Skip to content
HeyJared

The AI Architect

Subscribe for your FREE 7 AI Coding Techniques That Will Save You 10+ Hours This Week

Newsletter · By Tyler Folkman · English · Paid tier available · Official site

Indexed issues, last 90 days
12
Latest publication
Sep 27, 2026
Audience
Checking…
Earliest in this view
Jul 12, 2026

Latest issues

  1. Issue · Sep 27, 2026

    My Agent Spent 32,524 Tokens Before It Even Read a File (opens the original)

    Excerpt · Critical tone

    Read excerpt

    <img alt="Cover: a toll lane at night, the ticket printing before any car moves" class="sizing-normal" height="408" src="https://substackcdn.com/image/fetch/$s_!XqVh!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2

  2. Issue · Sep 20, 2026

    I Ran 60 AI Agents for a Full Day on Jev, the Model That Can't Talk. It Cost 35 Cents. (opens the original)

    Excerpt

    Read excerpt

    <img alt="Live screenshot of a 60-agent village running on the Jev decision model. The HUD shows $0.21 spent versus $23.10 simulated frontier cost, a 109x difference." class="sizing-normal" height="520" src="https://substackcdn.com/image/fetch/$s_!ETNz!,w_1456,c_limit,f_aut

  3. Issue · Sep 13, 2026

    I Cut My AI Coding Bill From $200 to $20 by Routing Jobs, Not Downgrading (opens the original)

    Excerpt

    Read excerpt

    <img alt="Cover art for the routing method: five job streams flow in from the left, two continue into a bright premium node while three route down into cheaper nodes, under the headline Route by job value." class="sizing-normal" height="520" src="https://substackcdn.com/ima

  4. Issue · Sep 6, 2026

    The Fastest Model Lost My Benchmark (opens the original)

    Excerpt

    Read excerpt

    <img alt="" class="sizing-normal" height="813" src="https://substackcdn.com/image/fetch/$s_!iBjR!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fb2fe27ac-c4e5-43d4-92b1-520da23684fe_2750x1536.j

  5. Issue · Aug 30, 2026

    I Stopped Betting My Work on One AI Model (opens the original)

    Excerpt

    Read excerpt

    <img alt="An analyst-style chart on white paper under the headline SAME BENCH. 10X CHEAPER.: two nearly identical benchmark bars, Claude Opus 4.8's vendor-reported result labeled FRONTIER SEAT at 85.0 and stamped $200/mo, and HARNESS GLM-5.3-FLASH at 84.3 stamped $20/mo, jo

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.

See coverage about The AI Architect