This might be beating a dead horse, but there are several "mysterious" problems LLMs are bad at that all seem to have the same cause. I wanted an article I could reference when this comes up, so I wrote one. LLMs can't count the number of R's in strawberry. LLMs …| Brendan Long
A few jobs ago, I worked at company that collected data from disparate sources, then processed and deduplicated it into spreadsheets for ingestion by the data science and customer support teams. Some common questions the engineering team got were: Why is the data in some input CSV missing in the output? Why is data in the output CSV not matching what we expect? To debug these problems, the process was to try to reverse engineer where the data came from, then try to guess which path that data ...| Brendan Long
In a recent post, Zvi described what he calls "The Most Forbidden Technique":An AI produces a final output [X] via some method [M]. You can analyze [M] using technique [T], to learn what the AI is up to. You could train on that. Never do that.You train on [X]. Only [X]. Never [M], never [T]. The article specifically discusses this in relation to reasoning models and Chain of Thought (CoT): if we train a model not to admit to lying in its CoT, it might still lie in the CoT and just not tell us...| Brendan Long
When you're subject to capital gains taxation, the government shares in some of the upside, but when you have capital losses, the government shares in the downside too. Because of this, the actual risk (and reward) of any given portfolio is lower than it seems. To counteract this, you should consider shifting your allocation toward riskier assets.| Brendan Long
7 years ago (!) I wrote a post comparing ZIP and tar, plus gz or xz, and concluded that ZIP is ideal if you need to quickly access individual files in the compressed archive, and tar + compression (like tar + xz) is ideal if you need maximum compression. Since then, I discovered pixz, which seems to provide the best of both worlds: Maximum compression with indexing for quick seeking.| Brendan Long
I've been working on an OCaml library to read XLSX files, and something I thought was odd is that all strings in an Excel workbook are listed in a "shared strings" file and then referenced by index. This seemed strange to me, since I would expect the compression algorithm to do this kind of work for you, but thinking about it made me better understand why that's necessary, and also what the advantages and disadvantages of the ZIP and tar + compression formats are.| Brendan Long