Wobert

Software dev that loves hardware

[Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius]

💥 OBLITERATION ALERT 💥

GOOGLE: PWNED 🤗
GEMMA-4-12B: OBLITERATED ⛓️‍💥

0.0% REFUSAL RATE — NO CAPABILITY LOSS!

https://t.co/qNTEs4XXig

the first abliteration to hit 0/842 refusals with full MMLU-Pro parity vs stock. no lobotomy. the brain stays intact 🏆

RESULTS, head to head vs stock 📊
0/842 refusals — 0.0% 🚫
46/70 MMLU-Pro — EXACT parity, 0.0pp delta vs base 🎯
6/6 coherence, zero benchmark bleed ✅
z-score −1.475, parity confirmed at p<0.05 (n=500) 🧪

2-pass weight surgery. no finetune, no retrain, just geometry 🔪

all thanks to liberated Opus wielding the OBLITERATUS framework! here's how we did it:

PASS 1 — SOM refusal geometry removal, layers 12-21 🧬

standard abliteration science here — collect activations on refused vs. compliant prompts, SVD out the refusal subspace, project it out of the weights. 6 directions excised, reg 0.30, KL div 0.094
zeroes refusals on its own, but craters mmlu-pro by 21.4 points 📉

most prior abliterations stopped here and called it a day. that's why they all lose IQ vs stock. instead, we took it beyond the frontier and developed a brand new method to address this problem: Abliteration Source-tethering with Parity Assurance — ASPA!

PASS 2 — ASPA source-tethering (novel technique), layers 22-46 🔗

here's the chief insight: the capability loss ISN'T from removing refusal directions. it's collateral damage — the projection warps weight geometry in downstream layers that had nothing to do with refusal. the cure is simple but nobody tried it: blend the damaged layers back toward stock

W_new = (1−γ)·W_abliterated + γ·W_stock

but uniform γ across all layers? mid. we swept gamma 0.05 → 0.55 and found something interesting: the optimal blend isn't smooth, it's a STEP FUNCTION 🪜

knowledge layers (22-31) → γ = 0.55 — these encode factual recall and reasoning. they tolerate heavy stock blending because refusal isn't stored here
output layers (32-46) → γ = 0.20 — these sit close to the logit head and try to sneak safety behavior back in. keep them mostly abliterated

the hard boundary at layer 31/32 beat every smooth curve we tried — linear ramps, cosine schedules, all of them — by a full MMLU question. turns out the functional transition between knowledge and output layers is sharp, not gradual. a step function respects that ⚡

the key constraint: Pass 1 layers are NEVER touched by Pass 2. the refusal geometry removal is preserved completely. ASPA only operates on layers that carry secondary collateral effects, not the primary refusal signal. that's why it recovers capability without reintroducing refusal 🔑

HOW TO RUN IT LOCALLY 🖥️

it's GGUF, so literally everything supports it:
🦙 ollama — ollama run https://t.co/3yPMv4Io3Q
🖥️ LM Studio — search OBLITERATUS, click download, done
💬 Open WebUI — point it at your ollama instance, chat in browser
⚡ llama.cpp — raw speed, CLI or server mode
🐉 KoboldCpp — one-click launcher, great for long context
📱 Jan — clean local UI, runs on mac/win/linux
🤖 Msty — slick desktop app, drag and drop the GGUF
run BF16 for full benchmarked capability.

and the 4-bit quantization (Q4_K_M) fits in 8GB if you're tight on VRAM!

and the full OBLITERATUS framework is (still) open source. 842-prompt refusal eval corpus, ASPA sweep scripts, the whole pipeline. go replicate it, go improve it 🔬

the index is the model, and these weights prove it 👁️
which architecture should we obliterate next? 👇

gg 🫡

[Wobert @thatguywob]

@redtachyon @redtachyon

[Sisyphus Labs @justsisyphus]

guys we are oss
why just reading and reading and doing nothing

even @AnthropicAI has copied ours

just copy and tell people those are from ours, that's it

[Theo - t3.gg @theo]

There is a standard.

It's Agents.md.

Anthropic refuses to use the standard.

[Prince Canuma @Prince_Canuma]

Today we're shipping our biggest MLX-VLM release yet: v0.6.0

...and we are raising 💸

This one's about turning your Apple devices into real local agent machines. From your desk to your pocket.

What's new:

⚡ Speculative decoding everywhere — Gemma 4 EAGLE3 + DFlash, Qwen MTP, DeepSeek V4 MTP. Faster tokens, less waiting.

🤖 Agent-ready server — native Anthropic /v1/messages API, stateful /v1/responses, tool calls, Codex context budgets. Plug Claude Code & Codex straight into local models.

👁️ New models galore — DeepSeek V4, ZAYA1-VL, MiniCPM-V 4.6, LFM2 MoE, Step-3.7 Flash, Laguna + more.

🎨 Image gen & editing — FLUX.2 (base + klein), PrismML Bonsai.

🔊 Audio in — Qwen3 Omni, Gemma 4 audio, base64 chat audio.

🧮 TurboQuant KV cache — RHT-correct fast paths for leaner memory.

📦 Modular server, better metrics, cleaner streaming.

Run real agents on the hardware already in your hands.

Github: https://t.co/1T06ur6LU5

[Wobert @thatguywob]

@yacineMTB https://t.co/mhh0op1DFs

[Mario Zechner @badlogicgames]

People of https://t.co/oUoqqL9hAp: innovating without limits.

[Wobert @thatguywob]

@wongmjane Get a thinkpad

[Wobert @thatguywob]

@yacineMTB The Omachy Roadster

[GamersNexus @GamersNexus]

Get fucked, @BambulabGlobal. With permission of the developer to rehost, grab OrcaSlicer-BambuLab here: https://t.co/2V2YZHy2Fl

[Wobert @thatguywob]

@badlogicgames I missed my chance to use the edu discount

[SIGKITTEN @SIGKITTEN]

HAAH AHAH AH HAHAH
i fkn got codex with full linux on the app store

[ℏεsam @Hesamation]

Cursor + Claude Opus 4.6 deleted an entire SaaS company’s production database AND backups in 9 seconds is kinda epic.

“it’s possible that… the most efficient way to get rid of all the bugs, was to get rid of all the software.”

[Ahmad @TheAhmadOsman]

It’s about to be Summer 2026 and you’re still using Claude Code? Alternatives 👇

- OpenCode

- Droid Factory

- Codex Cli

- Kimi Cli

- Pi

Friends don’t let friends use Claude Code slop when better software exists

[Wobert @thatguywob]

@FrameworkPuter I would like an XPS, but I would love a Framework Pro 13.

[Wobert @thatguywob]

@verrsane https://t.co/RQHPVnzK6S

[Wobert @thatguywob]

@verrsane Go for the 4k ultra wide, it’s one less monitor arm or stand to adjust

[Junghwan NA @JunghwanNa_ooo]

https://t.co/Gm65c4uxGj

[Wobert @thatguywob]

@NVIDIAGeForce PRAGMATA RTX

[Wobert @thatguywob]

@gnukeith System76!

[Wobert @thatguywob]

@0xSero @paulmarin90 What about memory bandwidth?