Meir Dick retweeted
What if scaling the context windows of frontier LLMs is much easier than it sounds?
We’re excited to share our work on Recursive Language Models (RLMs). A new inference strategy where LLMs can decompose and recursively interact with input prompts of seemingly unbounded length, as a REPL environment.
On the OOLONG benchmark, RLMs with GPT-5-mini outperforms GPT-5 by over 110% gains (more than double!) on 132k-token sequences and is cheaper to query on average.
On the BrowseComp-Plus benchmark, RLMs with GPT-5 can take in 10M+ tokens as their “prompt” and answer highly compositional queries without degradation and even better than explicit indexing/retrieval.
We link our blogpost, (still very early!) experiments, and discussion below.
Meir Dick retweeted
an MIT researcher built a realtime LLM vector steering tool and it’s the coolest thing I’ve seen someone build in a very long time.
this is so brilliant. the primary use case I see this realistically used for is long form writing tasks. some might find it controversial, considering it plays into llm-generated writing. however in my opinion it kind of solves for some amount of the tension around the issue by making the process multiplayer in a new way. the human and the AI become collaborators, sort of.
idk this sh*t is so cool though, man.
(@ far__behind on instagram)
Meir Dick retweeted
A brief history of AI Coding since Nov 2025:
Nov 2025: Opus 4.5 releases, OpenClaw gets built
Dec 2025: community agrees that models get good enough to handle 95% of coding tasks
Jan 2026: Ralph loops get popular, early efforts on loops/orchestration
Feb: Everyone feels knackered, too much strategic decision-making, fears around cognitive debt begin
Mar: Skills explosion as community converges around easy-to-share processes (superpowers already ahead of the game here)
Apr: most SOTA devs haven't written a line of code in months
May: "The unreasonable effectiveness of HTML" - more interest in richer review surfaces
Jun: "Loop Engineering" wins vaguepost of the year, signals more hype around process
Jul: Every talk in every conference becomes "here is my software factory"
Aug: Opus 5 speaks incomprehensibly, interest in ASD-STE100 peaks
Sep: Grok Bot gets popular, more interest in long-running "manager" threads which retain context and delegate work
Oct: The promised speed gains haven't materialised, "dark factory" feels a long way off still
Nov: No-slop manifesto releases, reading the code still appears essential
TL;DR: no-one is writing code anymore, and we are still figuring out what that means
Meir Dick retweeted
My newest book 'Fine Tuning AI' just came through the mail from O'Reilly
I think this is perhaps the most important book I've ever written. I strongly believe the best future career for many software developers will be in Fine Tuning AI for domain-specific tasks. With this book, I try to simplify it, primarily using Google's Gemma models.
You can find it on Amazon here: link.amazon/B02x2ZVPD
Or O'Reilly Safari here: oreilly.com/library/view/fin…
Thank you so much for your support!
laravel-cf-workersai 1.3.0 adds Cloudflare's Clef and Clairic.
Clef: classification for laravel/ai.
Clairic: typed extraction, one value per field, or null.
github.com/meirdick/laravel-…
@CloudflareDev Workers AI provider for the @laravel AI SDK: text, embeddings, reranking, images, speech, transcription, Clef decisions and Clairic typed extraction, with AI Gateway routing.
Meir Dick retweeted
Laravel Herd 2: Coding Agents, Workspaces, and Cloud Deploys posted by @ericlbarnes laravel-news.com/laravel-her…
Anyone at @CloudflareDev tried @AmpCode orbs? Want them self-hosted on Workers? Try cf-orbs: github.com/meirdick/cf-orbs
Part of the goal: prove Workers + Containers can do long-lived pause/resume for agent workflows. Disk snapshot on pause, 2.3 s wake.
@michellechen @acoyfellow @dillon_mulroy
1
42
Meir Dick retweeted
Yea. this is exactly as crazy as it seems.
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
Meir Dick retweeted
You're not a real engineer if you don't have a mystery $0.53 AWS bill coming from a rogue service in perpetuity.
Meir Dick retweeted
everything you need to know about clairic is in this video
Today we introduced a novel system one model, Clairic, based on regression instead of classification (i.e. decision models like Clef). This enables estimation of continuous values without having to exhaustively list choices upfront. It also enables very efficient extraction of structured data from unstructured inputs. Open weights coming soon!
General-purpose classification: Jev
General-purpose regression: Clairic
General-purpose anomaly detection: ?
General-purpose clustering: ?
General-purpose density estimation: ?
General-purpose dimension reduction: ?
Today we introduced a novel system one model, Clairic, based on regression instead of classification (i.e. decision models like Clef). This enables estimation of continuous values without having to exhaustively list choices upfront. It also enables very efficient extraction of structured data from unstructured inputs. Open weights coming soon!
Meir Dick retweeted
a brand new model paradigm! introducing 𝚌𝚕𝚊𝚒𝚛𝚒𝚌: a system one model for extracting, computing, estimating, and predicting values from unstructured inputs.
blog.cloudflare.com/clairic-…
Meir Dick retweeted
we shipped a new type of model: an extraction model!
pass it unstructured data, and get a list of the details and probability back. try it out and let us know what you think!
blog.cloudflare.com/clairic-…
Meir Dick retweeted
Function calling without waiting for Enter. Answers only when needed.
@typesafeai Jev understands intent and arguments as you type, then executes ahead of time once everything is in place.
My human values test result: idrlabs.com/human-values/58-… via @idr_labs
1
22
Introducing GLM-5.3-Flash
- Leading capabilities at a highly competitive price
- Natively multimodal with a 1M-token context window
- A 320B-A18B model released under the MIT License
- Previously previewed as Ox Alpha, running entirely on Chinese AI chips
Blog: z.ai/blog/glm-5.3-flash
Available now across all official platforms:
Weights: huggingface.co/zai-org/GLM-5…
API: docs.z.ai/guides/llm/glm-5.3…
Coding Plan: z.ai/subscribe
ZCode: zcode.z.ai/en
Chat: chat.z.ai
AutoClaw: autoclaw.z.ai
This might be the most beautiful thing I've read in my life. What a privilege to be alive in 2026.
ordinaryabundance.com

























