Dontopedia

rjs:longgen

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

rjs:longgen has 16 facts recorded in Dontopedia across 2 references, with 1 live disagreement.

16 facts·14 predicates·2 sources·1 in dispute

Mostly:targets models(2), aims at(1), estimated duration minutes(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (1)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

reportsLaunchInReports Launch in(1)

Other facts (15)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

15 facts
PredicateValueRef
Targets ModelsCode Lm[1]
Targets ModelsDecoder[1]
Aims atLonger Context Training[1]
Estimated Duration Minutes20[1]
Expected to Take~20[1]
Generates Num Samples10[1]
Generates Samples of Codes256[1]
Precedes TemporallyAr Decoder Results[1]
Trains With Context Length512[1]
Trains With Steps8000[1]
Launched innull[1]
Rdf:typeSoftware Configuration[2]
Trains With Longer Context512[2]
Trains With More Steps8000[2]
Has Code Lmtrue[2]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

aimsAtblah/watt-activation/part-299
ex:longer-context-training
estimatedDurationMinutesblah/watt-activation/part-299
20
expectedToTakeblah/watt-activation/part-299
~20
generatesNumSamplesblah/watt-activation/part-299
10
generatesSamplesOfCodesblah/watt-activation/part-299
256
precedesTemporallyblah/watt-activation/part-299
ex:ar-decoder-results
targetsModelsblah/watt-activation/part-299
ex:code-lm
targetsModelsblah/watt-activation/part-299
ex:decoder
trainsWithContextLengthblah/watt-activation/part-299
512
trainsWithStepsblah/watt-activation/part-299
8000
launchedInblah/watt-activation/part-299
null
typeblah/watt-activation/297
ex:SoftwareConfiguration
labelblah/watt-activation/297
rjs:longgen
trainsWithLongerContextblah/watt-activation/297
512
trainsWithMoreStepsblah/watt-activation/297
8000
hasCodeLmblah/watt-activation/297
true

References (2)

2 references
  1. [1]Part 29911 facts
    ctx:discord/blah/watt-activation/part-299
  2. [2]2975 facts
    ctx:discord/blah/watt-activation/297
    • full textwatt-activation-297
      text/plain2 KBdoc:agent/watt-activation-297/ad91f718-f038-464f-a6d2-ba91d77fe4e3
      Show excerpt
      [2026-03-14 05:23] xenonfun: 600K context, the UI crazy scroll thing and memory leaks are annoyin claude is sucking up 6GB now. [2026-03-14 05:24] xenonfun: ``` ⏺ Launched in rjs:longgen. This trains with longer context (512) and more steps

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.