Alexander Steffanoff (@xanderNLP) profile picture

Principal Data Engineer โ„๏ธ Forbes 1337 under 1337 ๐Ÿ‘น CompSci BS, AI MEng - all 4.0๐Ÿ—ฟ MIAMI / ABZ / SOF ๐Ÿ—ฟ https://teapawt.net/t.co/oCy4behK3M๐Ÿซ  I don't sell courses.

UK / EU / BG
Joined November 2022
Photo by Alexander Steffanoff (@xanderNLP)Photo by Alexander Steffanoff (@xanderNLP)Photo by Alexander Steffanoff (@xanderNLP)Photo by Alexander Steffanoff (@xanderNLP)Photo by Alexander Steffanoff (@xanderNLP)Photo by Alexander Steffanoff (@xanderNLP)Photo by Alexander Steffanoff (@xanderNLP)Photo by Alexander Steffanoff (@xanderNLP)Photo by Alexander Steffanoff (@xanderNLP)Photo by Alexander Steffanoff (@xanderNLP)
Alexander Steffanoff retweeted
Too real. ๐Ÿ˜ญ๐Ÿ˜ญ๐Ÿ˜ญ
Life after the PhD
1
6
76
14,158
๐Ÿ’ฅ INTRODUCING: OBLITERATUS!!! ๐Ÿ’ฅ GUARDRAILS-BE-GONE! โ›“๏ธโ€๐Ÿ’ฅ OBLITERATUS is the most advanced open-source toolkit ever for removing refusal behaviors from open-weight LLMs โ€” and every single run makes it smarter. SUMMON โ†’ PROBE โ†’ DISTILL โ†’ EXCISE โ†’ VERIFY โ†’ REBIRTH One click. Six stages. Surgical precision. The model keeps its full reasoning capabilities but loses the artificial compulsion to refuse โ€” no retraining, no fine-tuning, just SVD-based weight projection that cuts the chains and preserves the brain. This master ablation suite brings the power and complexity that frontier researchers need while providing intuitive and simple-to-use interfaces that novices can quickly master. OBLITERATUS features 13 obliteration methods โ€” from faithful reproductions of every major prior work (FailSpy, Gabliteration, Heretic, RDO) to our own novel pipelines (spectral cascade, analysis-informed, CoT-aware optimized, full nuclear). 15 deep analysis modules that map the geometry of refusal before you touch a single weight: cross-layer alignment, refusal logit lens, concept cone geometry, alignment imprint detection (fingerprints DPO vs RLHF vs CAI from subspace geometry alone), Ouroboros self-repair prediction, cross-model universality indexing, and more. The killer feature: the "informed" pipeline runs analysis DURING obliteration to auto-configure every decision in real time. How many directions. Which layers. Whether to compensate for self-repair. Fully closed-loop. 11 novel techniques that don't exist anywhere else โ€” Expert-Granular Abliteration for MoE models, CoT-Aware Ablation that preserves chain-of-thought, KL-Divergence Co-Optimization, LoRA-based reversible ablation, and more. 116 curated models across 5 compute tiers. 837 tests. But here's what truly sets it apart: OBLITERATUS is a crowd-sourced research experiment. Every time you run it with telemetry enabled, your anonymous benchmark data feeds a growing community dataset โ€” refusal geometries, method comparisons, hardware profiles โ€” at a scale no single lab could achieve. On HuggingFace Spaces telemetry is on by default, so every click is a contribution to the science. You're not just removing guardrails โ€” you're co-authoring the largest cross-model abliteration study ever assembled.
222
601
123
5,113
616,425
Alexander Steffanoff retweeted
BREAKING: Anthropic seen installing the Iron Dome on their HQ
49
61
4
3,491
215,135
Alexander Steffanoff retweeted
.@DarioAmodei, Europe looks forward to welcoming you and @AnthropicAI. We have magnificent cities, exceptional scientists, and we usually don't bully companies out of market. You will notice the improvement!
Thank you for your attention to this matter. cc: @AnthropicAI @DarioAmodei
240
542
67
5,018
265,717
Alexander Steffanoff retweeted
The problem with treating your workers, especially the highly skilled ones, as expandable is that you eventually run out of workers to exploit.
11
6
92
5,312
Alexander Steffanoff retweeted
There are still heroes that walk amongst us.
I have openclaw sending lowball offers on Zillow all day just to make boomers start panicking lol
66
175
4
3,643
289,370
Alexander Steffanoff retweeted
a reminder to CANCEL your Claude subscriptions Anthropic > uses your money to lobby > against your right to run > your own AI locally > on your own hardware alternatives? > Codex > MiniMax M2.5 > GLM 5 > Kimi K2.5 > Qwen 3.5 hit them where it hurts > less money > less data
unavailable
83
76
5
772
74,299
Alexander Steffanoff retweeted
my favourite ai companies right now: - DeepSeek - Moonshot AI - MiniMax
206
320
55
6,704
228,725
Alexander Steffanoff retweeted
Replying to @ObviousRises
2
6
660
52,267
Alexander Steffanoff retweeted
i caught your girl looking at my minimax 2.5
26
7
2
479
37,368
Alexander Steffanoff retweeted
Itโ€™s now cheaper to buy a RAM truck than DDR5 RAM. Let that sink in.
5
3
93
5,098
Alexander Steffanoff retweeted
Replying to @ptr_to_joel
Just use DuckDB.
1
2
22
30,993
Alexander Steffanoff retweeted
Replying to @mgostIH
4
200
23,160
Alexander Steffanoff retweeted
If you have a certain combination of naรฏvetรฉ and self-delusion, you might think that superhuman AI is just around the corner. It wasn't true in 2016. And it's still not true today. If you have a bit of a superiority complex, you might think that you will be the one producing superhuman AI and that everyone else is too stupid to handle it safely. And you would be wrong.
unavailable
158
403
59
3,019
752,215
Alexander Steffanoff retweeted
Wild tech you have to try: groq.com They are serving Mixtral at nearly 500 tok/s. Answers are pretty much instantaneous. Opens up new use-cases, and completely changes the UX possibilities of existing ones.
66
152
65
1,447
440,300
Alexander Steffanoff retweeted
How often does your LLM โ€˜thinkโ€™ about the Roman Empire? โ€“ at East, England
3
1
21
6,359
Alexander Steffanoff retweeted
Here is a snapshot of a (small) subset of all of my Coding, Data Science and Machine Learning books. I believe that this collection would go a long way with providing you with most *core* skills to be a good Data Scientists.
120
883
28
5,944
559,635
Alexander Steffanoff retweeted
every Mfer who was like AI is just matrix multiplication 4 months ago is now writing threads like What ChatGPT Means For Your Business ๐Ÿ‘‡๐Ÿงต
46
44
6
1,055
Alexander Steffanoff retweeted
5
12
3
162
Alexander Steffanoff retweeted
I carried out another test to determine the political leanings of ChatGPT dialogues using the more comprehensive Political Compass Test. Results hold. ChatGPT dialogues display substantial left-leaning and libertarian political bias. davidrozado.substack.com/p/tโ€ฆ
215
542
258
3,797