged from a GitHub repo with hardcoded “C...
We rarely decide something is true. We decide to stop checking. “Good enough!” we think.
That’s from the physician , on Substack, and it’s the most precise description I’ve found of what LLMs are actually doing to human judgment. Not dece...
Subscribers, engagement, traffic and sponsorship for Inside the Black Box: Cracking AI & Deep Learning.
| Subscribers | Engagement | 74 | Monthly Web Visits | ||
|---|---|---|---|---|---|
| Accepts Sponsors | Estimated Cost per Ad | ||||
The writers behind this newsletter.
Through "Inside the Black Box", I translate how AI actually works—the hidden mechanisms, the failure modes, the surprising capabilities—into clear language for builders, creatives, and curious professionals.
Awakened-Intelligence.com | AI systems architect & MI researcher. We build research infrastructure including automated pipelines, multi-agent loops, evaluation frameworks.
You can find recent issues that have been published by this newsletter 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.
To see how many people subscribe to this newsletter, 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.
Newsletter advertising can be extremely effective when it's done right. Before you pitch this newsletter 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.
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 this newsletter using the contact information provided and ask for a copy of their media kit.
Scroll up to where it says Related Newsletters to see other publications like this newsletter. You can also search our email newsletter directory to discover other newsletters that cover the topics you're interested in.
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.