tweetindex
TH

Jared Palmer ✓

@jaredpalmer · New York, NY · joined 05 Jun 2009

VP of Engineering @Cognition Previously: VP Eng @Microsoft. VP of AI @Vercel, Creator of @v0 and @aisdk, Founder of @Turborepo (acquired by Vercel)

110 891Followers
2 834Following
12 492Posts total
808.4KViews on collected posts

โพสต์ล่าสุด

@jaredpalmer try also with qwen 35BA3B - it has vision which is imo the thing that's really importantly missing from jev atm, i did a run on this earlier and it seems to be good 3.9K views · 54 likes · 0 reposts · 2 replies Open on X →
Kev-0.5B is now available on Hugging Face https://t.co/2B8cp3dX1K 5.9K views · 59 likes · 5 reposts · 3 replies Open on X →
Here's a little demo of Kev-0.5B running locally on my MacBook Pro M5 playing Chess against itself (h/t @nutlope for the demo idea) https://t.co/LPchbzIWRw
0:38
9K views · 64 likes · 2 reposts · 8 replies Open on X →
Kev is a LoRA adapter + a small readout head on top of Qwen2.5-0.5B. It reads a document once and answers many typed questions about it in parallel, in a single prefill pass with no decoding. The doc and every question are packed into one sequence. A block-causal mask lets each 11.9K views · 98 likes · 6 reposts · 9 replies Open on X →
Kev-0.5B: A tiny open source Jev-like decision model with a TypeSafe-compatible API based on Qwen2.5-0.5B that you can train and run on a MacBook Pro. Model card and weights are available on GitHub https://t.co/53wZQYhhmu https://t.co/6BXJQ8rSHt
405K views · 2.6K likes · 203 reposts · 92 replies Open on X →
Devin Fusion is my personal daily driver along with many of our biggest enterprise customers. By pairing frontier models together in an ensemble (planning vs. execution), Devin can deliver similar performance at a significantly cheaper price tag. 10.2K views · 87 likes · 10 reposts · 9 replies Open on X →
In Devin Fusion, we pair frontier models for planning with cost-effective models for execution. With Fable 5.1, this orchestration performs even better. We highly recommend Fusion as a cost-effective way to access frontier intelligence. https://t.co/unuQF6WS05 25K views · 71 likes · 4 reposts · 2 replies Open on X →
Proud of the team on this one. The new Devin CLI model picker lets you see your available models, compare cost, and easily switch effort levels 20.3K views · 202 likes · 5 reposts · 22 replies Open on X →
We rolled out support for GLM 5.3 Flash along with an improved model picker UX in Devin CLI. ⚡ Devin now supports: GLM-5.3, 5.3 Flash, 5.2 Claude Fable, Haiku, Opus, Sonnet GPT-5.6 Sol, Luna, Terra + others DeepSeek V4 Flash, Pro SWE-1.7, 1.6 Gemini 3.7 Flash Grok 4.6, 4.5 https 89.1K views · 542 likes · 41 reposts · 64 replies Open on X →
Kind of wild that everyone (including Meta itself with Hatch) is basically rebuilding Facebook M assistant from 2015. Zuck was 11 years too early. https://t.co/KPb8xQAC63 104.7K views · 401 likes · 12 reposts · 22 replies Open on X →
btw since Allbirds has pivoted into an AI compute company, we are actually in need of a new office slipper vendor if anyone has any suggestions 86.1K views · 300 likes · 3 reposts · 28 replies Open on X →
We launched a new startup program to give your team $65,000 in @DevinAI credits and grants along with dedicated support from our team Apply here: ↳ https://t.co/FTcZFzId0p https://t.co/T7dp4VBS47 37.2K views · 384 likes · 18 reposts · 33 replies Open on X →

เทียบกับบัญชีขนาดเดียวกัน

12 โพสต์จาก 90 วันที่ผ่านมา เทียบกับช่วง 100K–1M ผู้ติดตาม แสดงต่อคนมากกว่าบัญชีขนาดเดียวกัน.

ยอดดูมัธยฐาน22 641บัญชีนี้5 983ค่ามัธยฐานของ 100K–1M
การเข้าถึง, %20.42%บัญชีนี้1.49%ค่ามัธยฐานของ 100K–1M
การมีส่วนร่วม, %0.89%บัญชีนี้0.93%ค่ามัธยฐานของ 100K–1M
ตัวชี้วัดบัญชีนี้ค่ามัธยฐานของ 100K–1Mอัตราส่วน
ยอดดูมัธยฐานต่อโพสต์22 6415 9833.78×
การเข้าถึง (ยอดดู ÷ ผู้ติดตาม)20.42%1.49%13.7×
อัตราการมีส่วนร่วม0.89%0.93%0.95×

บัญชีอื่นในช่วงนี้ →   เปรียบเทียบกับบัญชีอื่น →   ค่าอ้างอิงเหล่านี้คำนวณอย่างไร →

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

37.2K26 Aug
86.1K28 Aug
104.7K
89.1K31 Aug
20.3K
25K1 Sep
10.2K
405K18 Sep
11.9K
9K
5.9K
3.9K

Last 12 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.18%26 Aug
0.39%28 Aug
0.42%
0.74%31 Aug
1.13%
0.32%1 Sep
1.04%
0.73%18 Sep
0.95%
0.82%
1.13%
1.44%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 100K–1M accounts is 0.93%.

What the audience does

Likes57.2%4 861 in total
Reposts3.6%309 in total
Replies3.5%294 in total
Quotes1.2%104 in total
Bookmarks34.5%2 934 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.

บัญชีที่คล้ายกัน