Tinker ✓

@tinkerapi · San Francisco · joined 05 Jan 2026

I tink, therefore I am. Post-training API by @thinkymachines

14 190Followers

1Following

156Posts total

231.7KViews on collected posts

Against accounts of the same size

7 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.

Median views13 023this account2 751median for 10K–100K

Reach, %91.78%this account9.00%median for 10K–100K

Engagement, %1.07%this account1.65%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	13 023	2 751	4.73×
Reach (views ÷ followers)	91.78%	9.00%	10.2×
Engagement rate	1.07%	1.65%	0.65×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

64.2K9 Apr

60K27 Aug

13K

8.1K28 Aug

45.1K31 Aug

37.6K

2.4K2 Sep

1.2K3 Sep

Last 8 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.54%9 Apr

1.07%27 Aug

1.02%

2.06%28 Aug

0.28%31 Aug

0.47%

1.10%2 Sep

2.34%3 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.65%.

What the audience does

Likes70.2%1 413 in total

Reposts7.7%154 in total

Replies2.6%53 in total

Quotes1.1%23 in total

Bookmarks18.3%369 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Latest posts

We previously highlighted @lightningrodai's data recipe for training forecasters. Their new work with @PTetlock and @VSatopaa adds another key piece: choosing the rule for scoring predictions, and how each one trades off accuracy and error. 1.2K views · 23 likes · 4 reposts · 1 replies 03 Sep 2026 New preprint from @lightningrodai, this time with Philip Tetlock and Ville Satopää! We post-train 5 versions of the same LLM, changing only the scoring rule used as the RL reward. Similar aggregate scores, but very different BIN profiles. A good Brier score alone doesn't tell h 2.4K views · 18 likes · 6 reposts · 0 replies 02 Sep 2026 We built Inkling to be fine-tuned, and @besimple_ai did an impressive job of that. Just 25-100 hours of specialized audio takes Inkling to the top rank for recovering subtle details from speech. 37.6K views · 159 likes · 10 reposts · 5 replies 31 Aug 2026 We published how @thinkymachines 's Inkling did on Voice Code Bench few weeks ago, and then we asked, what if we fine-tune Inkling? Inkling's main value prop is its small size and robustness, making it a good base model for domain specific fine-tuning. So we that's what we did. 45.1K views · 98 likes · 16 reposts · 8 replies 31 Aug 2026 GLM-5.3 from @Zai_org is now available on Tinker with 256k context. With scaled up post-training from the same base as GLM-5.2, it is currently the strongest open-weights model on coding evals such as Terminal-Bench 3.0 and DeepSWE 1.1. 8.1K views · 152 likes · 6 reposts · 8 replies 28 Aug 2026 alphaXiv is turning research papers from static artifacts into live research that grows and branches, with agents running their own experiments. Tinker makes running these experiments easy for both agents and people 13K views · 116 likes · 15 reposts · 2 replies 27 Aug 2026 Introducing autoresearch for arXiv papers: replicate and experiment on any arXiv paper using an army of Claude/Codex agents For post-training, your agents can use @tinkerapi to launch concurrent RL runs while you watch your experiment tree grow Try it out now on OpenResearch: h 60K views · 538 likes · 73 reposts · 19 replies 27 Aug 2026 We’ve redesigned our docs with easy access to SDK reference, tutorials, support, and our newly updated cookbook---v0.3.0! Whether you’re writing your first training loop in Tinker or debugging async RL, we want to make it easier to find what you need. 64.2K views · 309 likes · 24 reposts · 10 replies 09 Apr 2026