Archive

archive archive archive
2026

Claude and Codex subscriptions, now driving an R agent


Tinyverse Toolchain: Updates and Thanks


mx.client 0.1.1: using the Matrix protocol from R


corteza 0.6.9: The R agent harness hits its stride


R as CLI Agent Harness


tinytorch, torchlang, ariel | Deep Learning in R

A Linux-only libtorch wrapper, an R-side torch compiler, and a Triton backend.


saber | LLMs Work on Tokens, Code Lives in Trees

The structural gap at the heart of AI-assisted programming


The Tinyverse Development Toolchain


Text-to-Speech in R


Speech-to-Text in R


2025

Throwback Thursdays!


Chistes4Children - Jokes for Kids!


Introducing diffuseR


2024

Consulting


Every week Lil' Casey counts down the hits!


Introducing cornball.ai

The future of AI is here


0001

write_wav


write_audio


whisper_tokenizer


whisper_dtype


whisper_device


whisper_config


vram_report


voices


voice_upload


vocab_size


vae_decoder_native


use_fyi_md


use_fyi_hugo


use_fyi_docs


uninstall_cli


unigram_tokenizer


unet_sdxl_native_from_torchscript


unet_sdxl_native


unet_native_from_torchscript


unet_native


txt2vid_ltx2


txt2img_sdxl


txt2img_sd21


txt2img_flux2


txt2img_flux


txt2img


tts_voices


tts_to_file


tts_providers


tts_health


tts_chunked


tts


transcribe


tokenize_gemma3


text_to_tokens


text_encoder2_native


text_encoder_native


task_update


task_runs


task_resume


task_pause


task_list


task_get


task_delete


task_create


t5_encoder


t3_inference


symbols


submit_cran


subagent_spawn


subagent_query


subagent_list


subagent_kill


stt_health


stt


speech_design


speech_clone


skill_test


skill_remove


skill_list_installed


skill_install


set_tts_key


set_tts_base


set_stt_key


set_stt_base


set_elevenlabs_key


serve


sdxl_memory_profile


scheduler_run_once


scheduler_daemon


scheduler_add_noise


save_video_ltx23


save_video


save_image


save_frames


s3_tokenizer


run_app


run_app


rformat_file


rformat_dir


rformat


resample_audio


remove_sys


reload


read_torch_pt


read_safetensors


read_audio


qwen3_encoder


qwen3_available


qwen_bpe_tokenizer


quick_tts


quant_conv


projects


preprocess_image


post_quant_conv


pkg_internals


pkg_help


pkg_exports


offload_to_cpu


models2devices


models_available


model_exists


memory_stats


memory_search_fts


memory_import_claude


manager


maintainer


ltx23_vocoder_with_bwe


ltx23_vocoder_resblock


ltx23_vocoder


ltx23_video_vae


ltx23_video_upsampler3d


ltx23_video_up_block3d


ltx23_video_resnet_block3d


ltx23_video_mid_block3d


ltx23_video_encoder3d


ltx23_video_downsampler3d


ltx23_video_down_block3d


ltx23_video_decoder3d


ltx23_upsample1d


ltx23_tune_gc


ltx23_transformer_block


ltx23_transformer


ltx23_tone_map_latents


ltx23_text_connectors


ltx23_stage2_distilled_sigmas


ltx23_split_keys


ltx23_snake_beta


ltx23_set_attn_chunk


ltx23_rotary_pos_embed_1d


ltx23_rotary_pos_embed


ltx23_rms_norm


ltx23_release_dequant_buffers


ltx23_read_tail_frames


ltx23_read_audio


ltx23_quantize_nf4


ltx23_quantize_fp8


ltx23_preprocess_frames


ltx23_prepare_conditioned_latents


ltx23_per_token_rms_norm


ltx23_per_channel_rms_norm


ltx23_open_fp8_checkpoint


ltx23_open_checkpoint


ltx23_normalize_latents


ltx23_nf4_quantize


ltx23_nf4_linear


ltx23_nf4_dequantize


ltx23_memory_profile


ltx23_mel_stft


ltx23_map_vocoder_key


ltx23_map_vae_key


ltx23_map_dit_key


ltx23_map_connector_key


ltx23_map_audio_vae_key


ltx23_load_upsampler


ltx23_load_transformer_nf4


ltx23_load_transformer_fp8


ltx23_load_pipeline


ltx23_load_group


ltx23_latent_upsampler


ltx23_kaiser_sinc_filter1d


ltx23_is_fp8_cast_key


ltx23_get_timestep_embedding


ltx23_fp8_linear


ltx23_feed_forward


ltx23_encode_video_frames


ltx23_encode_audio


ltx23_downsample1d


ltx23_distilled_sigmas


ltx23_denormalize_latents


ltx23_connector_transformer_1d


ltx23_census


ltx23_causal_conv3d


ltx23_audio_vae


ltx23_audio_upsample


ltx23_audio_resnet_block


ltx23_audio_mel_frontend


ltx23_audio_encoder


ltx23_audio_downsample


ltx23_audio_decoder


ltx23_audio_causal_conv2d


ltx23_attention


ltx23_apply_split_rotary_emb


ltx23_apply_interleaved_rotary_emb


ltx23_antialias_act1d


ltx23_adain_filter_latent


ltx23_ada_layer_norm_single


load_whisper_model


load_unet_weights


load_unet_sdxl_weights


load_to_gpu


load_text_encoder2_weights


load_text_encoder_weights


load_text_encoder_safetensors


load_t5_text_encoder


load_s3tokenizer_weights


load_s3gen_weights


load_s3gen


load_qwen3_text_encoder


load_pipeline


load_model_component


load_hifigan_weights


load_gemma3_text_encoder


load_flux2_vae_decoder


load_decoder_weights


load_decoder_safetensors


load_chatterbox


load_campplus_weights


load_bpe_tokenizer


load_audio


load_all


list_whisper_models


list_downloaded_models


latents_to_video


languages


is_blackwell_gpu


install_sys


install_cli


install


img2img


get_model_paths


generate


gemma3_tokenizer


gemma3_text_model


gemma3_config_ltx2


fyi_options


fyi_internals


fyi_help_topics


fyi_help


fyi_exports


fyi_docs


fyi_cache_path


fyi_cache


fyi


flux2_vae_decoder


flux2_unpatchify_latents


flux2_unpack_latents_with_ids


flux2_transformer


flux2_single_block


flux2_prepare_text_ids


flux2_prepare_latent_ids


flux2_patchify_latents


flux2_parallel_self_attention


flux2_pack_latents


flux2_modulation


flux2_load_pipeline


flux2_is_quant_key


flux2_feed_forward


flux2_empirical_mu


flux2_double_block


flux2_bn_normalize


flux_unpack_latents


flux_transformer


flux_single_block


flux_quantize


flux_prepare_latent_image_ids


flux_pos_embed


flux_pack_latents


flux_open_quantized


flux_open_checkpoint


flux_memory_profile


flux_load_transformer


flux_load_pipeline


flux_is_quant_key


flux_double_block


flux_attention


flux_apply_rotary_emb


flux_ada_layer_norm_zero_single


flux_ada_layer_norm_zero


flux_ada_layer_norm_continuous


flowmatch_set_timesteps


flowmatch_scheduler_step


flowmatch_scheduler_create


flowmatch_scale_noise


flowmatch_calculate_shift


fix_description_cran


find_downstream


filename_from_prompt


encode_with_t5


encode_with_qwen3


encode_with_gemma3


encode_unigram


encode_qwen


encode_bpe


enable


elevenlabs_voices


elevenlabs_voice_upload


elevenlabs_voice_delete


download_whisper_model


download_model


download_ltx2


download_flux2_klein


download_flux1


download_component


download_chatterbox_models


document


disable


default_exclude


decode_tokens


decode_bpe


ddim_scheduler_step


ddim_scheduler_create


create_voice_embedding


create_s3gen_vocoder


compute_xvector_embedding


compute_speaker_embedding


compute_mel_spectrogram_ve


compute_mel_spectrogram


CLIPTokenizer


clip_pooled_output


clear_whisper_cache


clear_vram


clear_native_whisper_cache


clear_native_chatterbox_cache


clean


check_win_devel


check_examples_cran


check_description_cran


check_cran


check_code_cran


check


chatterbox_voice_upload


chatterbox_available


chatterbox


chat


build


briefing


bpe_tokenizer


blast_radius


available_sys


auto_devices


audio_to_mel