why does the algo hate this post
@swyx
-
Low-Background Tokens and Vintage Language Models for Quality AI
By
–
> be me
— swyx 🇸🇬 (@swyx) 30 avril 2026
> "the internet is polluted by ai slop, we need low-background tokens"
> "wouldnt it be cool if we could time travel and see what our ancestors 100 years ago would say to us"
> all the existing vintage models are like <4B
> we need a chat tuned 13B vintage model
>… https://t.co/DcXA62Jjnd> be me
> "the internet is polluted by ai slop, we need low-background tokens"
> "wouldnt it be cool if we could time travel and see what our ancestors 100 years ago would say to us"
> all the existing vintage models are like we need a chat tuned 13B vintage model > -
Wikis as Collaborative Tools for Thought and Productivity
By
–
wikis are all you need you have a nice mix of collab tool + tool for thought. . does this have a slack integration? lol i know i know.
-
Base Model Release Sparks Experimentation With API Completions
By
–
i havent done the work to compare it to peers but i'm just excited that we have a base model and honestly for all the people that complained about the death of the completions API (
@deepfates ? or deepfates adjacent) not enough people are experimenting with weird usages and -
Eugene Covers Paper Club on Latent Space Podcast
By
–
eugene is doing a great job covering it on the @latentspacepod paper club (will post on the youtube soon)
-
DeepSeek v4 Demonstrates SOTA Long Context Efficiency Without Benchmarking
By
–
IMO DeepSeek v4 demonstrated utter confidence and competence by not benchmaxxing, not focusing on some BS final run cost, not even spending inference-optimal compute. just showed up, demonstrated SOTA long context efficiency techniques (CSA, HCA, mHC, flash at 8% cost of pro,
-
AIE Now Run by Agents Says Unreleased Talk
By
–
AIE is run by agents at this point. full unreleased talk here
-
Article Quality Issues: Technical Depth and Advertising Concerns
By
–
gentle feedback that the article started strong but also degraded in quality as it went on and being light on technical detail (probably ai written) and came across more like an ad. shouldnt have had to read @mccatec
's comment to get to the crux of the issue.