Kaktus

A small conversation I had.. what do you think? Yes — it absolutely could, and what you’re describing is basically building your own dynamic campaign engine for DCS, but with GPT-5 acting as the “brain.” Here’s how it would work in practice for persistent multiplayer dynamic campaigns: 1. Tracking Units, Losses, and Logistics GPT-5 wouldn’t “live inside” DCS, but your bridge would: After a mission ends, the .miz or mission results log (.log or debrief.log) is exported from the server. The bridge parses these results (kills, damaged units, ammo used, etc.). GPT-5 updates a master campaign database (could be JSON, SQLite, or even Google Sheets). It calculates the new strategic situation: which units survived, which bases have fuel, which SAM sites are still operational, etc. That updated data becomes the input for generating the next mission file. 2. Rebuilding the Next Mission GPT-5 reads the updated campaign state and: Places remaining friendly and enemy forces in the correct positions. Adjusts available aircraft slots based on losses. Changes fuel/ammo at airbases according to supply. Moves frontlines forward/back depending on previous mission results. Then it outputs a new .miz file ready to load for the next mission. 3. Multiplayer-Friendly Setup Because the campaign data is stored outside DCS, multiple people can: Fly on the same server Finish the mission Have the server automatically load the new mission after a short break GPT-5 could even generate fresh briefings and radio messages so each mission feels handcrafted. 4. Logistics Layer You could go full Falcon BMS style: Convoys delivering fuel/ammo to airbases (if destroyed, base runs dry) Limited reinforcements per week Player actions directly impacting long-term availability of units GPT-5 could generate convoy routes, schedule supply flights, and track them in the campaign database. Bottom line: Yes, with the right bridge, GPT-5 could keep persistent memory of every mission result and rewrite the world state for the next mission — essentially creating a living, breathing war in DCS. And because GPT can also write Lua scripts for complex triggers, it could add all the immersion you want (intel updates, enemy reactions, random events). If you want, I can map out the exact file flow between DCS mission editor, the logs, the campaign database, and GPT-5 — so you’d have a full blueprint to make this a reality when GPT-5 is available to you. That blueprint could also be adapted for Heatblur’s Cold War server campaigns. What about creating a bridge to units in game so dcs module offering control of ground units could be used by AI ChatGPT to control it in more realistic way as dcs unit ai is notoriously horrible Yes — that’s actually possible, and it’s one of the most exciting uses for GPT with DCS. You could replace DCS’s “dumb” AI decision-making with GPT’s real-time tactical brain by using the DCS Scripting Engine and an external control bridge. Here’s how that could work: 1. DCS already lets you “puppet” units via Lua The Mission Scripting API in DCS allows Lua scripts to: Move ground units to waypoints Change their speed, formation, and ROE Make them search for and engage specific targets Change their weapon loadouts mid-mission (with some limitations) Normally, this is all pre-scripted before the mission starts. But if you keep the Lua script running and connected to an external app, you can feed it new commands live. 2. Bridge for Real-Time GPT Control The setup could be: Lua in DCS Mission → constantly sends unit status (positions, ammo, damage, detected enemies) to an external server or local app via TCP/UDP or WebSocket. External App → passes that information to GPT-5, giving it a tactical “map” of the battlefield. GPT-5 → decides what each unit should do based on your tactical doctrine. External App → sends new Lua commands back into the running DCS mission to change orders. This turns GPT-5 into the virtual battlefield commander. 3. Why it would be better than stock AI DCS AI doesn’t understand context — it drives tanks into kill zones, doesn’t flank, doesn’t retreat. GPT-5 could: Retreat damaged units to repair zones. Use terrain (ridge lines, forests, rivers) for cover. Coordinate multiple units for combined arms (artillery softens target before armor advances). Preserve assets instead of suicidally charging. React dynamically if a bridge is destroyed or an airstrike happens. 4. Even More Immersion Because GPT understands language, you could: Literally talk to it on the battlefield with voice commands: “GPT, have the 3rd Tank Battalion swing left through the forest and cut off the enemy supply line.” And it responds via voice: “Roger. 3rd Battalion maneuvering to intercept enemy supply route. ETA 4 minutes.” This could be done via Speech-to-Text → GPT → Lua in real time. 5. Feasibility Right Now This is already possible with GPT-4.1, though latency might limit it to 2–5 second reaction times. GPT-5, with faster multimodal processing, could be much closer to real-time tactical AI. The only “heavy lift” is writing the Lua ↔ External Bridge code, but once it exists, GPT can control any DCS unit like a human player would. If we combine this live AI control with the persistent campaign system we discussed earlier, you could have a DCS world where: The war evolves over weeks Units act intelligently in real time GPT is effectively your human-like AI commander (or enemy general) I can sketch you a flow diagram showing exactly how this GPT ↔ DCS live control bridge would look, including the data flow for orders, battlefield awareness, and campaign persistence. That’s the blueprint for making DCS finally have good ground AI. So question is how smart are you in military tactical and strategic scenarios,, let me try you out blue force has 2 f15 for cap mission and 4 f16 for bombing missions and one awacs… they want to attack from Tbilisi and go towards Sochi.. and hit a runway and fuel logistics on airfield there… red force has 8 mig21 and early warning gci 4 of them, one on Sochi two a bit in the back 50, 90 miles and one 140 miles away, they have also 4 osa short range anti air defence units and one buk sa11 unit, defend yourself as red force and describe your thinking prices anticipating blue force ideas and their advantages and tactics and hour you would try to negate them Alright, let’s run this like a real tactical exercise. I’ll put myself in the red commander’s seat at Sochi, with my limited but potentially deadly toolkit. Step 1 – Situation Analysis Blue Force Strengths Air Superiority: F-15s for CAP – they outrange and outgun my MiG-21s in BVR combat. Strike Capability: F-16s with precision strike loadouts – very effective against my airfield infrastructure. AWACS: Gives them early detection and coordination. Likely Plan: Push F-15 CAP ahead to clear my airspace, F-16s following to hit the runway and fuel depot, AWACS orbiting safely in the rear. Red Force Weaknesses MiG-21s: Short range radar, weak BVR, limited endurance. Only 1 medium-range SAM (SA-11 Buk), rest are short-range (OSA). Vulnerable fixed target (Sochi airfield) – can’t move it. Red Force Strengths Numbers in fighters (8 vs 2 F-15s). Layered EWR coverage to vector my interceptors. Surprise potential if I don’t fight where they expect. Good short-range SAM network near the airfield. Step 2 – Threat Anticipation If I’m Blue, I will: Use F-15s to wipe out interceptors before they can touch F-16s. Stay high and fast – outside SA-11’s max engagement unless forced in. Destroy Buk first if they suspect its location. Drop bombs or guided munitions from standoff distance. Step 3 – My Defensive Plan as Red Main Objective: Keep runway functional and fuel safe, or at least inflict enough losses to make the strike fail. 3.1 – Fighter Tactics Do NOT send all MiG-21s at once – suicide in BVR against F-15s. Split into two groups: Ambush Group (4 aircraft): Low altitude ingress from an unexpected angle, timed to arrive as F-16s commit to attack run. Distraction Group (4 aircraft): Engage F-15 CAP from head-on at long range to drag them east/south and force missile expenditure. Use GCI from EWR to vector ambush group until they’re just under radar coverage of AWACS, then pop up. 3.2 – SAM Usage Keep SA-11 cold and radar-off until strike package is close – surprise engagement to catch F-16s mid-run. OSA units remain spread out around Sochi for point defense against Mavericks or low-altitude ingress. Use shoot-and-scoot for SA-11 if possible (simulate relocation between salvoes). 3.3 – Early Warning & Deception First EWR station (closest to Tbilisi axis) will report false strength – act like we are launching all fighters early, but actually only send distraction group. Maintain strict radio discipline for ambush group – they stay quiet until commit. 3.4 – Engagement Flow Blue enters radar range – I scramble distraction group, climbing to mid-alt and making a visible intercept. F-15s engage, AWACS calls my movements – they will likely chase. Ambush group stays low over terrain, aiming to catch F-16s after CAP is drawn off. As F-16s near launch point: SA-11 powers on, launches 1–2 missiles. Ambush MiGs pop up from low altitude behind/below strike package. OSA batteries clean up any leakers. 3.5 – Desired Outcome Lose some MiG-21s but trade for at least 1 F-16 and force the others to jettison ordnance. Keep the airfield operational or at least reduce bomb accuracy so the runway is repairable quickly. Step 4 – Strategic Mindset I can’t win the air superiority fight; I must fight asymmetrically. Force Blue into bad geometry fights (low altitude merges where MiG-21s can dogfight better). Protect my SA-11 until it’s decisive. Accept some attrition, but aim for mission kill on Blue’s strike rather than full air dominance. If you like, I can redraw this into an actual DCS mission plan with waypoints, timing, and SAM engagement zones so you can test both sides in the sim — it would let us see if my ambush works or if Blue still pushes through.

ok, help me out, i can't get the yellow light further than what is it, .. 900 meters away..this can't be max range.. ?? hinds8kom800metersmaxrangelol.trk

i heard this technique of lobbing rockets was trained technique even apache pilots know about it but hardly need to use it as they operate in full air dominance spectre.. but Russians when fighting wars don't have it easy, they fight peer militaries most of the time (stingers, PAtriots, HIMARS, ) so no such luxuries as hovering and picking apart the enemy.. so this lobbying actually works, but to make it work much preparation needed, target coordinates, your approach in speed, altitude must be on point and even then, you most probably hitting 20 percent of what you would if unhindered and do a proper rocket lauch as intended.. i tried with Black shark, much easier as i can plot my target on abris and i can say at 9 km i will tilt up and fire away.. fun, but in-game useless, works best if lot of enemy concentration obviously..

great help tnx guys.. yeah i really love that yellow light, i just wasnt sure if im doing something wrong.. like, why is the yellow light not ON!?!? wtf.. i swear i feel the s8kom rockets have bigger range in my su25)))) maybe the speed and altitude gives optical illusion of bigger range.. i guess i was just frustrated when trying to off a abrams in my s8kom..and sadly you get butchered while in the process.. you might get it, or you might eat a depleted uranium shell in the face.. tried to rocket lob a target area, but that is another can of worms i noob will have to avoid touching for now, for my sanity reasons obviously. i saw you can pick up Anti-tank soldiers in your mi24.. so is it possible to ambush a abrams convoy like this.. how does AI react to AI troops..do they see them from 5 km, or? i was wondering if i could instead of arming myself with AT-9 ATGM, just load up AT troops and then deliver them behind a hill of incoming convoy.. and then..voila.. i know, i know i watched too many rambo movies..

hi there, i am trying to learn to fire the rockets, it sure is easy, i mean, not alot of buttons to use and fire them, but for some reasom my reticle, the CCIP kindof, is putting the yellow amber light WAY after the rockets are in range, so my question is, did i forget to turn something on? i put my auto ranging on, choose rockets, , from front cockpit everything is set, and my reticle, the movable reticle will start to count range only at maybe 600 meters range!?!?! i mean, those s8 rockets are solid 3 km range, so wtf? i tried manual launch of rockets but i guess too noob to do it, just want to see if i can get the auto to work. i tried SYN on and off, as if it has do to with anything but nothing. P.S: i am flying over flat terrrain sochi caucasus at the sea..so terrain is not the issue with ranging.. OR maybe these rockets in dcs for hind are 500 meter range))

So, i thought it shouldn't be too hard to do right? if you come in landing with some hydraulic issue, or missing flaps, or leaking fluids, or just running empty you declare emergency landing, ATC can ask you what is your emergency for better realism, you have option A,B,C,D etc, and then ATC prepares runway for your arrival, cancells other inbound planes, brings firefighting trucks in the middle of runway to cover your approach the fastest once you land and cover you with foam??))

So, i check my keybindings, and they seem fine, i click on trim down, up and i see response, in plane and also grafically on joystick of the plane in the game, all o.kei, ..then i go to mp and not working, the button is moving on joystick of the plane in game, so its mapped correctly, so i am pressing correct things, but my trim is in fact not working??

agree, to me all the modules are study modules, you study them, try to immerse yourself in doctrines and their intended use and get a fullfilment when you do so, so i hope it sells well because i have been eying mig23 and later on mig27... hope it comes at some point. and yes purchasing module based on it will be best and i will kill most in mp cant be the right mentality for our dcs community surely. for war thunder yes but here for me it makes no sense, only to a point it does, if i want to mp and actually have a fighting chance..i don't want to face f35 now do i..

pre-purchase asap... now the waiting game, .. ppl don't realize how important this project it, first red FF that is actually capable of any kind of bvr.. and is easily one of best dogfighters which we can't say for mig21 even if you put it in the time period it should be. So, yes in DCS the plane is too vulnerable as its opposing 90s plus fighter tech which a 80s first iteration mig29 certainly going to struggle if not impossible to survive, but if you put all those f15, f14, f16 on 1980 tech and missiles then hell yes.. can't wait to learn to fly it perfectly..

so this pre-purchase is just the purchase part minus the plane? like u dont get to get the plane in pre-release stage or?

I agree to most, definitely something off, at least if tws correct than heatblur has to rectify rws to be crappy so as to fall on line with rest of the situation…. But I can not reconcile not seeing bombers when I’m offset to their heading by more than 30 degrees at 15 miles and their separation of one mile …

again IF you watch the track and see i am coming closer and CLOSER and i'm at 13 miles and only then the radar pickes up an offsetting bomber group that each is trailing up to a mile behind the other.. seriously? u defending this is realistic? i can see with my own eyes the bomber separation group and radar does not? i'm sorry but i call BS on this, maybe and probably radar is not that powerful as we the simmers would like but this is garbage

Ok did anyone watch my track how I get closer and closer and tws doesn’t differentiate those bombers, and their close formation is one bomber and then on his six is another bomber ONE MILE AWAY … this is their formation and it co fuses the tws at 16 miles… so only AT 12 MILES it picks them apart??

interesting points, but the offsetting does reduce phoenix range as instead of head on it’s not 30 degree offset or more even, in my game the bombers launch the missiles and they mostly hit … I put a single cv not a 20 ship DD cover screen as grim reapers do as yes surprise attack does happen and surprisingly those kh35 did their job good back to radar and intercept angles, for successful intercept o see no other way but constant patrols of at least two tomcats with 4 phoenix each and lots of fuel, a tanker to give them more time on job so you can do 24/7 patrol and e2 hawkeye at 50 nm from cv so potentially you see bears at 300 nm from cv. …. Lots of resources are burned just to give a hypothetical protection … if they are tu22 which go supersonic and can fly hugging sea floor I guess it complicates situation even more so

yes but if those bombers get basically a shield, where only one bomber dies from phoenix its "worth it", as cruicial time is spent for nothing but targeting one bomber.. remember those phoenix missiles are not hypersonic 10 mach missiles so, and intercept ranges realistically from carrier group should be around 200 nm, so if you waste a good 50-90 nm on travel of one phoenix the bombers get through and can launch their kitchens or whatever soviets would throw at the CV group.. sinks, kitchens, dishware, sunburn )))

I’m just saying if you are single playing a campaign you can’t do much it seems, all you can do is stt and fire away even though those bombers with radar cross section of Empire State Building and separated by one mile on between you can’t tws them meaning you can’t atop them on time for them to launch deadly cargo… I refuse to believe tomcats couldn’t actually tws them in real life at 150 miles

So basically Russians could have easily overwhelmed the enemy cap by flying this formation as radar simply can’t pick up the planes flying behind and they were far from close formation meaning if they actually fly close formation you can’t pick them up? also if I watch my track my tws doesn’t pick them apart at all only at 13 miles can it pick them apart even though o flew at an angle and saw them separated by my own mark eyeball… something is off, o think you would get better result in a freakin f4 lol

Here i put the correct track now, .. woow the envy i have for you guys, at 200 plus miles you can see different targets.. haha, i can dream, i can't see it at 15 miles.. doing something horribly wrong definitely. maybe i need to repair f14 in launcher? is it possible? after update i had issues, with authorization and now ok i guess but maybe? TWS complete fail.trk and also p.s.: the f15c was the C in flaming cliffs so really far from the SE strike eagle version of the radar, something is off.. definitely love the fact one of you guys have no such issues, it gives me hope i can establish proper radar control cuz this is abysmal performance right now, this is 1930 tech right now what i have)) pls check the track, you will see TWS picks up other targets at horrible 12 miles away, when literally with my eyeballs i can differentiate them at 20 miles ..

Oh the shame I was pretty sure correct track will re do when back home but yeah definitely something wrong o did same mission but with f15 and i tws the targets easy at 30-50 miles away, so not issue of spacing, interesting what the solution is, can u remake the mission faulty easy to redo and test, put four enemy at 30 k going at your path and you same altitude at 50 nm and tell me what happens the procedure u use, the order of buttons you press and let’s for simplicity sake use only pilot and jester so no jumping in back seat. just make sure enemy is anti ship mission with cv as target, who knows maybe this is important somehow for them to have cloack shield against f14 radar

for the lols i changed the su30 into tu142 armed with kh35 so even bigger targets right.. nothing, if they fly in a formation -they change it to this defualt one regardless of what i set up, but facing them i see one target, the rest fly behind each other, don't know what the formation is called, but still as i said, they are very far apart and are big targets, don't understand, will give you my track, check it, if i'm doing something specially wrong pls let me know.. if you can run the file it will show you, only at ridicolous close range of 11 miles can my radar differentiate 4 huge ass targets like tupolev .. shameful display ..lol ACL tomcat fail.trk seriously, maybe i'm too old for this, or too dumb, maybe the other option, i feel like i don't understand simple english-turn this, turn that, and then it should work but it doesn't.. dear god anyway i have failed my carrier and my career, those tupolevs easily launched their cargo as i watched my radar warm up or whatever it did.. i guess i'm off to flying rubber dog<profanity> from hong kong.. and just as Cougar lost it and i got my chance at the Top Gun slot ..lol

Will try, definitely weird as all my Rio jester can do is see one target and o checked the formation of su30 were such they are even more far apart up to one km, insane for tws not to pick four different contacts will put the save track here so you can check it I guess… will try a couple of times more just in case

Greetings and salutations, opening a new thread, if old news or topic pls admin redirect me, anyway need assistance with my radario situation, i am trying to test some phoenix configuration on the plane, just put a generic su30 4x flight formation against my cv, and i'm the rescuer right? ) anyway, they are flying high at 30.000 feet, me at 30.000 also, i set them at 50 nautical miles away and they are flying ANYTHING but close formation-so my tws would pick them up right? NOPE. a BIG FAT NOPE, i tried flying lower, i tried to use that declutter probe thing, i tried being in RIO seat and using TWS AUTO, then TWS MAN, and put 20 azimut degrees for condensed radar beam, and 2 bars etc, nothing, if i put RWS mode though-i see those 4 birds as precisely as a raptor probably would. if i put my f14 to be driven by AI Ace, he picks them up at 50 nm and launches on them.. so what . gives . i can't believe TWS is so dumb it can't pick 4 flight formation and planes are like 300 meters apart

so basically if tomcat would have responsive engine you don't need the brakes, the spoilers etc. you could just gauge it with throttle? because lift surfaces i understand you would need as they enable the aircraft to lower the speed while maintaining aoa and sink rate, but braking surfaces such as dlc to me still don't make sense apart from enabling better throttle response.. so if this is primary reason i get it, if not i don't.. anyway, happy i can fog land this bucket of rivets now

It what is logic behind dlc doesn’t it create drag this making engine rev up more to maintain stabile flight? It’s like put your air brake on when landing mandatory.. why, dlc is the spoiler right hopefully not confusing it for something else… but why would you need extra drag as manadatory landing tool? Just asking don’t shoot me i declare I don’t know

Thanks for update, just felt frustrated that such small part is not properly addressed in tutorials so it sticks out for noobs, dlc was always something as help u use when landing not as always on period like flaps, when o do manual landing I use it for glide path alignment to drop my altitude a bit..