Thomas Friedel
@thomascygn.bsky.social
Tackling AI for agriculture @ https://plantix.net/ 🌱
Claude's new Office doc skills (PPTX, DOCX, XLSX, PDF) are 🔥
I've repackaged them for Claude Code, so now you can automate the creation of powerpoint
presentations and other documents from the CLI or in your product.
github.com/tfriedel/cla...
I've repackaged them for Claude Code, so now you can automate the creation of powerpoint
presentations and other documents from the CLI or in your product.
github.com/tfriedel/cla...
GitHub - tfriedel/claude-office-skills: Office document creation and editing skills for Claude Code - PPTX, DOCX, XLSX, and PDF workflows with automation support
Office document creation and editing skills for Claude Code - PPTX, DOCX, XLSX, and PDF workflows with automation support - tfriedel/claude-office-skills
github.com
October 4, 2025 at 3:22 PM
Claude's new Office doc skills (PPTX, DOCX, XLSX, PDF) are 🔥
I've repackaged them for Claude Code, so now you can automate the creation of powerpoint
presentations and other documents from the CLI or in your product.
github.com/tfriedel/cla...
I've repackaged them for Claude Code, so now you can automate the creation of powerpoint
presentations and other documents from the CLI or in your product.
github.com/tfriedel/cla...
Reposted by Thomas Friedel
🧵 THREAD: A federal whistleblower just dropped one of the most disturbing cybersecurity disclosures I’ve ever read.
He's saying DOGE came in, data went out, and Russians started attempting logins with new valid DOGE passwords
Media's coverage wasn't detailed enough so I dug into his testimony:
He's saying DOGE came in, data went out, and Russians started attempting logins with new valid DOGE passwords
Media's coverage wasn't detailed enough so I dug into his testimony:
April 18, 2025 at 12:10 AM
🧵 THREAD: A federal whistleblower just dropped one of the most disturbing cybersecurity disclosures I’ve ever read.
He's saying DOGE came in, data went out, and Russians started attempting logins with new valid DOGE passwords
Media's coverage wasn't detailed enough so I dug into his testimony:
He's saying DOGE came in, data went out, and Russians started attempting logins with new valid DOGE passwords
Media's coverage wasn't detailed enough so I dug into his testimony:
Reposted by Thomas Friedel
Switzerland seems to also allow training on copyrighted works: www.vischer.com/en/knowledge...
Part 26: AI training: How to Handle Copyright, Data Protection And Other Restrictions
27 March 2025 - AI models – especially large language models – need to see a lot of data as part of their training so that they can map the concepts required...
www.vischer.com
March 27, 2025 at 7:15 AM
Switzerland seems to also allow training on copyrighted works: www.vischer.com/en/knowledge...
The new chatgpt image style transfer is so impressive. Love the caricatures the most!
March 26, 2025 at 11:14 PM
The new chatgpt image style transfer is so impressive. Love the caricatures the most!
Reposted by Thomas Friedel
Obstore v0.6 brings simple, painless integration with Microsoft Planetary Computer!
- *Automatic token refresh*. No need to manually fetch SAS tokens and never think about token expiration times again.
- STAC API integration
developmentseed.org/obstore/late...
- *Automatic token refresh*. No need to manually fetch SAS tokens and never think about token expiration times again.
- STAC API integration
developmentseed.org/obstore/late...
Releasing obstore 0.6! - obstore
The simplest, highest-throughput Python interface to S3, GCS & Azure Storage, powered by Rust.
developmentseed.org
March 24, 2025 at 5:24 PM
Obstore v0.6 brings simple, painless integration with Microsoft Planetary Computer!
- *Automatic token refresh*. No need to manually fetch SAS tokens and never think about token expiration times again.
- STAC API integration
developmentseed.org/obstore/late...
- *Automatic token refresh*. No need to manually fetch SAS tokens and never think about token expiration times again.
- STAC API integration
developmentseed.org/obstore/late...
Reposted by Thomas Friedel
There's now so many awesome #geospatial people here it's hard to keep track! 🤩
Here's a thread of some of my favourite starter packs so far - let me know what I've missed!
🛰️ Earth Observation & remote sensing: go.bsky.app/4PMRhNL
🌏 GIS: go.bsky.app/TJ7qQF6 @milos-makes-maps.bsky.social
(1/n)
Here's a thread of some of my favourite starter packs so far - let me know what I've missed!
🛰️ Earth Observation & remote sensing: go.bsky.app/4PMRhNL
🌏 GIS: go.bsky.app/TJ7qQF6 @milos-makes-maps.bsky.social
(1/n)
November 19, 2024 at 1:22 AM
There's now so many awesome #geospatial people here it's hard to keep track! 🤩
Here's a thread of some of my favourite starter packs so far - let me know what I've missed!
🛰️ Earth Observation & remote sensing: go.bsky.app/4PMRhNL
🌏 GIS: go.bsky.app/TJ7qQF6 @milos-makes-maps.bsky.social
(1/n)
Here's a thread of some of my favourite starter packs so far - let me know what I've missed!
🛰️ Earth Observation & remote sensing: go.bsky.app/4PMRhNL
🌏 GIS: go.bsky.app/TJ7qQF6 @milos-makes-maps.bsky.social
(1/n)
Reposted by Thomas Friedel
Visiting friends in New York
March 12, 2025 at 3:36 AM
Visiting friends in New York
Reposted by Thomas Friedel
My new paper "Deep Learning is Not So Mysterious or Different": arxiv.org/abs/2503.02113. Generalization behaviours in deep learning can be intuitively understood through a notion of soft inductive biases, and formally characterized with countable hypothesis bounds! 1/12
March 5, 2025 at 3:38 PM
My new paper "Deep Learning is Not So Mysterious or Different": arxiv.org/abs/2503.02113. Generalization behaviours in deep learning can be intuitively understood through a notion of soft inductive biases, and formally characterized with countable hypothesis bounds! 1/12
Reposted by Thomas Friedel
asking the GOP, will they impeach this mf?
March 4, 2025 at 6:54 PM
asking the GOP, will they impeach this mf?
Reposted by Thomas Friedel
Among all the utterly insane stuff going on, this ranks pretty high on the insane scale. mRNA vaccines are one of the great scientific advances of this century.
www.newsfromthestates.com/article/bill...
www.newsfromthestates.com/article/bill...
Bill banning mRNA vaccines in Iowa passes subcommittee
A bill banning gene-based vaccines, like some forms of the COVID-19 vaccine, received approval from a Senate subcommittee Monday.
www.newsfromthestates.com
March 4, 2025 at 5:20 PM
Among all the utterly insane stuff going on, this ranks pretty high on the insane scale. mRNA vaccines are one of the great scientific advances of this century.
www.newsfromthestates.com/article/bill...
www.newsfromthestates.com/article/bill...
Reposted by Thomas Friedel
This is a crazy paper. Fine-tuning a big GPT-4o on a small amount of insecure code or even "bad numbers" (like 666) makes them misaligned in almost everything else. They are more likely to start offering misinformation, spouting anti-human values, and talk about admiring dictators. Why is unclear.
February 25, 2025 at 9:01 PM
This is a crazy paper. Fine-tuning a big GPT-4o on a small amount of insecure code or even "bad numbers" (like 666) makes them misaligned in almost everything else. They are more likely to start offering misinformation, spouting anti-human values, and talk about admiring dictators. Why is unclear.
Reposted by Thomas Friedel
Reposted by Thomas Friedel
Microsoft's OmniParser V2: Turning Any LLM into a Computer Use Agent
Blog: www.microsoft.com/en-us/resear...
Hugging Face: huggingface.co/microsoft/Om...
GitHub: github.com/microsoft/Om...
Blog: www.microsoft.com/en-us/resear...
Hugging Face: huggingface.co/microsoft/Om...
GitHub: github.com/microsoft/Om...
February 15, 2025 at 8:22 AM
Microsoft's OmniParser V2: Turning Any LLM into a Computer Use Agent
Blog: www.microsoft.com/en-us/resear...
Hugging Face: huggingface.co/microsoft/Om...
GitHub: github.com/microsoft/Om...
Blog: www.microsoft.com/en-us/resear...
Hugging Face: huggingface.co/microsoft/Om...
GitHub: github.com/microsoft/Om...
Reposted by Thomas Friedel
an audible “no fucking way..” escapes my mouth
they claim that you can get LLMs to give you well calibrated confidence scores
like, i knew you could do something like this with logits/attention values, but the idea that the LLM could speak it back to you.. 🤯
they claim that you can get LLMs to give you well calibrated confidence scores
like, i knew you could do something like this with logits/attention values, but the idea that the LLM could speak it back to you.. 🤯
Now I have some evidence to back up me telling all my collaborators to add confidence predictions to their prompts. Anecdotally, I've found this helpful for classification tasks.
arxiv.org/abs/2412.14737
arxiv.org/abs/2412.14737
On Verbalized Confidence Scores for LLMs
The rise of large language models (LLMs) and their tight integration into our daily life make it essential to dedicate efforts towards their trustworthiness. Uncertainty quantification for LLMs can es...
arxiv.org
February 7, 2025 at 11:21 PM
an audible “no fucking way..” escapes my mouth
they claim that you can get LLMs to give you well calibrated confidence scores
like, i knew you could do something like this with logits/attention values, but the idea that the LLM could speak it back to you.. 🤯
they claim that you can get LLMs to give you well calibrated confidence scores
like, i knew you could do something like this with logits/attention values, but the idea that the LLM could speak it back to you.. 🤯
Reposted by Thomas Friedel
🌍 New paper: Generative networks for spatio-temporal #gap_filling of #Sentinel2 reflectances @esa.int.
🆓 Free access the first 50 days to the #ISPRS paper @elsevierconnect.bsky.social:
isp-uv.short.gy/GapFillingSe...
Work developed in the context of Xaida Project.
#AI #EarthObservation
🆓 Free access the first 50 days to the #ISPRS paper @elsevierconnect.bsky.social:
isp-uv.short.gy/GapFillingSe...
Work developed in the context of Xaida Project.
#AI #EarthObservation
January 29, 2025 at 2:28 PM
🌍 New paper: Generative networks for spatio-temporal #gap_filling of #Sentinel2 reflectances @esa.int.
🆓 Free access the first 50 days to the #ISPRS paper @elsevierconnect.bsky.social:
isp-uv.short.gy/GapFillingSe...
Work developed in the context of Xaida Project.
#AI #EarthObservation
🆓 Free access the first 50 days to the #ISPRS paper @elsevierconnect.bsky.social:
isp-uv.short.gy/GapFillingSe...
Work developed in the context of Xaida Project.
#AI #EarthObservation
Reposted by Thomas Friedel
Today’s Stratechery was great on this: stratechery.com/2025/deepsee...
DeepSeek FAQ
DeepSeek has completely upended people’s expectations for AI and competition with China. What is it, and why does it matter?
stratechery.com
January 28, 2025 at 4:11 AM
Today’s Stratechery was great on this: stratechery.com/2025/deepsee...
Reposted by Thomas Friedel
Today, the Sentinel-2C spacecraft will take over from S2A in providing operational data.
This is wonderful news, and will ensure continuity of the Sentinel data for many years to come. Great effort from the S2C commissioning team!
See here for more info: sentinels.copernicus.eu/web/sentinel...
This is wonderful news, and will ensure continuity of the Sentinel data for many years to come. Great effort from the S2C commissioning team!
See here for more info: sentinels.copernicus.eu/web/sentinel...
January 21, 2025 at 10:09 AM
Today, the Sentinel-2C spacecraft will take over from S2A in providing operational data.
This is wonderful news, and will ensure continuity of the Sentinel data for many years to come. Great effort from the S2C commissioning team!
See here for more info: sentinels.copernicus.eu/web/sentinel...
This is wonderful news, and will ensure continuity of the Sentinel data for many years to come. Great effort from the S2C commissioning team!
See here for more info: sentinels.copernicus.eu/web/sentinel...
Reposted by Thomas Friedel
Google's Titans: a new architecture with attention and a meta in-context memory that learns how to memorize at test time as presented by one of the author - @alibehrouz.bsky.social
January 13, 2025 at 7:53 PM
Google's Titans: a new architecture with attention and a meta in-context memory that learns how to memorize at test time as presented by one of the author - @alibehrouz.bsky.social
Reposted by Thomas Friedel
"Sky-T1-32B-Preview, our reasoning model that performs on par with o1-preview on popular reasoning and coding benchmarks."
That was quick! Is this already the Alpaca moment for reasoning models?
Source: novasky-ai.github.io/posts/sky-t1/
That was quick! Is this already the Alpaca moment for reasoning models?
Source: novasky-ai.github.io/posts/sky-t1/
January 14, 2025 at 12:34 AM
"Sky-T1-32B-Preview, our reasoning model that performs on par with o1-preview on popular reasoning and coding benchmarks."
That was quick! Is this already the Alpaca moment for reasoning models?
Source: novasky-ai.github.io/posts/sky-t1/
That was quick! Is this already the Alpaca moment for reasoning models?
Source: novasky-ai.github.io/posts/sky-t1/
Reposted by Thomas Friedel
False-color data from Maxar (left) and Planet (right) reveal the horrific extent of destruction in LA. Never seen anything like the scenes on the ground. Stay safe, donate, support climate action
January 9, 2025 at 5:09 PM
False-color data from Maxar (left) and Planet (right) reveal the horrific extent of destruction in LA. Never seen anything like the scenes on the ground. Stay safe, donate, support climate action
Reposted by Thomas Friedel
A new position paper on "inference time compute".
They present some theory on why it is necessary, how does it work, why we need it and what does it mean for "super" intelligence.
They present some theory on why it is necessary, how does it work, why we need it and what does it mean for "super" intelligence.
January 9, 2025 at 9:23 PM
A new position paper on "inference time compute".
They present some theory on why it is necessary, how does it work, why we need it and what does it mean for "super" intelligence.
They present some theory on why it is necessary, how does it work, why we need it and what does it mean for "super" intelligence.
Reposted by Thomas Friedel
This might be the first time after 10 years that boosted trees are not the best default choice when working with data in tables.
Instead a pre-trained neural network is, the new TabPFN, as we just published in Nature 🎉
Instead a pre-trained neural network is, the new TabPFN, as we just published in Nature 🎉
January 8, 2025 at 6:00 PM
This might be the first time after 10 years that boosted trees are not the best default choice when working with data in tables.
Instead a pre-trained neural network is, the new TabPFN, as we just published in Nature 🎉
Instead a pre-trained neural network is, the new TabPFN, as we just published in Nature 🎉