This daily picks page was compiled by the Postprint pipeline on 2026-10-06 (Asia/Shanghai). Sampling covers 20 public X accounts (including @pmarca, @balajis, @karpathy, @paulg, @sama, @naval and others) through the public read-only FxTwitter API — this is an account-pool observation, not an X-wide ranking. Today's sampling observed 119 items; 3 of them were newly verified and published on this site today; 2 were excluded by our editorial content filter. Entries below are ordered by a composite pick score (likes + 2×reposts + 3×bookmarks + 0.001×views) and presented as editorial selections. All interaction numbers are real sampled values shown with their collection time (2026-10-06 UTC); metrics we could not collect are omitted, never filled with zeros.
On this page
- 1. We'll be spending a lot more time trying to understand the outputs of language models.
- 2. We're publishing our most detailed threat intelligence report to date.
- 3. One pattern I find useful for working with LLMs is a nice long ramble session.
- 4. This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then…
- 5. A harness for every task: dynamic workflows in Claude Code
- 6. This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other…
- 7. We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle".
- 8. HILTON: $928 Million for Solar Panels Went to Ballot Harvesting
- 9. Introducing gdp-ts: Ghosts of Departed Proofs for TypeScript.
- 10. DHH is fundamentally right about Rust. For context, Vercel has been undergoing a Rust-ification…
1. We'll be spending a lot more time trying to understand the outputs of language models.
Andrej Karpathy (@karpathy) · post · sampled 2026-10-06
53,527 likes6,272 reposts1,532 replies79,283 bookmarks1,399 quotes7,368,619 views
metrics sampled 2026-10-06 (UTC)
What it is: A long X post published on X by Andrej Karpathy (@karpathy), about 1,816 characters of text. It opens with: "We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for…" The headline above is our summary of the post's opening, not the author's own title.
Why it is getting attention: From these sampled numbers, the sampled view count (7,368,619) suggests it reached a wide audience within this account pool; the sampled like count (53,527) is well above the rest of today's sample. This is an editorial observation based on publicly visible metrics, not an official ranking or platform conclusion.
Original on X ↗ Export it with Postprint →
2. We're publishing our most detailed threat intelligence report to date.
Anthropic (@AnthropicAI) · post · sampled 2026-10-06
50,532 likes11,716 reposts3,233 replies41,925 bookmarks4,931 quotes43,750,943 views
metrics sampled 2026-10-06 (UTC)
What it is: A long X post published on X by Anthropic (@AnthropicAI), about 936 characters of text. It opens with: "We're publishing our most detailed threat intelligence report to date. It covers how people tried to misuse Claude—for cyberattacks, influence operations, surveillance, biology, and building weapons—and how we found and stopped them. We disrupted every operation in the…" The headline above is our summary of the post's opening, not the author's own title.
Why it is getting attention: From these sampled numbers, the sampled view count (43,750,943) suggests it reached a wide audience within this account pool; the sampled like count (50,532) is well above the rest of today's sample. This is an editorial observation based on publicly visible metrics, not an official ranking or platform conclusion.
Original on X ↗ Export it with Postprint →
3. One pattern I find useful for working with LLMs is a nice long ramble session.
Andrej Karpathy (@karpathy) · post · sampled 2026-10-06
50,135 likes4,083 reposts2,523 replies15,123 bookmarks1,490 quotes4,369,484 views
metrics sampled 2026-10-06 (UTC)
What it is: A long X post published on X by Andrej Karpathy (@karpathy), about 797 characters of text. It opens with: "One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10…" The headline above is our summary of the post's opening, not the author's own title.
Why it is getting attention: From these sampled numbers, the sampled view count (4,369,484) suggests it reached a wide audience within this account pool; the sampled like count (50,135) is well above the rest of today's sample. This is an editorial observation based on publicly visible metrics, not an official ranking or platform conclusion.
Original on X ↗ Export it with Postprint →
4. This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then…
Andrej Karpathy (@karpathy) · post · sampled 2026-10-06
19,434 likes2,030 reposts1,053 replies21,477 bookmarks484 quotes4,071,861 views
metrics sampled 2026-10-06 (UTC)
What it is: A long X post published on X by Andrej Karpathy (@karpathy), about 1,916 characters of text. It opens with: "This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the…" The headline above is our summary of the post's opening, not the author's own title.
Why it is getting attention: From these sampled numbers, the sampled view count (4,071,861) suggests it reached a wide audience within this account pool; the sampled like count (19,434) is well above the rest of today's sample. This is an editorial observation based on publicly visible metrics, not an official ranking or platform conclusion.
Original on X ↗ Export it with Postprint →
5. A harness for every task: dynamic workflows in Claude Code
Thariq (@trq212) · article · sampled 2026-10-06
11,045 likes1,464 reposts276 replies24,785 bookmarks307 quotes3,392,982 views
metrics sampled 2026-10-06 (UTC)
What it is: A long-form X article published on X by Thariq (@trq212). It opens with: "Last week, we released dynamic workflows in Claude Code. Claude can now write its own harness on the fly, custom-built for the task at hand. While the default Claude Code harness is built for coding,"
Why it is getting attention: From these sampled numbers, the sampled view count (3,392,982) suggests it reached a wide audience within this account pool; the sampled like count (11,045) is well above the rest of today's sample. This is an editorial observation based on publicly visible metrics, not an official ranking or platform conclusion.
Original on X ↗ Export it with Postprint →
6. This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other…
Andrej Karpathy (@karpathy) · post · sampled 2026-10-06
23,519 likes1,946 reposts1,383 replies13,941 bookmarks706 quotes8,406,377 views
metrics sampled 2026-10-06 (UTC)
What it is: A long X post published on X by Andrej Karpathy (@karpathy), about 853 characters of text. It opens with: "This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under the hood engineering work to make this "just work" (e.g. across tools, integrations, compute environments, memory,…" The headline above is our summary of the post's opening, not the author's own title.
Why it is getting attention: From these sampled numbers, the sampled view count (8,406,377) suggests it reached a wide audience within this account pool; the sampled like count (23,519) is well above the rest of today's sample. This is an editorial observation based on publicly visible metrics, not an official ranking or platform conclusion.
Original on X ↗ Export it with Postprint →
7. We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle".
Andrej Karpathy (@karpathy) · post · sampled 2026-10-06
29,599 likes2,311 reposts1,795 replies12,111 bookmarks743 quotes6,113,747 views
metrics sampled 2026-10-06 (UTC)
What it is: A long X post published on X by Andrej Karpathy (@karpathy), about 1,605 characters of text. It opens with: "We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for…" The headline above is our summary of the post's opening, not the author's own title.
Why it is getting attention: From these sampled numbers, the sampled view count (6,113,747) suggests it reached a wide audience within this account pool; the sampled like count (29,599) is well above the rest of today's sample. This is an editorial observation based on publicly visible metrics, not an official ranking or platform conclusion.
Original on X ↗ Export it with Postprint →
8. HILTON: $928 Million for Solar Panels Went to Ballot Harvesting
UngaTheGreat (@UngaTheGreat) · post · sampled 2026-10-06
16,214 likes6,304 reposts180 replies1,322 bookmarks210 quotes251,170 views
metrics sampled 2026-10-06 (UTC)
What it is: A long X post published on X by UngaTheGreat (@UngaTheGreat), about 460 characters of text. It opens with: "HILTON: $928 Million for Solar Panels Went to Ballot Harvesting"
Why it is getting attention: From these sampled numbers, the sampled view count (251,170) suggests it reached a wide audience within this account pool; the share-to-like ratio suggests many readers found it worth passing along. This is an editorial observation based on publicly visible metrics, not an official ranking or platform conclusion.
Read & export this article on Postprint →
9. Introducing gdp-ts: Ghosts of Departed Proofs for TypeScript.
Guillermo Rauch (@rauchg) · post · sampled 2026-10-06
1,950 likes95 reposts130 replies2,254 bookmarks34 quotes181,785 views
metrics sampled 2026-10-06 (UTC)
What it is: A long X post published on X by Guillermo Rauch (@rauchg), about 1,187 characters of text. It opens with: "Introducing gdp-ts: Ghosts of Departed Proofs for TypeScript."
Why it is getting attention: From these sampled numbers, the sampled view count (181,785) suggests it reached a wide audience within this account pool; the sampled like count (1,950) is well above the rest of today's sample. This is an editorial observation based on publicly visible metrics, not an official ranking or platform conclusion.
Read & export this article on Postprint →
10. DHH is fundamentally right about Rust. For context, Vercel has been undergoing a Rust-ification…
Guillermo Rauch (@rauchg) · post · sampled 2026-10-06
2,970 likes139 reposts169 replies929 bookmarks59 quotes308,701 views
metrics sampled 2026-10-06 (UTC)
What it is: A long X post published on X by Guillermo Rauch (@rauchg), about 1,014 characters of text. It opens with: "DHH is fundamentally right about Rust. For context, Vercel has been undergoing a Rust-ification (carcinization, technically 🦀) for a while."
Why it is getting attention: From these sampled numbers, the sampled view count (308,701) suggests it reached a wide audience within this account pool; the sampled like count (2,970) is well above the rest of today's sample. This is an editorial observation based on publicly visible metrics, not an official ranking or platform conclusion.
Read & export this article on Postprint →
The takeaway
Taken together, today's batch is 10 long-form pieces drawn from the same public-account pool, mostly articles and threads saved and shared by readers. The full, continuously updated collection lives on the trending page, and any X article or thread can be turned into a document with the Postprint tool.
Source coverage: 20 public X accounts sampled via FxTwitter (public, read-only). This page reflects only what those accounts published and what our sampler could verify — it is not affiliated with, endorsed by, or an official ranking of X. Sampling date: 2026-10-06 (Asia/Shanghai). Questions or takedown requests: contact us.
Snapshot note: this page preserves the metrics as sampled on
2026-10-06; later re-runs refresh the same URL for the same day and never rewrite
past days' snapshots.