MarineLives
@marinelives.bsky.social
Lives touched by the marine, 1574-1688. A volunteer led collaboration publishing to the Commons. See also: https://generativelives.substack.com/
Some potential topics for the ai-and-history-collaboratory to discuss in the next few months #ai #history #llms @anterotesis.bsky.social @bho.bsky.social @ihr.bsky.social
November 26, 2025 at 6:02 PM
Some potential topics for the ai-and-history-collaboratory to discuss in the next few months #ai #history #llms @anterotesis.bsky.social @bho.bsky.social @ihr.bsky.social
(5) Here is an extract from our Users Manual for Ver.4.4
November 24, 2025 at 7:13 AM
(5) Here is an extract from our Users Manual for Ver.4.4
(4) I selected Cautious Inference Mode. Made no edits to the RA's Persona. Then saved the RA's original message and the RA's conirmation of Cautious Mode to the Research Board on the right.
November 23, 2025 at 8:42 PM
(4) I selected Cautious Inference Mode. Made no edits to the RA's Persona. Then saved the RA's original message and the RA's conirmation of Cautious Mode to the Research Board on the right.
(3) Click on Calibrate Assistant and you havean inference spectrum: strict, cautious, moderate, and bold. Each mode has associated text defining that inference approach, which you can edit. The preference is then sticky, but can be altered during the session with the RA
November 23, 2025 at 8:38 PM
(3) Click on Calibrate Assistant and you havean inference spectrum: strict, cautious, moderate, and bold. Each mode has associated text defining that inference approach, which you can edit. The preference is then sticky, but can be altered during the session with the RA
Here is the next screen after you register. The RA explains its capabilities and asks to calibrate the user's preferences for inference approach. Note teh Research Board on the right. You can add your own User Notes. Everything captured and tagged in JSON.
November 23, 2025 at 8:34 PM
Here is the next screen after you register. The RA explains its capabilities and asks to calibrate the user's preferences for inference approach. Note teh Research Board on the right. You can add your own User Notes. Everything captured and tagged in JSON.
I am looking for a couple of beta testers who will take half an hour and try out a Socratic Research Assistant I have been building powered by Gemini 3.0 Pro Preview. The idea is to get much greater control over the persona, and inference approach of Gemini through the interface
November 23, 2025 at 8:29 PM
I am looking for a couple of beta testers who will take half an hour and try out a Socratic Research Assistant I have been building powered by Gemini 3.0 Pro Preview. The idea is to get much greater control over the persona, and inference approach of Gemini through the interface
Here are the Yorkshire data. Scarborough and Hull.
July 20, 2025 at 1:32 PM
Here are the Yorkshire data. Scarborough and Hull.
Did ships get bigger in the C17th? Yes. Contact me if you would like access to the data and would like to discuss. And of course the devil is in the detail, but this is a relatively and well defined large dataset #earlymodern #marinehistory @thiagokrause.bsky.social @brodiewaddell.bsky.social
July 20, 2025 at 12:17 PM
Did ships get bigger in the C17th? Yes. Contact me if you would like access to the data and would like to discuss. And of course the devil is in the detail, but this is a relatively and well defined large dataset #earlymodern #marinehistory @thiagokrause.bsky.social @brodiewaddell.bsky.social
A potential use of AI image analysis which could be done at scale as part of an analysis of historic literacy? I loaded images of 140 signature, initial(s), mark(s) into NotebookLM & interrogated them palaeographically (with zero training). @thiagokrause.bsky.social @timhitchcock.bsky.social
June 18, 2025 at 8:03 AM
A potential use of AI image analysis which could be done at scale as part of an analysis of historic literacy? I loaded images of 140 signature, initial(s), mark(s) into NotebookLM & interrogated them palaeographically (with zero training). @thiagokrause.bsky.social @timhitchcock.bsky.social
Looking for a Turkish speaker who would be willing to sample a couple of minutes of a Turkish podcast generated by Google NoteBook LM Plus [podcasts in 50 languages, handles 300 sources, very useful mindmaps]. Can send .wav file or give NB access @thiagokrause.bsky.social @timhitchcock.bsky.social
May 16, 2025 at 11:22 AM
Looking for a Turkish speaker who would be willing to sample a couple of minutes of a Turkish podcast generated by Google NoteBook LM Plus [podcasts in 50 languages, handles 300 sources, very useful mindmaps]. Can send .wav file or give NB access @thiagokrause.bsky.social @timhitchcock.bsky.social
Many different types of vessel in the SOLM-QUANT database, all waiting to be characterised quantitatively and qualitatively
May 1, 2025 at 1:00 PM
Many different types of vessel in the SOLM-QUANT database, all waiting to be characterised quantitatively and qualitatively
Looking for two or three Early Modern marine historians, marine archaeologists, and knowledgeable enthusiasts interested in exploring novel, as yet unpublished 5,000+ ship database [SOLM-QUANT] for C17th commercial (and naval) ships - Get in touch to learn more #marinehistory #earlymodern
May 1, 2025 at 12:30 PM
Looking for two or three Early Modern marine historians, marine archaeologists, and knowledgeable enthusiasts interested in exploring novel, as yet unpublished 5,000+ ship database [SOLM-QUANT] for C17th commercial (and naval) ships - Get in touch to learn more #marinehistory #earlymodern
An extract from four case studies of ship to shore and shore to ship operational communication, a section within CH 6: Strategy, Operations and Geography, CH 6: Strategy, Operations and Geography. @brodiewaddell.bsky.social
April 16, 2025 at 8:24 AM
An extract from four case studies of ship to shore and shore to ship operational communication, a section within CH 6: Strategy, Operations and Geography, CH 6: Strategy, Operations and Geography. @brodiewaddell.bsky.social
Here is a brief intro
April 16, 2025 at 5:41 AM
Here is a brief intro
I have been busy these last four months. Now looking for a publisher. Any suggestions. Can supply draft chapters and appendices for anyone interested in taking a look. @timhitchcock.bsky.social @brodiewaddell.bsky.social
April 15, 2025 at 1:59 PM
I have been busy these last four months. Now looking for a publisher. Any suggestions. Can supply draft chapters and appendices for anyone interested in taking a look. @timhitchcock.bsky.social @brodiewaddell.bsky.social
We have a nice new shiny organization card for MarineLives on Hugging Face, where you can find models and datasets huggingface.co/MarineLives
December 9, 2024 at 8:56 PM
We have a nice new shiny organization card for MarineLives on Hugging Face, where you can find models and datasets huggingface.co/MarineLives
4/ I am performing the test fine-tune from a Colab notebook, and am monitoring the evaluation, training and systems data from a Weights and Biases monitoring screen. I'm using a paid T4 GPU @beismo.bsky.social
December 7, 2024 at 12:37 PM
4/ I am performing the test fine-tune from a Colab notebook, and am monitoring the evaluation, training and systems data from a Weights and Biases monitoring screen. I'm using a paid T4 GPU @beismo.bsky.social
3/ Everything looks good so far. I am three epochs into a test run of a ten epoch fine-tune. @beismo.bsky.social @timhitchcock.bsky.social
December 7, 2024 at 12:34 PM
3/ Everything looks good so far. I am three epochs into a test run of a ten epoch fine-tune. @beismo.bsky.social @timhitchcock.bsky.social
2/ My first fine-tuning run is going to be a fine-tune of mBert (110M parameter LLM) using paired line Yiddish Hebrew text. I am running it for 10 epochs as a test. I got Gemini to modify some existing code I have @beismo.bsky.social @timhitchcock.bsky.social
December 7, 2024 at 12:31 PM
2/ My first fine-tuning run is going to be a fine-tune of mBert (110M parameter LLM) using paired line Yiddish Hebrew text. I am running it for 10 epochs as a test. I got Gemini to modify some existing code I have @beismo.bsky.social @timhitchcock.bsky.social
I am working with @beismo.bsky.social to fine-tune two small large language models to correct raw machine transcription of Yiddish in Hebrew script. We plan to show the results this coming Tuesday at our next ai-and-history-collaboratory @timhitchcock.bsky.social @mark-l-thompson.bsky.social
December 7, 2024 at 12:02 PM
I am working with @beismo.bsky.social to fine-tune two small large language models to correct raw machine transcription of Yiddish in Hebrew script. We plan to show the results this coming Tuesday at our next ai-and-history-collaboratory @timhitchcock.bsky.social @mark-l-thompson.bsky.social
Do you wonder what "fine-tuning" a large language model means? How could it help in historical research? Next Tuesday during our weekly one hour ai-and-history-collaboratory we are going to run some code and train a small large language model called mT5 github.com/Addaci/marin...
December 6, 2024 at 10:26 AM
Do you wonder what "fine-tuning" a large language model means? How could it help in historical research? Next Tuesday during our weekly one hour ai-and-history-collaboratory we are going to run some code and train a small large language model called mT5 github.com/Addaci/marin...
Interested in learning to use large language models for historical research? We have a Colab notebook which guides non-coders through using APIs to interrogate data github.com/Addaci/Aurel...
December 3, 2024 at 11:24 AM
Interested in learning to use large language models for historical research? We have a Colab notebook which guides non-coders through using APIs to interrogate data github.com/Addaci/Aurel...
Revised agenda and link again to the Colab notebook on our GitHub site github.com/Addaci/Aurel...
December 3, 2024 at 11:22 AM
Revised agenda and link again to the Colab notebook on our GitHub site github.com/Addaci/Aurel...