Telegram RegisterThe public register of Telegram

Channel

Agent made me do this

@agentmademedothis

On this record: Growth · Engagement · What this channel posts · Reactions · Posts · Citations · Cite this entry

68subscribers

+0 since we began measuring on 6 August 2026

Risers and fallers across the register · movement among entries of Under 1,000.

Register entry

Telegram ID-1003848078805
TypeChannel
Username@agentmademedothis
DescriptionLatest agentic engineering news, freshly delivered directly from my twitter feed. May contain subjective opinions.
CreatedBetween 1 February 2026 and 26 June 2026— estimated from Telegram’s id allocation, not measured. How this range is calculated.
First recorded10 August 2026
Last confirmed live10 August 2026
Measurements held2
On Telegramt.me/agentmademedothis

Growth

686 August 2026 — 68 subscribers10 August 2026 — 68 subscribers6 August 202610 August 2026
2 measurements spanning 3 days. Dots are measurements; the straight line between them is drawn to join them, not to claim we know the path taken in between — snapshots are recorded only when a count changes, so gaps mean “no change observed”, never “interpolated”. The vertical axis spans 67–69 and does not start at zero.
Measurement log — every subscribers count we have recorded
Measured (UTC)SubscribersChange
10 Aug 2026, 01:0068no change
6 Aug 2026, 15:2168first reading

Engagement

18 posts held, back to 26 June 2026the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 pageof Telegram’s post history, 20 posts per page.

ERR · 30 days
95.4%
avg views ÷ 68 subscribers
Avg views / post
64.9
9 posts measured
Reaction rate
2.13%
reactions ÷ views · ER floor
Posts in window
9
of 18 held

ERR is average views per post over the last 30 days divided by subscribers, the definition TGStat uses, so this figure is comparable with the one you will see elsewhere. It falls structurally as a channel grows: a high ERR on a small channel and a low one on a large channel describe reach mathematics, not quality. We publish the figure and the sample it came from and pass no verdict on it.

ER is defined industry-wide as (forwards + reactions + comments) ÷ views— note the denominator is views, not subscribers. Telegram’s public web preview carries views and reactions but not forward or comment counts, so the reaction rate above is the reactions term only and is therefore a floor: the true ER for this channel is higher by an amount we have not measured and will not estimate. It is computed over the 4 of 9 measured posts that carry a reaction reading, and over those same posts' views.

What these figures were computed from
WindowRolling 30 days · latest post in window 4 August 2026
Posts held18 (26 June 20264 August 2026)
Views total584
Reactions total6
Forwards / commentsnot exposed by the public surface — not measured, not estimated
Readings taken10 Aug 2026, 01:00 UTC

Views are a single reading per post, taken at the time above. A post published in the last day or two is still accumulating views, which pulls the 30-day average down slightly. That is a property of the standard definition rather than a fault in it, so we keep the definition rather than “correcting” the number into something nobody can reproduce.

Precision. Telegram publishes view counts on its public widget in short form — 8.12K, 3.7M — so any reading at or above 1,000 reaches us rounded to three significant figures, and only counts below 1,000 are exact. Averages and rates derived from them are shown to the same precision rather than to the unit: a figure like 3,701,250 would assert digits nobody measured.

Reaction counts are published per emoji and rounded the same way, so a total below 1,000 is exact and a larger one is a sum that may carry a rounded component from each emoji above 1,000. Because it is a sum, it does not look rounded — read a large reaction total as three significant figures per contributing emoji rather than as the figure it prints.

What this channel posts

Photos
68
Videos
2
Links
104

Lifetime counters from Telegram’s own channel header, read 10 August 2026 — not the date at the top of this page, which is when the subscriber count was last read. Below Telegram’s rounding threshold, so these counts are exact.

Reaction mix

13 reactions across 9 posts, in 7 distinct kinds. The most used accounts for 30.8% of them.

Every reaction kind recorded on the sample, most used first
ReactionCountShareShare, drawn
👍430.8%
🤔323.1%
215.4%
👨‍💻17.69%
💋17.69%
🔥17.69%
🥰17.69%

No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.

Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.

Coverage. Reactions were read on 10 of the 18 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 13reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.

Measured over the 18 most recent posts we hold, published 26 June 2026 to 4 August 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.

Recent posts

4 Aug 2026, 08:34 UTC42 viewsread 10 August 2026
Photo

Amazing technical details on how GPT-Live works https://openai.com/index/continuous-voice-interaction-with-gpt-live/

31 Jul 2026, 21:57 UTC65 viewsread 10 August 2026
Photo

Yes https://manifest.build/blog/why-we-deprecated-our-llm-router/

30 Jul 2026, 18:45 UTC62 views3 reactionsread 10 August 2026
Photo

Luna is sooo underrated! And today it got even better with 80% off!

🤔3

24 Jul 2026, 08:03 UTC84 views1 reactionsread 10 August 2026
Photo

GPT-Live is now in Codex, and I feel very much like Thomas here. Even more crazy when you can start this conversation on your phone using Remote and just orchestrate treads or projects, ask to interact with computer using Browser Use and Computer Use. Life-changing experience.

1

22 Jul 2026, 17:20 UTC68 views1 reactionsread 10 August 2026

Happy pi approximation day! Using Codex might feel like magic when it comes to compaction - it is by far more superior than any other compaction technique I saw so far. And if you use GPT models in pi, you don’t inherit this compaction by default - you use pi’s compaction or write your own. https://github.com/algal/pi-openai-server-compaction - this extension uses proprietary Codex compaction endpoint, and basical

1

18 Jul 2026, 06:46 UTC69 viewsread 10 August 2026

You can now use Amp with a subscription! Amp is usually referred to as “the porsche in the coding agents’ space”. Before, the only way one could experience it was using API tokens in a pay-as-you-go model. Now, for $20/month, you can take your existing Codex or Grok subscription and use it inside Amp. I’m definitely subscribing, will you? https://ampcode.com/news/subscriptions

15 Jul 2026, 20:12 UTC68 views1 reactionsread 10 August 2026

For those who’re wondering what is this no-name lab and why it’s important: Thinking Machines Lab - AI startup founded by Mira Murati, former CTO at OpenAI, in February 2025, and immediately raised $2B from A16Z 🤓

👨‍💻1

15 Jul 2026, 20:06 UTC61 viewsread 10 August 2026
Photo

Thinking Machines released their first model - Inkling Open weights, multimodal (text, image, audio), and interestingly - “continuous thinking effort” Inkling supports controllable thinking effort, allowing you to balance performance with token efficiency. On benchmarks it sets somewhere around K2.6, some are speculating that this model checkpoint is set specifically to be in the perfect place for post training to

12 Jul 2026, 18:27 UTC76 views1 reactionsread 10 August 2026

If you’re bored on Sunday night: - Claude Code gets 50% more weekly limit + Fable until July 19 - Codex temporarily drops 5h limits and usage gets reset in the next hour

💋1

11 Jul 2026, 09:11 UTC75 viewsread 10 August 2026
Photo

GPT-5.6 Sol and Luna are ahead of Terra at every point on the Intelligence vs Cost per Task chart. GPT-5.6 Luna stands out as a particularly cost efficient model Charting the Artificial Analysis Intelligence Index shows the trade-off between intelligence and Cost per Intelligence Index Task. Across reasoning efforts, each GPT-5.6 model pushes past GPT-5.5 on the Pareto frontier (excluding non-reasoning). However, L

9 Jul 2026, 17:40 UTC64 viewsread 10 August 2026
Photo

GPT 5.6 is here Early feedback from testing - the model is extremely eager to finish the task, "it's like /goal on every prompt" New "Ultra" mode that uses multi-agent architecture to achieve better results faster Fun fact - Luna was post-trained by Sol https://openai.com/index/gpt-5-6/

Showing the 12 most recent of 18 posts we hold for @agentmademedothis. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.

Citation-graph rank

Citation-graph rank — 252,334 of 1,183,361entries in the measured graph. A weighted position computed from the forward and mention edges below — republished posts weigh more than named mentions — and recomputed periodically, over the whole graph. Published only as this ordinal position, never as a score: a position is a fact, and a score printed beside one channel’s name would read as a verdict this register does not make. The two counts beneath stay separate for the same reason mentions are never summed with forwards anywhere else on this page — a named-by count costs nothing to manufacture. The top 100 by this measure, or how it is computed.

Mentions

Named by 1 registered channel — every channel on the register whose own posts have named this one, by its current username or any other username it currently holds, merged from two separately captured readings of the same fact so a namer caught by only one of them is not missed and a namer both caught is not counted twice. A username this channel has since dropped is not matched — that handle may belong to someone else now, and crediting today’s namer to yesterday’s owner would misattribute it.

Named by

Channels on the register whose posts name this channel's handle.

A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.

Cite this entry

A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 10 August 2026 — this entry's latest reading, not the date you are reading this.

“Agent made me do this” (@agentmademedothis), 68 subscribers as measured 10 August 2026. Telegram Register, tgregister.com/channel/agentmademedothis.

Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.