Kimi K3 Open Source AI Beats GPT & Fable? 🤯 (Coding FF7, Red Dead & MLX)
Credibility score: 44/100 — Mixed Credibility. Several questionable claims detected. Watch with healthy skepticism.
BSmeter analyzed "Kimi K3 Open Source AI Beats GPT & Fable? 🤯 (Coding FF7, Red Dead & MLX)" and rated it 44/100 for credibility (a BS score of 56/100 — mixed credibility), on 2026-07-18. Its weakest claim — "Made full FF7, RDR2, and GTA5 remakes with one model" — scored 20/100 and was flagged as confidence mismatch. 30 claims were checked against the video transcript. Scores are produced by BSmeter's AI analysis of the transcript, not independent human verification.
Claims analyzed
2.8 trillion param Kimi K3 beats GPT & Fable — zero model shown — Confidence Mismatch (45/100)
Drops a 2.8-trillion claim and leaderboard before any model or benchmark loads. Bold. Stupid, but bold. 😈
Drops 2.8-trillion-param model with no source or benchmark link — Confidence Mismatch (45/100)
Announces 2.8 trillion parameters like it’s settled fact — zero receipts, zero paper, zero link. 😈
Kimi K3 never stops until 100% happy — built-in harness claim — Confidence Mismatch (45/100)
Says the model has a 'builtin harness' that keeps going until 100% — names no code or test that proves it.
Made full FF7, RDR2, and GTA5 remakes with one model — Confidence Mismatch (20/100)
Says 'made' like he shipped finished games — these are tiny demos at best, not remakes.
Calls built-in harness the 'main innovation' with zero comparison — Confidence Mismatch (45/100)
Labels it the core breakthrough like that's obvious — no benchmarks, no prior models mentioned. 😈
Lists basic edits as if they're new frontier capabilities — Missing Context (45/100)
Acts like skin tone and age sliders are mind-blowing — most image models have had this for years. 😈
Jumps from 'potentially' to asking for full AAA browser game in one breath — Confidence Mismatch (45/100)
Slides from 'maybe' to demanding AAA graphics and proper models with zero evidence it can deliver. 😈
Jumps from prompting an AI to 'make GTA 6 ourselves' — Confidence Mismatch (45/100)
Said 'make GTA 6 ourselves' like the prompt is the hard part. Bold. Stupid, but bold.
Model correctly flags the absurd ask — speaker still calls the attempt 'doing some stuff' — Missing Context (45/100)
Model tells the truth about scope and budget — speaker shrugs it off and keeps going anyway. 😈
Bugs exist but model is still great — Missing Context (45/100)
Admits collisions are broken — then immediately pivots to 'so much good' without showing the fix.
Calls current output 'not best' while promising quality with tweaks — Missing Context (45/100)
Promises 'quality game' with extra turns — never shows what that actually produces. 💀
Prompt upgrade equals better game — Missing Context (45/100)
Calls the prompt 'more ambitious' while the actual output still shows placeholder buildings and broken physics.
Audio generation is now a 'skill' — Loaded Language (45/100)
Labels basic TTS as a learned 'skill' like the model gained a new ability rather than just calling an API.
Calls it a 'vision model' that 'sees and understands' — Loaded Language (45/100)
'Understands' is doing heavy lifting — it's generating previews, not proving comprehension. 🔥
Attributes 'excitement' to the model about its own work — Loaded Language (45/100)
Model isn't excited — it's role-playing the prompt. Anthropomorphism doing the selling. 😈
5-hour FF7 + MLX port — no receipts, just time claim — Confidence Mismatch (45/100)
Drops '5 hours' like it's measured — zero logs, zero timestamps, zero proof it wasn't 20. 💀
Calls it AAA graphics while showing early dark prototype — Confidence Mismatch (45/100)
Labels it 'AAA graphics' while the actual screenshots are still very dark and unfinished.
Claims it's AAA graphics on an FF7 clone — confidence without proof — Confidence Mismatch (45/100)
Calls it AAA graphics while describing a hobbyist AI clone. That's a stretch with zero comparison data.
Assumes the AI is 'happy' with its own dark screenshots — anthropomorphism as evidence — Just Vibes (50/100)
Treating the AI saying 'done' like it has taste. Cute bit, but it's just code stopping.
Prompted the AI to fix dark textures after it already called itself done — iterative coaxing presented as success — Missing Context (45/100)
The model didn't nail it first try. User had to step in and correct it, then showed the improved version.
Presents MLX Linux attempt as impressive without showing results — Missing Context (45/100)
Mentions it downloaded MLX on Linux but leaves out whether anything actually worked or just failed.
One prompt created full FF7 scene — confidence mismatch — Confidence Mismatch (45/100)
Calls it 'just one prompt' like that explains the entire result. Zero detail on what was actually fed in.
Tifa or Eric romance choice — false dilemma — False Dilemma (20/100)
Presents only two romance options when the original game and mods have way more paths.
Gemini and Claude failed, Kimi succeeded — anonymous authority on other models — Anonymous Authority (45/100)
Names Gemini Pro and Claude Sonnet Max failing the same prompt with zero logs or output shown. 💀
Calls the fix 'sneaky' then walks it back — Loaded Language (45/100)
Labels the code change 'sneaky' for drama — then immediately says he doesn't know if it is.
LLM diagnosed quantization as the bug — no proof it actually checked — Anonymous Authority (45/100)
AI said it 'checked everything' — zero receipts on what it actually looked at. Classic anonymous authority move.
Claims the real bug was something else entirely — Missing Context (45/100)
Says 'this was the bug' like it's obvious — never shows what the original prompt or expected behavior actually was.
Claims the real bug was elsewhere — but the 'good' edit gets zero scrutiny — Missing Context (45/100)
Calls the LN head fix 'good' then immediately dismisses it without showing why it wasn't the actual problem.
Missing comma zero declared the sole bug — no evidence it's the only one — Confidence Mismatch (45/100)
Calls the missing comma 'the bug' with total certainty while admitting the model found it by accident.
Calls the missing comma 'so simple' after AI found it — Confidence Mismatch (45/100)
Calls the fix trivial only after the model spotted it. Before that, it was apparently invisible to him.
See the full analysis with sources and timestamps →