clare clover

107 posts

clare clover banner
clare clover

clare clover

@claliclo

tech medic | university academic | clinician | consultancy | all in on ai

southern earth Katılım Ekim 2025
106 Takip Edilen6 Takipçiler
Sabitlenmiş Tweet
clare clover
clare clover@claliclo·
Real-world test of @claudeai Haiku 4.5 vs @OpenAI GPT-5 medium. Using @cursor_ai +/- plan mode to codify & summarise a complex medical transcript. Analysis by GPT5-Pro with structured eval rubric. Haiku 4.5_no-plan =4.0/5, Haiku4.5_+plan =4.3/5, GPT5 =4.6/5 Haiku 4.5 2-3x faster
clare clover tweet media
English
1
0
0
49
Shokz
Shokz@ShokzUSA·
Things we tested OpenDots 2 against: ✅ Training sessions ✅ All-day wear ✅ One (1) helium balloon The math seems to be mathing. At 6.4g per earbud, OpenDots 2 is about as light as the balloon itself 🎈 #Shokz #ClipPlayGo #Openearbuds #OpenDots2
English
5
2
14
5.2K
joe feeney
joe feeney@iamsomewalrus·
@jxnlco Pro and the fact I can’t go back and forth between codex and pro is crazy. Had to build a skill for it.
English
1
0
0
537
jason
jason@jxnlco·
If you use Codex, is there any reason you still use ChatGPT? what do you use it for? how has it been better or critical for you?
English
1K
13
1.1K
256.3K
Adrian Brojbeanu
Adrian Brojbeanu@theadriann·
@jxnlco I'm not fully sure whether Codex uses the same search stack as ChatGPT, or whether it relies more on tools from my local environment (+network)
English
1
0
1
1.3K
clare clover
clare clover@claliclo·
@the_fnu_lnu @mattpocockuk This is true but it’s solvable. Auto conversion with Docling, deterministic clean up script then overnight LLM final tidy including YAML header finalisation. I have many hundreds managed this way
English
1
0
0
17
fnu_lnu
fnu_lnu@the_fnu_lnu·
@mattpocockuk Emails, discord, all ok but as soon as you start ingesting PDFs it gets complicated with quality
English
1
0
0
289
Matt Pocock
Matt Pocock@mattpocockuk·
Doing my first ever experiments with a personal, entirely agent-managed Karpathy-style wiki X, Discord, Gmail are all being ingested into it every few hours This is the knowledge base that will serve as the environment for all of my future loops
English
121
35
1.6K
400K
Anders Jensen-Waud
Anders Jensen-Waud@jensenwaud·
@mattpocockuk I have tried that and found it quite slow. So I implemented a small embedded graph database instead to store it all. Works a lot better.
English
2
0
1
84
clare clover
clare clover@claliclo·
@trq212 Please be kind to us health professionals. We need it too.
English
0
0
0
11
Thariq
Thariq@trq212·
Have seen some questions about the updated classifiers and wanted to clarify. As with the original classifiers, a small fraction of routine coding and debugging tasks will be flagged and fall back to Opus. We're excited for guys to get access back tomorrow.
Anthropic@AnthropicAI

Claude Fable 5 will be available again globally tomorrow. After a series of productive conversations with the US government, we're redeploying the model with a new set of classifiers to target and block more cybersecurity tasks. In the near term, some routine tasks like coding and debugging will fall back to Opus 4.8. We’ll continue to refine these classifiers over the coming weeks to reduce false positives and better distinguish genuine misuse from legitimate requests. We’ve also begun drafting a consensus framework—with Amazon, Microsoft, Google, and other Glasswing partners—for assessing the severity of AI jailbreaks and how AI developers should respond to them. We invite other industry partners and model providers to join us in this effort. Finally, we’re scaling up our collaboration with the US government on model testing and safeguards. This will include pre-release access to models and safeguards for evaluation, information sharing on jailbreaks and misuse, and dedicated resources for joint research. Thank you to our users for your patience, and to our partners across the government, industry, and the research community who worked alongside us to make Fable 5 available again. Read our full blog: anthropic.com/news/redeployi…

English
566
174
3K
779K
Cursor
Cursor@cursor_ai·
Introducing Cursor for iOS. Build from anywhere by launching always-on cloud agents. Or remotely control agents running on your computer from the app. Composer 2.5 is 75% off in the app now through July 5.
English
964
1.1K
13.1K
6.4M
clare clover
clare clover@claliclo·
@jietang I would rather have no vision and same or better intelligence at a smaller size. For my 128GB Mac Studio would be nice!
English
0
0
0
17
jietang
jietang@jietang·
Any new features we must have in the next version of glm?
English
1.8K
140
4.6K
577.1K
clare clover
clare clover@claliclo·
@MatthewBerman Same reason top tier hotels don’t have a level 1. It lobby -> Level 9
English
0
0
1
6.7K
Matthew Berman
Matthew Berman@MatthewBerman·
Why is it called Fable 5 and not just Fable or Fable 1?
English
413
18
2.9K
577.8K
clare clover retweetledi
Justine Moore
Justine Moore@venturetwins·
@ianneo_ai By default, it will generate in Chinese - but you can easily ask to make it in English (or another language) instead. Link below, just give it to Codex and it will handle the rest. H/T to @ianneo_ai for making this! github.com/helloianneo/ia…
English
4
16
296
20K
Heptabase
Heptabase@Heptabase·
Agent Mode is now available in Heptabase AI! It can now edit and create cards, read images, follow mention links, read sub-whiteboards, and explore your knowledge base more deeply. This means better answers and less manual work.
English
4
2
34
5.4K
Josh Pigford
Josh Pigford@Shpigford·
i swear this is gonna make me turn clearly.md into an actual evernote alternative. and yes i'm aware i just deleted basically every clearly feature in the name of simplicity. 😭
Josh Pigford tweet media
English
14
0
50
9.3K
clare clover retweetledi
Thariq
Thariq@trq212·
HTML is the new markdown. I've stopped writing markdown files for almost everything and switched to using Claude Code to generate HTML for me. This is why.
Thariq@trq212

x.com/i/article/2052…

English
902
1K
12.1K
4.4M
Derek Martin 🇨🇦
Derek Martin 🇨🇦@lo_fye·
@claliclo @MatthewBerman I bought the same! But it’s soooo much screeeen. I can barely read the text at the far edges, and the screens overhang the edges of my desk, lol.
English
1
0
0
17
Matthew Berman
Matthew Berman@MatthewBerman·
thinking about getting the apple studio display 27", is it worth it? right now i have the lg 34" UltraWide 5K (about 7 years old, held up very well)
English
65
3
60
25.6K
clare clover
clare clover@claliclo·
@MatthewBerman I decided on 3x Dell UltraSharp 27 4K Thunderbolt Hub Monitor - U2725QE instead. No regrets screen quality
English
2
0
1
559
clare clover
clare clover@claliclo·
@Heptabase I have 2 accounts. Can it recreate a WB from one onto the other?
English
0
0
0
226
Heptabase
Heptabase@Heptabase·
Today, we're excited to release the Heptabase CLI — a new way for external AI agents to interact with your local Heptabase knowledge base from the terminal. Once enabled (Settings > AI Features > CLI), any AI coding agent (e.g., Claude Code, Codex) can: - Create, read, and edit note cards and journals - Search your Card Library - Manage tags - Read your AI Tutor courses, lessons, and chat history This is just the first step; we'll keep expanding the CLI surface so AI agents can act on your knowledge at the same depth that you can. If you build something interesting with it, feel free to share with our community!
English
6
7
87
14.6K