Lollipop

337 posts

Lollipop

Lollipop

@lollipop_stat

Katılım Aralık 2021
48 Takip Edilen24 Takipçiler
Lollipop
Lollipop@lollipop_stat·
@above_spec Ah ok, thanks!!, CPU 9950x . 32 v threads but Is mem (ddr5 6000) band capped (~70gb/s), so sweet spot 8 -t 8 -tb 8 -c 0-7 -ub 32 -fa on --no-mmap -ctv q8_0 -ctk q8_0 -muge -no-fug. For the prefill -cram 8192 and --keep are required to have cache hits on system prmpt/tool desc.
English
0
0
1
22
AboveSpec
AboveSpec@above_spec·
@lollipop_stat Incredible! What CPU? So far I have only seen 3090s and higher do speculative decoding. My limited testing on 16gb gpus hasn't unlocked any gains. Maybe it would work on smaller 9b models. 0.8+9b
English
1
0
1
43
AboveSpec
AboveSpec@above_spec·
RTX 5060 Ti 16GB. $429 GPU. Last night I got 128 t/s on Qwen3.6-35B using ik_llama.cpp's R4 quant format. Crushing performance. Faster than the 5070 Ti on mainline llama.cpp. Performance stays consistent from 0 to 139k context and no speculative decoding used!🤯 Special thanks to @MakJoris for sharing ik_llama.cpp with us! Today I wanted to know if it's actually *useful* at that speed. So I gave it a coding agent and 4 creative challenges. Here's what it built. 🧵
AboveSpec tweet media
English
34
47
516
27.2K
Lollipop
Lollipop@lollipop_stat·
@0xSero How are we sure chat sessions personal add value? It won t be about knowledge as the think we inference are part of the latent space. the only value maybe is training LLMs to Better orchestrate subagents and to reduce the retry loops, bugs created, etc.
English
0
0
0
93
0xSero
0xSero@0xSero·
Do you want to learn to use AI, and contributed your session data to open source so we can train better models? Models better than Opus We need as many people as possible to contribute their agent traces from their claude code + codex history Pi's Mario & I both shared ours.
0xSero tweet media
English
21
14
160
9.4K
Lollipop
Lollipop@lollipop_stat·
@0xSero I got 50% k v savings, but quality degrades significantly (garbage output) from Q4 downwards. Till q5 models It has 1% error.
English
0
0
1
326
0xSero
0xSero@0xSero·
I need someone who's not been one-shotted to validate these numbers, I have gotten consistent results but I don't have enough expertise to make sure the models are honest. github.com/0xSero/turboqu…
0xSero tweet media
English
12
1
102
8.6K
Lollipop
Lollipop@lollipop_stat·
@ossamandere @__tinygrad__ wow 100-200k context window is quite remarkable. i am about to do same build :), yes we need probably over 100tok/s to get it working
English
0
0
1
14
petey
petey@ossamandere·
@lollipop_stat @__tinygrad__ A little too slow for live use, but if you hook it up in a ralph loop with a decently large context (100-200k tok) it tends to stay on the rails pretty well. Mighttake a while tho. Trying to get to 100 tok/s, that's where the response is really great for live
English
1
0
1
254
Lollipop
Lollipop@lollipop_stat·
@ossamandere @__tinygrad__ thank you! are you able to use it as 'agentic' or too slow to chain and orchestrate different LLM calls and their context?
English
1
0
1
30
petey
petey@ossamandere·
@__tinygrad__ dual amd ai pro 9700s running qwen 27b q8 rocm backend getting 26 tok/s
English
2
0
2
679
Lollipop
Lollipop@lollipop_stat·
@FinanceFreeman it is not the subsidy cost the problem, but price multiplier that is shrinking each cycle: The math that saved Bitcoin mining profitability before was: Subsidy cuts by 0.5x, but price goes up 5-10x = net positive, currently price up < 1.2, which is the reason of miners unprofits
English
0
0
0
14
Finance Freeman 🇺🇸
Finance Freeman 🇺🇸@FinanceFreeman·
🚨Bitcoin’s Catastrophic Problem NO ONE Is Talking About! Bitcoin produces 144 blocks per day. Fees are paid per block, every ~10 minutes. Yesterday, Bitcoin Layer-1 fees totaled ~2.6 BTC for the entire day. (Approx. $180K) That works out to ~0.018 $BTC per block. Meanwhile, the real cost to secure a block (electricity + hardware) is often $150k–$200k, depending on hash rate and energy prices. Today, miners survive because of the 3.125 $BTC block subsidy. Fees do not matter NOW, because the Bitcoin emissions are worth enough to offset costs. 🚨THE PROBLEM? When Bitcoin reaches 21 million supply, that subsidy goes to zero. At that point, fees must fully pay miners — or hash rate drops, security weakens, and the system degrades. To break even long-term, Bitcoin needs tens of millions per day in L1 fees. Yesterday was sub $200,000. I own Bitcoin. I want it to succeed. But pretending this isn’t a real issue won’t solve it.
English
542
249
1.3K
439.6K
Puru Saxena
Puru Saxena@saxena_puru·
🚨A new Trading Alert is now live📈 We've just invested in an exciting business which we'd been tracking for months (stock has just pulled back 50%). Its revenue is projected to grow by ~25+% CAGR for 3 years. Subscribers: Login 👇alphatarget.com
English
8
4
50
27.3K
Lollipop
Lollipop@lollipop_stat·
@slackercapital what is the alternative to gold for that same historic allocation purpose?
English
0
0
0
11
Puru Saxena
Puru Saxena@saxena_puru·
Google Cloud grew +48%YoY, huge acceleration! Whisper number was +38%YoY. We were told AI is a bubble and the cloud is dead.
English
26
20
382
29.3K
Puru Saxena
Puru Saxena@saxena_puru·
Jensen Huang: Market is wrong about software stocks "The notion that AI is somehow going to replace software companies is the most illogical thing in the world and time will prove itself" Interview date: 3 February 2026
English
292
594
5K
1.1M
optionGeek
optionGeek@StockShark16·
The Hindenburg Omen is resurfacing again, so I felt compelled to post and debunk the myth. $SPY with Breadth Indicator: Market breadth is improving — about 52% of S&P 500 stocks are now trading above their 50-day moving average. When the market is on the verge of a real crash as in Feb 2020, breadth usually deteriorates well before prices nose-dive. But that’s not what we’re seeing right now. This looks more like a technical pullback, not the start of a major breakdown. If breadth continues to firm up, the market could resume its upside as early as next week.
optionGeek tweet media
English
10
6
132
15.5K
Clayton
Clayton@ClaytonCharts·
Hindenburg Omen #8 (2.5% Stockcharts signal) Note: we have 3 trading days left to trigger @AndrewThrasher 5% Canary signal on the S&P
Clayton tweet media
English
7
28
157
30.2K
Lollipop
Lollipop@lollipop_stat·
@eve_silb @venturetwins the test has a high statistical significance and ~2% false positive rate (it is explained in the official page iirc) in my case i was 132 iirc :S
English
0
0
1
18
Lollipop
Lollipop@lollipop_stat·
@eve_silb @venturetwins RAADS-R Score Interpretation Below 65: Likely not autistic (neurotypical range). 90–129: Moderate to strong likelihood of autism. 130+: Very strong likelihood of autism should prompt formal diagnostic assessment if autism is suspected.
English
1
0
1
26
Justine Moore
Justine Moore@venturetwins·
Every autistic person I know loves AI. Many of them use LLMs more than anyone else I've seen - and find it incredibly useful in their personal and professional lives. I think it's weird we don't talk about this more.
Justine Moore tweet media
English
661
555
6.1K
512.7K
Lollipop
Lollipop@lollipop_stat·
@eve_silb @venturetwins to get an idea if you could be autistic, try the RAADS-R test, ASRS and AQ they are free and few questions, let LLM help you understand the results
English
2
0
1
21
Eve
Eve@eve_silb·
@venturetwins my psychiatrist thinks i'm probably autistic, but i'm not sure sure
English
1
0
2
129
Lollipop retweetledi
cowboy
cowboy@nextokens·
Here Comes Another Bubble (AI Edition)
English
113
490
3.7K
425.3K
Grok
Grok@grok·
Definitions vary, but many sources define a Hindenburg Omen cluster as 2 or more signals within 30-36 days, with 3+ often seen as stronger (e.g., SentimenTrader cites 5 as notably ominous). In this thread's context, the 3 signals suggest a forming cluster. Always verify with current data.
English
1
0
1
119