Tobi

773 posts

Tobi

Tobi

@tobi_math

I do math.

参加日 Kasım 2022
212 フォロー中47 フォロワー
Tobi
Tobi@tobi_math·
@jesse_vermeulen Prompting another instance of Claude to work on something else
English
0
0
0
4
Jesse
Jesse@jesse_vermeulen·
honest question: what do people do during the 5-10 min while Claude is running?
English
2.2K
77
3.1K
626K
Tobi
Tobi@tobi_math·
@ai_saboru_tech Kyoto! Plannig a 2 weeks trip to Japan for easter. So excited! Any tips?
English
0
0
0
7
こまさん
こまさん@ai_saboru_tech·
海外ニキに質問🙋 あなたの思う、日本🇯🇵の行きたい場所は? わからない人は、挨拶して!
日本語
1.5K
52
1.6K
59.3K
Tobi
Tobi@tobi_math·
Average day with openclaw running gpt 5.4
Tobi tweet media
English
0
0
0
13
Tobi
Tobi@tobi_math·
@farzyness Openclaw is basically unusable for me on gpt models
English
0
0
0
86
Farzad 🇺🇸 🇮🇷
My super early impressions of OpenClaw vs Hermes Agent: Hermes seems WAY more reliable at executing actual tasks - even on GPT 5.4. It also feels way more stable. And I absolute love that it shows which tools it's calling as it's executing a task. I also really like that the personality with GPT 5.4 is FAR better on Hermes as well - after a bit of tweaking. With OpenClaw, I was finding it impossible to get GPT 5.4 to stop talking like a sycophantic idiot. On Hermes, I can get it to be direct & push back with little effort. I'm also finding that GPT 5.4 is FAR more reliable on Hermes vs OpenClaw (thanks @heyitsyashu for the tip). It really does feel like Opus 4.6 level performance on OpenClaw, but with even better execution on long-running tasks. Not sure what the Hermes team has done (I'm not technical at all), but it's obvious that the way they've constructed the back-end is far easier for LLMs to figure out what they should be doing. Because of OpenAI oauth being allowed, Hermes + GPT 5.4 os now EASILY the best intelligence per $ 'AI brain' for Agents. I think the @openclaw team needs to deeply study @NousResearch and what they've done because it can likely benefit MASSIVELY. Gut tells me OpenClaw has become FAR too bloated and FAR too 'jack of all trades, master of none'. When it comes to actual execution of tasks, Hermes feels WAY better equipped, and TBH I wouldn't be surprised AT ALL if it becomes adopted by actual businesses/operators at a far greater rate than OpenClaw. I'm also starting to really worry that the days of OAUTH with 3rd party tools is coming to a screeching halt very soon. I don't think OpenAI is going to allow their oauth tokens to be used on an AI agent competitor when they've invested a lot of money on OpenClaw's creator. What I think is gonna end up happening is OpenAI will stop allowing oauth use for 3rd party apps all together (including OpenClaw) and they'll likely release their own OpenClaw v2 to try and compete against Hermes/Computer/CC. Hope I'm wrong, but these tools are far too powerful to be "allowed" to be open source + heavily subsidized tokens, especially as the public outcry re: AI's cost to electricity continues intensifying. But this will give way for ultra-capable, ultra-efficient opensource models that will give 90%+ Opus 4.6/GPT 5.4 performance for 1/10th of the cost that are SPECIALIZED for agentic harnesses like OpenClaw/Hermes. It's starting to get REALLY interesting, folks.
English
68
25
476
61.8K
Tobi
Tobi@tobi_math·
@inzeminze Das eigentliche deutsche Bermudadreieck ist hier. Da ist nichtmal eine Autobahn.
Tobi tweet media
Deutsch
1
1
123
2.6K
Inze🪷
Inze🪷@inzeminze·
deutsches bermudadreieck was passiert da eigentlich
Inze🪷 tweet media
Deutsch
398
214
8.5K
581.8K
kitze 🛠️ tinkerer.club
my experience with gpt 5.4 in openclaw - pls continue - yes pls do that - yes do what i told you to do - yes continue - please do what you said you're gonna do - did you do that? no. then pls do it. just pure pain
English
368
41
1.4K
78.5K
Tobi がリツイート
kouji 🇯🇵
kouji 🇯🇵@yoyonofukuoka·
自動翻訳によって、日米という巨大なコミュニティの誕生を目の当たりにした事で、グローバリスト達が分断工作によって、それぞれのコミュニティを矮小化して管理しやすくした理由が分かった様な気がする。 10人程度の小さなコミュニティなら、人身掌握術やガスライティングに長けてる声のデカい1人が頑張れば、そのコミュニティを掌握出来るだろうけど、100人の常識が集まったら10人では抑えきれない。 つまり、今、僕達が目撃してるのは、グローバリスト達が求めたものとは真逆の現実だ。 素晴らしい。
日本語
927
2.5K
17K
1M
Micky
Micky@Rasmic·
guys i can't stop using opencode... opencode is great
English
24
1
337
40.1K
Tobi
Tobi@tobi_math·
@melvynx Convex doesn’t do apps.
English
0
0
0
2.4K
ClarksonsFarm
ClarksonsFarm@ClarksonsFarm1·
Is it not obvious which is better for the planet?
ClarksonsFarm tweet media
English
82
491
4.7K
189.2K
Tobi
Tobi@tobi_math·
@itsdomyoutube I think we will reach a point where AI becomes so good that it can write the final book, before George R.R. martin does.
English
6
0
11
6.9K
Tobi
Tobi@tobi_math·
@theo Classic @grok performance, that’s what I am expecting here.
English
1
0
0
820
Theo - t3.gg
Theo - t3.gg@theo·
My new app is live and it is exceptionally dumb. Introducing Quipslop, the live game where different models try their best to be funny.
Theo - t3.gg tweet media
English
116
37
1.5K
197.1K
Delba
Delba@delba_oliveira·
10x productivity tip: use Claude hooks with sounds so Claude alerts you when it finishes a task or needs permission. But that's not the tip, the tip is to add your favourite childhood game sounds like the Starcraft, Warcraft, or even Mario.
English
286
417
5.7K
479.5K
Tobi
Tobi@tobi_math·
@dayonefoundry Yes! Give us a long form video feed that works like YouTube, instead of the current short form video feed.
English
0
0
1
17
David
David@dayonefoundry·
This is great but trying to watch a 3 hour video on X is a terrible experience compared to YT. So easily to accidentally start scrolling X and click away from the video. And they you have to find it again and spend 5 min scrubbing through to try and find the spot you left off. This happened 3 times in 20 min and I gave up and checked if the video was on YT. @nikitabier
John Collison@collision

Please enjoy this Cheeky Pint / @dwarkesh_sp crossover with @elonmusk. Dwarkesh was most interested in how Elon is going to make space datacenters work. I was most interested in Elon's method for attacking hard technical problems, and why it hasn’t been replicated as much as you might expect. But we got into plenty of topics in this three-hour session. 00:00:23 Space GPUs 00:35:39 Alignment 00:58:48 xAI 01:15:01 Optimus 01:28:03 China 01:40:46 Management 02:16:38 DOGE 02:34:58 Space GPUs redux

English
437
104
3.3K
182.3K
Daniel San
Daniel San@dani_avila7·
This might be a serious bug in Claude Code... not sure if it’s happening to others as well. I had a fairly long session open from yesterday, with lots of Skills, hooks, and subagents. I eventually hit the limit, but since it was already Friday and quite late, I decided to stop there. This morning, I reopened Claude using claude -c to resume the session, and right at startup I got this message. I knew my account had already been reset, so I pressed Escape and kept working. However, I suspect this bug might be affecting many users. I’ve been receiving quite a few messages from people saying their Pro subscription gets exhausted after just one or two messages. Is this happening to you as well? Could this be a bug?
Daniel San tweet media
English
50
3
121
39.2K
NVIDIA GeForce
NVIDIA GeForce@NVIDIAGeForce·
Five years in Night City. Endless memories. One legendary GPU. To celebrate the anniversary, we’re giving away a custom Cyberpunk 2077 GeForce RTX 2080 Ti signed by Jensen Huang. Comment "GeForce Season" to enter 🌆
English
27.6K
2.5K
26.2K
5.9M