
Hostile Neural Networks in FTB Skies 2
FTB Skies 2 1.24.0 ships version 6.5.1 · First seen in 1.0.1
Hostile Neural Networks is a mod in FTB Skies 2 1.24.0, where it is version 6.5.1. Simulate Mobs to create not-so-simulated drops! (Summary from the mod's Modrinth page.)
Hostile Neural Networks guide for FTB Skies 2
Last verified for FTB Skies 2 v1.24.0 on Oct 14, 2026 · text last changed Oct 14, 2026
Also applies to:FTB StoneBlock 4 1.4.0 to 1.23.0Project Infinity 0.1 0.0.51.4-hotfix-2
- Sections
- 8
- Recipes shown
- 11
- Items named
- 14
- Quests covered
- 7
Every recipe and number here was checked against FTB Skies 2 1.24.0, read from the running game on Oct 13, 2026.
What is Hostile Neural Networks?
1 part
Hostile Neural Networks lets you simulate mobs and turn the results into their drops, so you don't have to farm or hunt them. It's based on Deep Mob Learning. If you want mob loot on demand, this is the mod for you.[1]
Everything starts with the Data Model, an item that holds information about one entity. You craft a Model Framework, use it on the target entity to build the model, and then train it.[1]
You can train a model in the Deep Learner or in the Simulation Chamber. The Deep Learner holds a few models, and the kills you make train them. Every model starts out Faulty and has to reach Basic in the Deep Learner. From Basic up, the Simulation Chamber can run simulations of it. Those always give a generalized prediction and may also give a Mob Prediction. The chance depends on the model's accuracy, which tops out at 99.5% at Self Aware. A simulation costs energy and needs a catalyst, usually a Prediction Matrix.[1]
Mob Predictions are processed in the Loot Fabricator, which uses power to turn them into mob drops. The drops come from a pre-defined list, and you pick a target for each model type. The fabricator remembers your choice per type, so one machine can handle several kinds of prediction.[1]
Where it fits in the pack
The pack ships Hostile Neural Networks 6.5.1. Its quests sit in the resource_generation chapter and follow the same flow as the mod itself.[2][3]
- Start with "Hostile Neural Networks!" quest, which asks for the Model Framework and the Deep Learner.[3]
- Next is "Simulating Loot" quest: the Simulation Chamber, a Prediction Matrix, and a Generalized Overworld, Nether or End Prediction.[3]
- Then "Generating Loot" quest asks for the Loot Fabricator and a Fabrication Directive.[3]
- After that, a quest in "Generating Resources" asks for the Data Center and the Data Center IO Port.[3]
- "Warden Prediction" quest, "Ender Dragon Prediction" quest and "Wither Prediction" quest each ask for a mob-specific Prediction. They also unlock after the Loot Fabricator quest.[3]
The mod also supports custom Data Models added through datapacks, with one file per model in the data_models subfolder.[1]
Unverified The sources don't show whether the pack changes any of this mod's recipes, configs or model values, so check the in-game recipes before relying on mod defaults. This site does hold FTB Skies 2's own recipes, read from the pack itself: look the item up in the item browser.
How do you get started with Hostile Neural Networks?
4 parts
Hostile Neural Networks lets you simulate mobs and turn the results into real drops. The pack's quest chain walks you through it in a good order, and this section follows the same path: build a model, train it, simulate, fabricate loot, then scale up.[1][3]
Step 1: Model Framework and Deep Learner
Everything starts with the Data Model, an item that holds information about one type of mob. You craft a Model Framework first, then use it on the target entity to build the model. The first quest in the chain asks for this item and the Deep Learner.[1][3]
Crafting Shaped
| any redstone dust | any redstone dust | |
| any gold ingot |
Recipe id: hostilenetworks:framework
The Deep Learner holds a few data models, and the kills you make begin to train them. Every model starts out Faulty and has to be trained up to Basic here before it can go further.[1]
Crafting Shaped
| any obsidian | any obsidian | |
| any glass panes | ||
| any obsidian | any redstone dust | any obsidian |
Recipe id: hostilenetworks:deep_learner
Step 2: Simulation Chamber and Prediction Matrix
Once a model is Basic or higher, the Simulation Chamber can run simulations of it. Simulations always produce a generalized prediction, and they may also produce a mob prediction, depending on the model's accuracy. Running them costs energy and needs a catalyst item, which is usually a Prediction Matrix. The second quest asks for the chamber, the matrix and one of the generalized predictions (Overworld, Nether or End).[1][3][4]
Crafting Shaped
| Empty slot | any glass panes | Empty slot |
| any obsidian | ||
| any lapi gems | any lapi gems |
Recipe id: hostilenetworks:sim_chamber
Crafting Shaped
| any iron ingot | any glass panes | Empty slot |
| any glass panes | any glass panes | |
| Empty slot | any glass panes | any gold ingot |
Recipe id: hostilenetworks:prediction_matrix
The pack also has recipes that convert one generalized prediction into the next tier, from Generalized Overworld Prediction to Generalized Nether Prediction and from there to Generalized Ender Prediction.[5]
Crafting Shaped
| Empty slot | Empty slot | |
| Empty slot | Empty slot |
Recipe id: hostilenetworks:living_matter/overworld_to_nether
Crafting Shaped
| Empty slot | Empty slot | |
| Empty slot | Empty slot |
Recipe id: hostilenetworks:living_matter/nether_to_ender
Step 3: Loot Fabricator and Fabrication Directive
The Loot Fabricator materializes predictions into real items. It uses power, and the drops come from a pre-defined list. You can choose a target for each type of model, and the fabricator remembers each choice, so one machine can take several prediction types.[1][4]
Crafting Shaped
| Empty slot | any netherite ingot | Empty slot |
| any diamond gem | any obsidian | any diamond gem |
| any gold ingot | any gold ingot |
Recipe id: hostilenetworks:loot_fabricator
The Fabrication Directive stores selections from a Loot Fabricator. Right-click to copy a layout and Shift-Right-click to apply it, which saves you from re-selecting everything on each new machine. The quest chain asks for it right alongside the fabricator.[3][4]
Crafting Shaped
| Empty slot | any generalized prediction | Empty slot |
| Empty slot | Empty slot |
Recipe id: hostilenetworks:fab_directive
After the fabricator quest, three more quests each ask for a Prediction. These are the mob predictions your simulations can produce.[1][3]
Step 4: Scale up with the Data Center
The Data Center is the late-game step, and its quest comes after the Loot Fabricator quest. It runs up to 25 Data Models at once, each producing one drop per cycle into a shared output buffer. Its crafting recipe uses the Loot Fabricator and the Simulation Chamber you already built.[3][4][5]
Crafting Shaped
| any obsidian | ||
| any obsidian | any obsidian | any obsidian |
Recipe id: hostilenetworks:data_center
It needs a hollow 7×7×7 shell. The floor must be obsidian, and the walls and ceiling must be black stained glass. The controller replaces one bottom-wall block and must face outwards.[4]
The Data Center IO Port can replace any wall or ceiling block of that shell. Right-click it to cycle between Energy, Models, Inputs and Outputs.[4]
Crafting Shaped
| any iron ingot | any iron ingot | |
| any iron ingot | any iron ingot |
Recipe id: hostilenetworks:data_center_io_port
How does Hostile Neural Networks work?
7 parts
The basic loop
Everything in this mod revolves around the Data Model, an item that holds information about one entity. You craft a Model Framework, use it on the target to build the model, and then train it.[1]
In this pack, right clicking a blank model on a mob or block attunes it to that target, because [[config:config/hostilenetworks.cfg#models.Right Click To Attune]] is on. Block data models (the built-in ore models, for example) are switched off through [[config:config/hostilenetworks.cfg#models.Enable Block Data Models]], which the config describes as experimental.[6]
Crafting Shaped
| any redstone dust | any redstone dust | |
| any gold ingot |
Recipe id: hostilenetworks:framework
Training with the Deep Learner
The Deep Learner holds a few data models, and kills you make start training them. Every model starts out Faulty and has to reach Basic in the Deep Learner before anything else.[1]
The pack keeps [[config:config/hostilenetworks.cfg#models.Action Upgrades Model]] on, so killing mobs and breaking blocks upgrades the matching model. [[config:config/hostilenetworks.cfg#models.Continuous Accuracy]] is also on, so a model's accuracy rises as it progresses toward the next tier instead of jumping only at tier changes.[6]
The Deep Learner works as a curio, and there is a key binding to open it. The on-screen HUD defaults to the top left with zero offsets, set through [[config:config/hostilenetworks.cfg#client.Deep Learner HUD Anchor Point]], [[config:config/hostilenetworks.cfg#client.Deep Learner HUD X Offset]] and [[config:config/hostilenetworks.cfg#client.Deep Learner HUD Y Offset]].[4][6]
Crafting Shaped
| any obsidian | any obsidian | |
| any glass panes | ||
| any obsidian | any redstone dust | any obsidian |
Recipe id: hostilenetworks:deep_learner
Simulation Chamber
Once a model is Basic or higher, the Simulation Chamber can run simulations of it. Every simulation produces a generalized prediction, and it may also produce a Mob Prediction, depending on the model's accuracy. Accuracy rises with the tier, up to 99.5% at Self Aware.[1]
Simulations cost energy, based on the model type, and need a catalyst item, which is usually a Prediction Matrix. In this pack the chamber stores up to 2,000,000 FE ([[config:config/hostilenetworks.cfg#power.Sim Chamber Power Cap]]).[1][6]
The chamber has two modes. In training mode, simulations increase model data but produce no outputs. In inference mode, simulations produce output but the models gain no data.[4]
[[config:config/hostilenetworks.cfg#models.Sim Chamber Upgrades Model]] controls training mode. 0 disables it entirely, 1 allows it, and 2 only trains up to tier boundaries. The pack uses 1.[6]
Crafting Shaped
| Empty slot | any glass panes | Empty slot |
| any obsidian | ||
| any lapi gems | any lapi gems |
Recipe id: hostilenetworks:sim_chamber
Crafting Shaped
| any iron ingot | any glass panes | Empty slot |
| any glass panes | any glass panes | |
| Empty slot | any glass panes | any gold ingot |
Recipe id: hostilenetworks:prediction_matrix
This pack's recipe makes 16 Prediction Matrices per craft.
Loot Fabricator
The Loot Fabricator spends power to turn predictions into real drops. The drops come from a pre-defined list, and you pick a target for each type of model. The fabricator remembers the choice per type, so one machine can take several kinds of prediction.[1][4]
In this pack it costs 256 FE/t to run ([[config:config/hostilenetworks.cfg#power.Loot Fab Power Cost]]) and stores up to 1,000,000 FE ([[config:config/hostilenetworks.cfg#power.Loot Fab Power Cap]]).[6]
A Fabrication Directive stores the selections from a fabricator. Right-click to copy, and Shift-Right-click to apply them to another one.[4]
Crafting Shaped
| Empty slot | any netherite ingot | Empty slot |
| any diamond gem | any obsidian | any diamond gem |
| any gold ingot | any gold ingot |
Recipe id: hostilenetworks:loot_fabricator
Crafting Shaped
| Empty slot | any generalized prediction | Empty slot |
| Empty slot | Empty slot |
Recipe id: hostilenetworks:fab_directive
Generalized predictions can also be converted by crafting. Both of these recipes turn one prediction into the next dimension's version.[5]
Crafting Shaped
| Empty slot | Empty slot | |
| Empty slot | Empty slot |
Recipe id: hostilenetworks:living_matter/overworld_to_nether
Turns a Generalized Overworld Prediction into a Generalized Nether Prediction.
Crafting Shaped
| Empty slot | Empty slot | |
| Empty slot | Empty slot |
Recipe id: hostilenetworks:living_matter/nether_to_ender
Turns a Generalized Nether Prediction into a Generalized Ender Prediction.
Data Center multiblock
The Data Center is the late-game automation machine. It runs up to 25 Self Aware Data Models at once, and each one produces one drop per cycle into a shared output buffer.[4]
- Build a hollow 7×7×7 shell around the controller.[4]
- The floor must be obsidian. The walls and ceiling must be black stained glass.[4]
- The controller replaces one bottom-wall block and must face outwards.[4]
Put Data Models into the 5×5 grid and matching items into the four input slots. Each active slot uses one input per cycle and produces the drop chosen by its Fabrication Directive.[4]
IO ports and power
A Data Center IO Port can replace any wall or ceiling block of the shell, and the controller detects it automatically. Right-click it to cycle through four modes: Energy accepts power, while Models, Inputs and Outputs expose the matching item slots.[4]
In this pack the Data Center stores up to 8,000,000 FE ([[config:config/hostilenetworks.cfg#power.Data Center Power Cap]]). It pays a per-tick cost for each active model, set by [[config:config/hostilenetworks.cfg#models.Data Center Sim Cost Multiplier]]. The pack value is 1.5, which means 150% of the model's base cost.[6]
Crafting Shaped
| any obsidian | ||
| any obsidian | any obsidian | any obsidian |
Recipe id: hostilenetworks:data_center
Crafting Shaped
| any iron ingot | any iron ingot | |
| any iron ingot | any iron ingot |
Recipe id: hostilenetworks:data_center_io_port
Where else predictions are used in this pack
The pack's Deep Mob Soul Binder is a Modern Industrialization multiblock. Its layout needs a Simulation Chamber built into the structure.[7]
Its recipes take a prediction (witch, shulker, zombie or enderman) plus an empty soul vial, and produce a filled soul vial for that mob. Each recipe takes 200 ticks. The villager soul vial recipe takes a villager item instead of a prediction.[8]
A pack-added Create sequenced assembly for Evolutionary Matter deploys Generalized Overworld Prediction, Generalized Nether Prediction and Generalized Ender Prediction in turn. It runs 16 loops.[9]
How do you progress through Hostile Neural Networks?
5 parts
In this pack, Hostile Neural Networks progression is a single quest chain in the resource_generation chapter. Each step unlocks the next, so you build the machines in a fixed order, from the Deep Learner up to the Data Center.[3]
The quest path
- Start with quest "Hostile Neural Networks!" quest. It asks for a Model Framework and a Deep Learner.[3]
- Quest "Simulating Loot" quest comes next. You hand in a Simulation Chamber, a Prediction Matrix and one generalized prediction, which can be Overworld, Nether or End.[3]
- Quest "Generating Loot" quest asks for a Loot Fabricator and a Fabrication Directive.[3]
- Quest a quest in "Generating Resources" asks for a Data Center and a Data Center IO Port.[3]
- Quests "Warden Prediction" quest, "Ender Dragon Prediction" quest and "Wither Prediction" quest each ask for a Prediction item. All three unlock after the Loot Fabricator quest, so you can work on them in any order alongside the Data Center quest.[3]
Early tier: the Deep Learner and the Model Framework
Both items from the first quest are crafted in the pack. Here are the in-pack recipes.[3][5]
Crafting Shaped
| any redstone dust | any redstone dust | |
| any gold ingot |
Recipe id: hostilenetworks:framework
Crafting Shaped
| any obsidian | any obsidian | |
| any glass panes | ||
| any obsidian | any redstone dust | any obsidian |
Recipe id: hostilenetworks:deep_learner
Middle tier: simulation and fabrication
The second quest brings in the Simulation Chamber and the Prediction Matrix. The Prediction Matrix is also what you need to craft a Fabrication Directive, which is part of the Loot Fabricator quest.[3][5]
Crafting Shaped
| Empty slot | any glass panes | Empty slot |
| any obsidian | ||
| any lapi gems | any lapi gems |
Recipe id: hostilenetworks:sim_chamber
Crafting Shaped
| any iron ingot | any glass panes | Empty slot |
| any glass panes | any glass panes | |
| Empty slot | any glass panes | any gold ingot |
Recipe id: hostilenetworks:prediction_matrix
Crafting Shaped
| Empty slot | any netherite ingot | Empty slot |
| any diamond gem | any obsidian | any diamond gem |
| any gold ingot | any gold ingot |
Recipe id: hostilenetworks:loot_fabricator
Crafting Shaped
| Empty slot | any generalized prediction | Empty slot |
| Empty slot | Empty slot |
Recipe id: hostilenetworks:fab_directive
Upgrading predictions by dimension
The generalized predictions follow the dimensions. A Generalized Overworld Prediction can be crafted into a Generalized Nether Prediction, and that can be crafted into a Generalized Ender Prediction.[5]
Crafting Shaped
| Empty slot | Empty slot | |
| Empty slot | Empty slot |
Recipe id: hostilenetworks:living_matter/overworld_to_nether
Crafting Shaped
| Empty slot | Empty slot | |
| Empty slot | Empty slot |
Recipe id: hostilenetworks:living_matter/nether_to_ender
Late tier: the Data Center
The Data Center is the end of the quest chain. It has its own in-pack recipe, and so does the IO port that goes with it.[3][5]
Crafting Shaped
| any obsidian | ||
| any obsidian | any obsidian | any obsidian |
Recipe id: hostilenetworks:data_center
Crafting Shaped
| any iron ingot | any iron ingot | |
| any iron ingot | any iron ingot |
Recipe id: hostilenetworks:data_center_io_port
Unverified The sources do not say which prediction types the three final prediction quests require, or how the pack's recipes compare to the mod's defaults. Check the quest book in game before you plan around either.
How does Hostile Neural Networks work with other mods?
2 parts
The one confirmed link between Hostile Neural Networks and other mods in this pack is a recipe the pack added for Evolutionary Matter. It is where your simulation output gets used outside the mod's own machines.[5]
Evolutionary Matter
Evolutionary Matter is made with a Create sequenced assembly recipe, and the pack added it. It takes the generalized predictions from this mod together with items from several other mods, and it passes through Incomplete Evolutionary Matter along the way. The recipe block below shows the exact in-pack recipe.[5]
Sequenced Assembly (create)
Charged Redstone Crystal
7× Incomplete Evolutionary Matter
Generalized Ender Prediction
Generalized Nether Prediction
Generalized Overworld Prediction
100× Portal Fluid Source
Living Flesh
Nitro Crystal
Recipe id: ftb:create/sequenced_assembly/evolutionary_matter
Added by the pack. It mixes Hostile Neural Networks predictions with items from other mods.
Simulations in the Simulation Chamber always produce a generalized prediction, so a working chamber setup is how you get the prediction items this recipe asks for.[1][5]
Quests
The pack's Hostile Neural Networks quests sit in the resource_generation chapter and only ask for items from this mod. The chain starts with "Hostile Neural Networks!" quest (Model Framework and Deep Learner). It continues with "Simulating Loot" quest (Simulation Chamber, Prediction Matrix and one of the generalized predictions), then "Generating Loot" quest (Loot Fabricator and Fabrication Directive).[3]
After the Loot Fabricator quest the chapter branches. a quest in "Generating Resources" asks for the Data Center and Data Center IO Port. "Warden Prediction" quest, "Ender Dragon Prediction" quest and "Wither Prediction" quest each ask for a Prediction. None of these quests mixes in items from other mods, so the Evolutionary Matter recipe is the only cross-mod connection the sources confirm.[3]
Which FTB Skies 2 quests use Hostile Neural Networks?
2 parts
In this pack, Hostile Neural Networks shows up in the quest chapter called resource_generation. The quests have no titles, so the page refers to them by ID. They form a short chain, and each one asks you to obtain items from the mod.[3]
The quest chain, in order
- "Hostile Neural Networks!" quest is the starting quest. It asks for a Model Framework and a Deep Learner.[3]
- "Simulating Loot" quest unlocks after the first quest. It asks for a Simulation Chamber and a Prediction Matrix. It also needs one prediction item, and any of Generalized Overworld Prediction, Generalized Nether Prediction or Generalized Ender Prediction counts.[3]
- "Generating Loot" quest follows the Simulation Chamber quest. It asks for a Loot Fabricator and a Fabrication Directive.[3]
Branching after the Loot Fabricator
Once the Loot Fabricator quest is done, the chain splits and several quests open up at once. You can do them in any order.[3]
- a quest in "Generating Resources" asks for a Data Center and a Data Center IO Port.[3]
- "Warden Prediction" quest, "Ender Dragon Prediction" quest and "Wither Prediction" quest each have a single task: hand in a Prediction.[3]
Unverified The prediction quests list the generic prediction item, so which specific prediction each one wants can't be confirmed from the available quest data. Check the in-game quest book to see exactly what each one asks for.
Which Hostile Neural Networks config options matter?
4 parts
Everything for Hostile Neural Networks lives in one file, config/hostilenetworks.cfg. Most of the options you will care about are power sizes and how models level up, so here is exactly how this pack sets them.[6]
The value the pack flags as changed
[[config:config/hostilenetworks.cfg#models.Data Center Sim Cost Multiplier]] is set to 1.5. It scales the per-tick power cost the Data Center pays for each active model, as a multiplier on the model's base simCost, so 1.5 means 150% of normal. The allowed range is 0.01 to 100.0. The config listing marks this option as changed by the pack, but the mod default it shows is also 1.5, so 1.5 is the value you get in this pack.[6]
Power
The power options below all match the mod defaults in this pack.[6]
- [[config:config/hostilenetworks.cfg#power.Data Center Power Cap]]: 8,000,000 FE. The config describes this as sized for 25 concurrent self-aware simulations.[6]
- [[config:config/hostilenetworks.cfg#power.Sim Chamber Power Cap]]: 2,000,000 FE stored in the Simulation Chamber.[6]
- [[config:config/hostilenetworks.cfg#power.Loot Fab Power Cap]]: 1,000,000 FE stored in the Loot Fabricator.[6]
- [[config:config/hostilenetworks.cfg#power.Loot Fab Power Cost]]: 256 FE/t for the Loot Fabricator.[6]
Model training and attuning
- [[config:config/hostilenetworks.cfg#models.Action Upgrades Model]] is true, so killing mobs and breaking blocks upgrades the data on a matching model.[6]
- [[config:config/hostilenetworks.cfg#models.Right Click To Attune]] is true, so right clicking a blank data model on a mob or block attunes it to that target.[6]
- [[config:config/hostilenetworks.cfg#models.Continuous Accuracy]] is true, so a model's accuracy rises as it gains progress toward the next tier, instead of staying at the base accuracy of its current tier.[6]
- [[config:config/hostilenetworks.cfg#models.Sim Chamber Upgrades Model]] is 1, meaning the Simulation Chamber's Training Mode upgrades model data. The options are 0 (disabled, which also disables Training Mode entirely), 1 (yes) and 2 (only up to tier boundaries).[6]
- [[config:config/hostilenetworks.cfg#models.Enable Block Data Models]] is false. It is described as experimental and covers block data models such as the built-in ore models.[6]
Deep Learner HUD
The HUD is anchored at top_left with an X offset of 0 and a Y offset of 0, which are the mod defaults. Change [[config:config/hostilenetworks.cfg#client.Deep Learner HUD Anchor Point]], [[config:config/hostilenetworks.cfg#client.Deep Learner HUD X Offset]] and [[config:config/hostilenetworks.cfg#client.Deep Learner HUD Y Offset]] to move it. Each offset can go from -1000 to 1000.[6]
What changed in Hostile Neural Networks between versions?
FTB Skies 2 1.22.0 ships with Hostile Neural Networks 6.5.1, built for Minecraft 1.21.1. The mod has been in the pack since FTB Skies 2 1.0.1 or earlier, so it's been part of the pack for a long time.[2]
Unverified The mod's changelogs for 6.5.1, 6.5.0 and 6.4.1 were available only as titles, with no entries I could read, so I can't say what changed in those releases. There are also no pack changelog entries for this mod, so any change the pack made to it between releases is unconfirmed.
Sources
- Hostile Neural Networks project page (modrinth) · official mod data
- FTB Skies 2 1.22.0 mod list · pack file
- FTB Skies 2 1.22.0 quests: "resource_generation" · pack file
- hostilenetworks tooltips and descriptions (English lang file) · official mod data
- FTB Skies 2 1.22.0 recipe dump: recipes making Hostile Neural Networks items · pack recipe dump
- FTB Skies 2 1.22.0 config: config/hostilenetworks.cfg · pack file
- kubejs/startup_scripts/registry/multiblocks/deep_mob_binder.js (FTB Skies 2's own script) · pack file
- kubejs/server_scripts/recipes/custom_mi_multiblocks/deep_mob_binder.js (FTB Skies 2's own script) · pack file
- kubejs/server_scripts/recipes/mods/create.js (FTB Skies 2's own script) · pack file
Where this guide comes from
Written from what FTB Skies 2 itself ships: its files and recipes, the in-game guidebooks and the mods' own pages. Every statement links to the source it came from, and the numbers are checked against the pack before publishing.
Guide last verified Oct 14, 2026.
Report wrong info
Version in each release
44 releases, first in 1.0.1
| FTB Skies 2 | Version | Jar | Where it came from |
|---|---|---|---|
| 1.24.0 Oct 12, 2026 | 6.5.1 | HostileNeuralNetworks-1.21.1-6.5.1.jar | From the published release |
| 1.23.0 Sep 24, 2026 | 6.5.1 | HostileNeuralNetworks-1.21.1-6.5.1.jar | From the published release |
| 1.22.0 Sep 3, 2026 | 6.5.1 | HostileNeuralNetworks-1.21.1-6.5.1.jar | From the published release |
| 1.21.1 Jul 29, 2026 | 6.5.0 | HostileNeuralNetworks-1.21.1-6.5.0.jar | From the published release |
| 1.20.1 Jul 29, 2026 | 6.5.0 | HostileNeuralNetworks-1.21.1-6.5.0.jar | From the published release |
| 1.20.0 Jul 27, 2026 | 6.5.0 | HostileNeuralNetworks-1.21.1-6.5.0.jar | From the published release |
| 1.19.0 Jul 24, 2026 | 6.4.1 | HostileNeuralNetworks-1.21.1-6.4.1.jar | From the published release |
| 1.18.2 Jun 21, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.18.1 Jun 16, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.18.0 May 31, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.17.0 May 27, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.16.0 May 13, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.15.0 May 1, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.14.3 Apr 1, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.14.2 Apr 1, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.14.1 Mar 27, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.14.0 Mar 21, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.13.4 Feb 27, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.13.3 Feb 19, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.13.2 Feb 17, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.13.1 Feb 13, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.13.0 Feb 12, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.12.0 Jan 6, 2026 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.11.0 Dec 10, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.10.2 Nov 24, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.10.1 Nov 20, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.9.2 Oct 7, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.9.1 Sep 29, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.9.0 Sep 22, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.8.0 Aug 27, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.7.0 Aug 23, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.6.1 Aug 8, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.6.0 Aug 6, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.5.2 Jul 24, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.5.1 Jul 23, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.5.0 Jul 22, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.4.1 Jul 15, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.4.0 Jul 15, 2025 | 6.3.0 | HostileNeuralNetworks-1.21.1-6.3.0.jar | From the published release |
| 1.3.1 Jul 9, 2025 | 6.2.0 | HostileNeuralNetworks-1.21.1-6.2.0.jar | From the published release |
| 1.3.0 Jul 8, 2025 | 6.2.0 | HostileNeuralNetworks-1.21.1-6.2.0.jar | From the published release |
| 1.2.0 Jul 6, 2025 | 6.2.0 | HostileNeuralNetworks-1.21.1-6.2.0.jar | From the published release |
| 1.1.1 Jul 2, 2025 | 6.2.0 | HostileNeuralNetworks-1.21.1-6.2.0.jar | From the published release |
| 1.1.0 Jul 1, 2025 | 6.2.0 | HostileNeuralNetworks-1.21.1-6.2.0.jar | From the published release |
| 1.0.1 Jul 1, 2025 | 6.2.0 | HostileNeuralNetworks-1.21.1-6.2.0.jar | From the published release |
"From pack files" means the list came from the pack's own files; "from the published release" means ForgeBase read the jars of the release itself.
Items and blocks
14 items from the 1.24.0 recipe dump.
FTB Skies 2 quests (7)
Quests from the pack's FTB Quests book that ask for this mod's items.
Generating Resources (7)
- Ender Dragon Prediction
- Generating Loot
- Hostile Neural Networks!
- Simulating Loot
- Warden Prediction
- Wither Prediction
- A quest in "Generating Resources"
Config options (how FTB Skies 2 sets them)
13 settings shipped in the pack's config files; 1 differ from the mod's documented default.
Show settings
| Setting | FTB Skies 2 value | Mod default |
|---|---|---|
models.Data Center Sim Cost Multiplier changed by FTB Skies 2Per-tick power cost the Data Center pays per active model, as a multiplier on the model's base simCost. 1.5 = 150% of normal. config/hostilenetworks.cfg | 1.5 | 1.5 |
client.Deep Learner HUD Anchor Point The anchor point for this element. config/hostilenetworks.cfg | top_left | top_left |
client.Deep Learner HUD X Offset The X offset for this element. config/hostilenetworks.cfg | 0 | 0 |
client.Deep Learner HUD Y Offset The Y Offset for this element. config/hostilenetworks.cfg | 0 | 0 |
models.Action Upgrades Model Whether killing mobs and breaking blocks will upgrade the data on a corresponding model. Note: If you disable this, be sure to add a way for players to get non-Faulty models! config/hostilenetworks.cfg | true | true |
models.Continuous Accuracy If true, the accuracy of the model increases as it gains progress towards the next tier. If false, always uses the base accuracy of the current tier. config/hostilenetworks.cfg | true | true |
Which FTB Skies 2 mods work with Hostile Neural Networks?
The FTB Skies 2 mods that share the most recipes with Hostile Neural Networks. Highlighted ones have a guide.
Comments and tips
Loading comments...