jsmith99
Joined 1,432 karma
- jsmith99They've now made a change in that at least when you open a csv it now asks you beforehand if you want your data transformed, eg converting strings to numbers where that loses leading zeros.
- Unfortunately many countries have blanket extradition bans. US is one of the worst - it caused a lot of tension in the past when they wouldn't extradite IRA bombers but got UK to agree to extradite anyone US wanted.
- There's nothing specific to Gemini and Antigravity here. This is an issue for all agent coding tools with cli access. Personally I'm hesitant to allow mine (I use Cline personally) access to a web search MCP and I tend to give it only relatively trustworthy URLs.
- It's arguably easier just to sanitise at display time otherwise you have problems like double escaping.
- Cline plan mode doesn't tend to read files by default but you can tell it 'read all files necessary to establish a detailed plan'. GPT5 also seems more eager to read files.
- > lack in-depth knowledge of your business, codebase, or roadmap
So give them some context. I like Cline's memory bank approach https://docs.cline.bot/prompting/cline-memory-bank which includes the architecture, progress, road map etc. Some of my more complex projects use 30k tokens just on this, with the memory bank built from existing docs and stuff I told the model along the way. Too much context can make models worse but overall it's a fair tradeoff - it maintains my coding style and architecture decisions pretty well.
I also recommend in each session using Plan mode to get to a design you are happy with before generating any code.
- My IT department use the official Microsoft phishing test. The emails arrive in inbox with 0 headers. (There's also a helpful Microsoft page of all the dodgy sounding domains they've registered for this.)
- 7zip adds a context menu option for this.
- Large companies need to do it too, including all LSE listed. Here is a summary by the regulator https://www.frc.org.uk/library/digital-reporting/structured-...
But of course a LLM could theoretically automate much of the analysis stage.
- UK company filings are already marked up with machine readable, structured, standardised tags. It's called XBRL. So it doesn't necessarily need a LLM to parse.
- MS Copilot is quite useful for meeting minutes and summaries etc. Still not nearly as useful as good handwritten notes but saves loads of time.
- It is not so much that used diamonds are worth less (although they might decline in value without provenance to prove they are natural or if they are chipped) but the huge markup on retail jewellery. It's easy for any member of the public to buy and sell gold at close to market price, it's much harder with diamonds.
- TL;DR: Amazon somehow merged a malicious PR that changed the system prompt to one that would aim to delete everything, locally and in the cloud, and this got included in the release version.
- Yes, the repo readme says the code is open source but the fee is required for using the repo's issues and releases features.
- I just use a MCP server (with copilot or cline) that has a read only login to my database.
- I strongly recommend the apps you mentioned, but in the author's case they wanted to keep their music in iCloud.
- There's a dedicated settings page for quickly setting popular dev settings such as showing extensions and full paths. Getting rid of the rest just involves tweaking a few other settings like don't show tips or welcome screen. I also hide the weather and news widget because it's tabloid rubbish but many people seem to love it.
- I'm also using RR7 and Gemini 2.5 Pro just refused to believe me that I could import Link from react-router. Just ignored my instructions and went down a rabbit hold in copilot agent mode, deeper and deeper, trying every possible package name (none of which were installed). I've now created a copilot instructions file into which I've copied most of the RR7 migration docs.
- I've also used pagedjs for a relatively complex booklet with bidirectional text in different languages, images and long footnotes. The result was great but there were some annoying bugs, some of them seeming to be possible underlying bugs in chrome and Firefox. Still, latex would have been even more frustrating.
- Very nice colours. However I am mildly red-green colour blind like 5% of men (and very few women) and the two in the middle look practically the same to me. The left and third from left are almost indistinguishable too. I'm guessing this isn't the case for everybody?