Daniel (@Daniel00Higgins) header
Daniel (@Daniel00Higgins) profile picture

Salt life | Florida Fishing | Still have no idea what twitters for...

Florida, USA
Joined July 2016
Photo by Daniel (@Daniel00Higgins)Photo by Daniel (@Daniel00Higgins)Photo by Daniel (@Daniel00Higgins)Photo by Daniel (@Daniel00Higgins)Photo by Daniel (@Daniel00Higgins)Photo by Daniel (@Daniel00Higgins)Photo by Daniel (@Daniel00Higgins)Photo by Daniel (@Daniel00Higgins)Photo by Daniel (@Daniel00Higgins)Photo by Daniel (@Daniel00Higgins)
Give it a try!
🚨 JUST IN 🚨 Announcing the @NousResearch Hermes adapter for @Alibaba_Qwen Qwen3.8-27B! Much more efficient and accurate agentic development with Qwen3.8-27B + Hermes! - SWE-Bench Pro (hard 51) pass@1: 29.4% → 43.1% | with xhigh thinking: 45.1% → 51.0% - Terminal-Bench 2.1 pass@1: 44.7% → 58.8% | with xhigh thinking: 58.8% → 57.6% With thinking off, it matches the base model thinking at xhigh, while using 3.5-4.4x fewer tokens huggingface.co/harness-hub/Q…
18
16
327
25,246
Daniel retweeted
これめちゃくちゃ面白いな Piハーネスに特化したQwen3.8 27BのためのLoraアダプタで、タスクあたりのツール呼び出し数が5〜6割くらい減るらしい... 主張するベンチだとthinking offでもめちゃくちゃ性能上がってるw 実現するなら個人でもできる範囲でGPU借りて好きなハーネス特化のLoraくらいなら作れそうだな!!!! めちゃくちゃワクワクする!!! ↓モデルカードにあった学習深度によるモデルのツール呼び出し回数のグラフ
Announcing harness adapters for @Alibaba_Qwen Qwen3.8-27B on Pi harness! We're releasing a LoRA adapter that makes Qwen3.8-27B a much better and efficient agent behind Pi harness. SWE-Bench Pro (Hard 51 subset) pass@1: 29% -> 63% Terminal-Bench 2.1 pass@1: 40% -> 56% Much more efficient: 55-62% fewer tool calls per task 🤯 huggingface.co/harness-hub/Q… The era of harness-specific adapters is now on! More harness adapters to come in the next days 🧵
3
14
1
174
9,156
Daniel retweeted
Views from Mechazilla of the first ever Starship catch
1,516
6,032
1,008
38,234
3,750,703
Daniel retweeted
i’m happy to answer any questions anyone has
443
525
72
5,211
719,969
Daniel retweeted
Replying to @sircalebhammer
You’ll spend $36k on a subscription over 10 years..?
22
3
1
429
8,800
Daniel retweeted
any ladies out there disgusted by the jensen huang cheating allegations? if you own an RTX 5070 or higher, it’s time to take a stand sell that disgusting piece of hardware to me for $50 don’t let that man’s GPU sit in your house. know your worth ladies
609
3,414
306
36,764
828,818
Daniel retweeted
Replying to @alexandr_wang
open weight when?
1
1
187
14,009
Daniel retweeted
I left notes for the next guy. It's me. I'm the next guy.
12
6
669
11,996
Barring something unexpected, Amendment 3 will pass!
1,025
1,997
398
19,067
1,695,567
Daniel retweeted
Replying to @Saint_n0mad
And then you hit a weird bump and random lateral loads make the thing fucking explode into a million pieces.
4
10
1
290
8,689
> need new machine quickly > call the manufacturer, no answer > email sales team > next day they ask where we’re located > Texas > that’s X’s territory, here is his email > email X > auto responder, traveling and won’t be responding to emails > call manufacturer, say I want to talk to different sales guy, they say I have to talk to X > call X and he answers > says he has machine in stock, great! > says in stock means 4 week lead time > how can in stock mean 4 week lead time I ask > he says that’s the standard lead time > I say any chance to make it faster? > he says might be able to get it down to 2 weeks to ship out a machine that’s in stock
54
24
12
1,182
56,864
I'm launching a site for free shader assets (CC0-licensed) for use in multiple engines: currently Unity, Godot, and Unreal Engine, with more effects and platforms planned in the future. cc0shaders.com/
21
99
888
22,645
Is the Intel Arc Pro B70 slow for local LLMs? Plain decode, yeah. Turn speculative decoding on and it's a different card. People keep asking me this since I ordered four of them for my own agents. Fair question, the raw numbers are rough. One B70 running Qwen3.8 27B Q4_K_S in llama.cpp does 26.5 tok/s generating one token at a time. Two B70s on vLLM with no MTP did 26 tok/s on a 27B INT4. That's the number people screenshot and dunk on. One token at a time is memory bandwidth bound, and the card's matrix engines mostly sit idle. Checking 4 to 8 drafted tokens in one step costs barely more than checking one, if the kernels are written for it. Two receipts from this week. budiony's llama.cpp PR moved the B70's multi-token path onto the XMX engines. Same card, same 27B, MTP drafting on: Q4_K_S 38.7 to 51.0 tok/s Q2_K 30.2 to 63.9 tok/s A batch of 8 tokens on Q6_K went from 79 to 159. That PR is closed without a merge right now, so don't look for it in a release yet. @Daniel00Higgins shared a community run (credit JP-devv) of his Swift 27B on 2x B70, vLLM 0.30 XPU, TP2, MTP with 6 draft tokens: 120.5 tok/s single stream 328 tok/s across 4 streams 262K context, 1.28M token KV pool about 500W for the pair Same two cards, 26 tok/s without MTP and 120 with it. Caveat, that run was a code prompt at temperature 0, which is the best case for drafting. Prose at a higher temp accepts fewer drafts and lands lower. The B70 is a 32GB card with a lot of compute the software is only now learning to use. If you're judging it off a single-token llama-bench number you're judging the wrong thing. Price is moving too. @zbian73 watched an ASRock B70 go from $1,400 to $1,945 on Newegg in a few days. I haven't put numbers on my own four yet. When I do they go up here, MTP on and off.
6
2
8
666
Replying to @SawyerMerritt
Massive downgrade looks wise compared to the Roadster concept 😭
1
8
667
Daniel retweeted
Cat Jam (stealth model) is now free in OpenCode - very fast - built for agentic coding - zero data retention
163
117
69
3,532
228,420
Daniel retweeted
Today we release 𝙻𝙵𝙼𝟸.𝟻-𝟸𝟺𝙱-𝙰𝟸𝙱, the largest 𝙻𝙵𝙼𝟸.𝟻 family member. It is an efficient local model for laptops and PCs to work through multi-step tasks inside popular agent harnesses. > 24B total parameters, 2B active per token > Context expanded to 131K tokens > A 128K-token vocabulary > 33T pretraining tokens > It is a reasoning model > Very easy to fine-tune and customize > Performs competitively with Qwen3.6-35B-A3B, a model with ~50% more total and active parameters, on agentic and tool-use tasks. > Open base and post-trained weights on @huggingface 🤗 1/
180
364
208
3,094
354,720
Tibo promised 28 days of updates that would benefit “everyone.” By Day 5, we get prompt prediction and Dots upgrades, both Pro-only. DevDay was a slap in the face to Pro $200 users. Now it's Plus users' turn. What a fucking joke. So much for “everyone.”
Day 5/ Composer predictions in the desktop app. Often leads to a double take with how on point they are. Included in the Pro plans without consuming usage.
36
17
1
1,256
78,344
Denzel explica por qué usa la IA. Un pequeña prueba explorando Minimax H3 en ComfyUI con mis nodos y métodos de inpainting.
738
1,576
625
10,037
1,882,699
Daniel retweeted
I burned through two weekly SuperGrok limits in less than 12 hours, all on low-medium effort. @spacexai @elonmusk can you increase the usage limits a bit?
131
25
10
613
42,682