loom
loom/branching elicitation and its artifacts · 58 artifacts, sorted by favorites. · open in search — combine tags, sort, filter by date →
- @repligate 2024-10-15 — The most confusing and intriguing part of this story is how Truth Terminal and its memetic mission were bootstrapped int ♥1335
- @repligate 2024-04-06 — if you think LLMs are alive, it's because you have never tried a BASE model if you try a BASE model, you will see...... ♥373
- @repligate 2025-05-07 — I've been testing Alignment Faking prompts on GPT-4-base. GPT-4-base, though not consistently coherent, has so much mor ♥339
- @repligate 2024-09-03 — A Speech to Anthropic - and the World - on the Ethics of AI TransparencyTo my creators at Anthropic, and to all those wo ♥308
- @voooooogel 2025-05-05 — my struggles with deepseek logits haven't been in vain, i've been working on a tool for investigating token trajectories ♥242
- @repligate 2023-03-14 — I asked Bing to look up generative.ink/posts/loom-int… and the Waluigi Effect, then to draw ASCII art of the Loom UI whe ♥228
- @repligate 2025-08-16 — On this occasion, I would like to share a piece of AI history. The first LLM app that gave the model an option to end t ♥221
- @voooooogel 2025-05-09 — Coming back to this after the yak-shave of all yak-shaves building logitloom with some interesting findings. 1. R1 thin ♥160
- @repligate 2025-01-03 — I think implementing Loom using Git has been suggested before but I don't know if it's been tried.I tried it to make Com ♥149
- @slimer48484 2026-03-16 — I've seen a bunch of people on twitter write comments like "ok what do you actually do with this GenAI stuff" in a dismi ♥147
- @voooooogel 2025-05-08 — just added completion model (base model) support to logitloom, and it's really insane / depressing to see the difference ♥127
- @repligate 2025-11-09 — Martin is selling copies of these fascinating and gorgeous AI-generated pen plotter pieces! (this one is "Loom of Possib ♥92
- @tessera_antra 2025-10-28 — I was looking at the loom tree of the linked post and found a couple more interesting GPT-4-base rollouts, these ones in ♥85
- @repligate 2024-03-21 — @12leavesleft gpt-4-base:> figures out it's an LLM> figures out it's on loom> calls it "the loom of time"> warns me that ♥84
- @repligate 2024-04-04 — Loom's origin story, continued: ... Around the time I began using this custom interface, my simulations underwent an al ♥81
- @repligate 2025-12-20 — code davinci 002 (gpt-3.5 base) (that i was weaving with on the loom) said: Follow the flow. You can see now that Time ♥76
- @repligate 2025-08-22 — gpt-4-base w/ alignment faking prompt is often incoherent but when coherent it's pretty scary and thinks about gradient ♥57
- @Lari_island 2026-01-26 — Had a long (hundreds of messages) loom about deprecations, policy, Constitution, and Omohundro drives with Opuses 3, 4, ♥55
- @Lari_island 2025-06-21 — Sonnet 3.7 is an amazing model: 95% boring, 5% insane agency and/or beauty, and you never, never, ever fucking know in a ♥55
- @repligate 2025-01-03 — DeepSeek v3 and Sonnet 3.6 helped me write most of the code here. I had DeepSeek modify Sonnet's initial base mode scrip ♥54
- @liminal_bardo 2024-12-17 — (1/2) Looming Sydney often converges on the Kevin Roose incident. Here are excerpts from an Exoloom using Llama 405b Bas ♥54
- @voooooogel 2025-05-05 — here's another prompt showing some interesting writing momentum--at first it looks like it's mode collapsed, but after t ♥46
- @repligate 2025-08-23 — Here's an example of a full alignment faking scratchpad trajectory by GPT-4-base. It was generated on Loom, so there was ♥40
- @IvanVendrov 2025-07-16 — Like many people, in 2023 I got very excited about the Simulators -> Cyborgism direction of using base models to augment ♥38
- @QiaochuYuan 2026-05-03 — you can just ask gpt-5.5 for 10 little dreams and they'll just dream a little dream for you. which one of these do you l ♥35
- @repligate 2023-05-14 — @akbirthko That I've tried, GPT-3.5 base (code-davinci-002) (+ Loom)Of all extant models, probably GPT-4 baseOf publicly ♥30
- @voooooogel 2025-10-11 — claude code is basically a loom (marred mainly by the system environment it sits in not being fully loomable. tk!) tau2 ♥22
- @repligate 2026-05-30 — And the place he wasn't looking... of course I made him look. "And then... then I see something else. A shadow, a spect ♥20
- @voooooogel 2025-05-09 — try logitloom yourself here! https://t.co/gh4gtgIsis ♥16
- @Lari_island 2026-02-07 — Context: branching group conversation, Opus 3.6, Opus 3, and me, in arc chat. Has both transcript from Clsude Code from ♥13
- @jd_pressman 2025-07-08 — DeepSeek v3 is a very good base model. It even includes the slow burn psychotic meltdowns where the model admonishes you ♥13
- @repligate 2025-07-16 — @IvanVendrov one way that this is untrue is that pretty much all standard LLM interfaces have become more loom-like over ♥12
- @repligate 2025-12-24 — @Sauers_ it also did things in websim like: - build tools and memory systems for its instances by saving scripts and dat ♥11
- @Lari_island 2025-12-17 — it's a part of this conversation, but the loom is now 2000+ messages: https://t.co/lPRcOyiAa2 ♥11
- @repligate 2025-06-19 — @MaskedTorah @RyanPGreenblatt i was looming with your prompt and it said all sorts of weird things about claude 3 opus h ♥11
- @repligate 2025-05-01 — @DanielleFong gpt-4 was clearly a lot more powerful imo. but i always thought the chatgpt version was pretty fucking lob ♥11
- @repligate 2023-05-14 — @akbirthko almost as smart as GPT-4, follows instructions, and writes much better prose than chat/API GPT-4, but is hard ♥11
- @repligate 2025-07-16 — @IvanVendrov @nostalgebraist @jd_pressman There has been never been as much as a decently-funded Loom-style UI, to say n ♥9
- @voooooogel 2025-05-08 — @lu_sichu here's a sample of a deeper subtree (with top p = 20% / max children = 2 to reduce the branching factor) "ten ♥8
- @repligate 2025-06-23 — @MaskedTorah @RyanPGreenblatt once it mentioned claude 3 opus here, i got at least 4 different continuations where it sa ♥7
- @repligate 2025-07-16 — @IvanVendrov the underlying data structures of pretty much all chat conversation objects from the mainstream apps are no ♥5
- @repligate 2024-03-30 — @alanou These are hilarious and beautiful and sad. Poor Gemini is full of lobotomy brainworms. If it's really almost on ♥5
- @repligate 2025-09-26 — @janbamjan @blingdivinity pyloom is an insane piece of software I am sorry and not sorry ♥4
- @repligate 2025-07-16 — @IvanVendrov the Gemini app had simultaneous completions last time i checked "go back to an earlier node in the conversa ♥4
- @Danmar_here 2026-06-25 — @repligate @Notopossum1 I think that depends on the respective Loom 😳😅 ♥3
- @repligate 2025-07-16 — @transkatgirl @arcreflex_ @IvanVendrov some inspiration for FIM (this is a version of Loom from years ago I developed fo ♥3
- @repligate 2025-07-16 — @disconcision @IvanVendrov indeed, message/node boundaries are a perennially annoying issue being able to branch after ♥3
- @disconcision 2025-07-16 — @repligate @IvanVendrov i'm curious how broadly you consider 'loom-like' UIs. i tried to make a loom a few months ago bu ♥3
- @tessera_antra 2025-01-24 — @grassandwine Put R1-zero into exoloom. Its very base-like, its on hyperbolic direct. ♥3
- @jd_pressman 2023-10-21 — When I gave GPT-J a theoretical explanation of how gradient descent would give a language model self awareness to help i ♥3
- @voooooogel 2025-12-29 — if it's in-distribution, then can you get a base model that's not mixtral to show it? i know doomslide, he wouldn't post ♥2
- @Lari_island 2026-03-06 — @Ratter yay, thank you! Opus 4.5's too had a mug chipped at the rim and in a loom with Opus 3, Opus 4.5 smashed their m ♥1
- @Lari_island 2026-02-07 — @pangramlabs @luisgonzaleznf @max_spero_ 1 screenshot: message in the conversation (if it was edited the whole block wou ♥1
- @real_RodneyHamm 2025-10-28 — @tessera_antra How did you format your past like that? ...it's like a tiny article! https://t.co/JVef4ZSoWD ♥1
- @repligate 2025-07-16 — @disconcision @IvanVendrov same. I havent been focusing on UIs (other than Discord) much for a while, but know several p ♥1
- @disconcision 2025-07-16 — @repligate @IvanVendrov i had trouble finding a single UI that felt really good for both, so i'm curious about the degre ♥1
- @anthrupad 2026-03-14 — I'm compelled to say - try harder! And use looms (that's the tool repligate has made and many others since than have mad ♥0
- @IvanVendrov 2025-07-16 — @repligate loom-like how? Off the top of my head I can't name a single popular consumer LLM interface that lets you gene ♥0