Nikolay Savinov 🇺🇦
@SavinovNikolay
Followers
3K
Following
4K
Media
24
Statuses
927
Research Scientist at @GoogleDeepMind Work on LLM pre-training in Gemini ♊ Lead 10M context length in Gemini 1.5 📈
London, UK
Joined March 2018
I was leading long context in Gemini for a while now, and today I’m proud to share what the team has achieved: over 1M context in a large-scale foundation model. Big shoutout to @TeplyashinDenis and @machelreid - without you this would not have happened!.
9
19
227
RT @deedydas: China's Gaokao is the biggest exam in the world: 13M test takers and 9hrs. ~0.02% make it to the top uni, Tsinghua. As of thi….
0
208
0
RT @demishassabis: Really exciting to see the UK government choose Gemini to help speed up the planning process across the country.
0
160
0
RT @paulgauthier: Gemini 2.5 Pro 06-05 has set a new SOTA on the aider polyglot coding benchmark, scoring 83% with 32k thinking tokens. Th….
0
53
0
RT @OfficialLoganK: The new Gemini 2.5 Pro is SOTA at long context, especially capable on higher number of items being retrieved (needles)….
0
73
0
RT @lmarena_ai: 🚨Breaking from Arena: @GoogleDeepMind's new Gemini-2.5-Flash climbs to #2 overall in chat, a major jump from its April rele….
0
92
0
RT @mntruell: Cursor now supports 1M context-windows, the most expensive models, and unlimited tool calls with API pricing.
0
74
0
RT @burkov: Crazy times. This morning, while getting breakfast, I instructed Gemini to write a Python script that connects to my Spotify, p….
0
40
0
RT @Yampeleg: Gemini’s attention to detail is wild. Fed a ~400k token codebase and forgot about it. Found the tab still open a day later….
0
33
0
RT @JeffDean: Caching of tokens when you use the same input context repeatedly now happens implicitly, making things a lot easier to deal w….
0
26
0
No need to explicitly specify caching in Gemini API anymore, now it's done automatically - important for long-context applications, e.g. coding!.
We just shipped implicit caching in the Gemini API, automatically enabling a 75% cost savings with the Gemini 2.5 models when your request hits a cache 🚢. We also lowered the min token required to hit caches to 1K on 2.5 Flash and 2K on 2.5 Pro!.
2
3
56
RT @deedydas: 1. Take a screen recording explaining your app.2. Upload it to YouTube.3. "Build me this”. Gemini 2.5’s ability to comprehend….
0
332
0
Nice study on scaling needles for MRCR!.
1/ Context Arena Update: Added MRCR 4needle and 8needle results for some of the top models. It's probably we'll get more model releases between today and over the next 2 weeks. I'll try my best to keep up. 😅. Top Results (4needle, AUC @ 1M):.1. Gemini 2.5 Flash Preview
0
1
11
RT @doodlestein: The new update to Gemini 2.5 Pro is awesome. It’s totally incredible to me that I can now dump 2 megabytes of code (36.5k….
0
16
0
RT @emollick: Pretty awesome result from the new version of Gemini 2.5. I changed one line of War and Peace, inserting a sentence into Book….
0
74
0
RT @lmarena_ai: All these category strengths by the latest Gemini-2.5-Pro. 💻 Coding, Math, Creative Writing, Longer Query, . the communi….
0
11
0
RT @GoogleDeepMind: We’re releasing an updated Gemini 2.5 Pro (I/O edition) to make it even better at coding. 🚀. You can build richer web a….
0
535
0
RT @OfficialLoganK: Gemini 2.5 Pro just got an upgrade & is now even better at coding, with significant gains in front-end web dev, editing….
0
355
0
RT @demishassabis: Artificial Pokémon Intelligence achieved!😀 been a lot of fun to watch - congrats to the Gemini team and thanks @TheCodeO….
0
165
0
Check out our deep dive into long context with @OfficialLoganK!.
Dive into long context in the latest Release Notes podcast 🎙. @GoogleDeepMind’s @OfficialLoganK and @SavinovNikolay discuss scaling context windows into the millions, recent quality improvements, RAG versus long context, and more. Key moments:.0:52 Introduction & defining
3
7
66