Sources · Twitter/X

@pvncher

Active

pvncher

Linked items 37
Errors 20
Last fetched 2026-05-05 12:19
Priority P3

Edit

Human-friendly label. Leave blank to fall back to the identifier.

Drives ingestion cadence and the default ranking weight applied to items from this source.

How often the watch loop polls this source. Minimum 5 min. Leave blank for the per-type default.

Optional. Pin a specific summarization model for items from this source.

Cancel

Recent items

The 15 most-recently-ingested items from this source, newest first.

Title Type Fetched
@pvncher: This is pretty nuts article 2026-05-05
@pvncher: Have friends working on this! They actually set it up so you can run whatever agent you like via AC... article 2026-05-04
@pvncher: Try the orchestrate workflow in @RepoPrompt Haseeb >|< (@hosseeb) What's the craziest example of ... article 2026-05-04
@pvncher: The problem with this take is that it neglects how much low hanging fruit there is in optimizing too... article 2026-05-03
@pvncher: This Coding from your phone is the death of work life balance Guido van Rossum (@gvanrossum) Ev... article 2026-05-01
@pvncher: On extremely low bandwidth, ChatGPT is more usable than Google. Kinda nuts article 2026-04-30
@pvncher: Another line "...so we don’t just make the stopwatch happier while hiding a rake in the grass." article 2026-04-28
@pvncher: Gpt 5.5 loves talking about creatures so much that they prompt it out of the model Paxaral (@paxar... article 2026-04-28
@pvncher: GPT 5.5 says the WEIRDEST shit "I’ll keep babysitting it rather than leave a little perf gremlin run... article 2026-04-27
@pvncher: It's super upsetting how shit a mac app optimized to run on macOS 26 looks on macOS 15 article 2026-04-27
@pvncher: Do this with @RepoPrompt ‘optimize’ to orchestrate the loop! Helps keep much better track of baseli... article 2026-04-27
@pvncher: It depends on how you use it. If you want to use GPT 5.5 like Claude Opus, with interactive steerin... article 2026-04-27
@pvncher: New `optimize` workflow in @RepoPrompt cutting latency in speech to text from "900ms to around 250ms... article 2026-04-25
@pvncher: From the @RepoPrompt discord: Deepseek v4 flash is an exceptional model in its weight class. Surpas... article 2026-04-25
@pvncher: This is pretty nuts - it can watch the orchestrator work in the @RepoPrompt ui article 2026-04-25