veganism.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Veganism Social is a welcoming space on the internet for vegans to connect and engage with the broader decentralized social media community.

Administered by:

Server stats:

295
active users

#gptel

0 posts0 participants0 posts today
Phil<p><code>gptel-org-tools</code><span> update.<br><br>Edit: there's some kind of issue with </span><a href="https://social.anoxinon.de/@Codeberg" class="u-url mention" rel="nofollow noopener" target="_blank">@Codeberg@social.anoxinon.de</a> which prevents the link from working (returns 404). The <i>old</i> (but up to date) repo is here: <a href="https://git.bajsicki.com/phil/gptel-org-tools" rel="nofollow noopener" target="_blank">https://git.bajsicki.com/phil/gptel-org-tools</a><span><br><br>1. Cloned to </span><a href="https://codeberg.org/bajsicki/gptel-org-tools" rel="nofollow noopener" target="_blank">https://codeberg.org/bajsicki/gptel-org-tools</a><span>, and all future work will be happening on Codeberg. <br>2. Added </span><code>gptel-org-tools-result-limit</code><span> and a helper function for it. This sets a hard limit on the number of characters a tool can return. If it's over that, the LLM is prompted to be more specific in its query. Not applied to all tools, just the ones that are likely to blow up the context window. <br>3. Added docstrings for the functions called by the tools, so LLMs can look up their definitions.<br>4. Improved the precision of some tool descriptions so instructions are easier to follow.<br>5. Some minor improvements w/r/t function names and calls, logic, etc. Basic QA.<br><br>Now, as a user: <br>1. I'm finding it increasingly frustrating that Gemma 3 refuses to follow instructions. So here's a PSA: Gemma 3 doesn't respect the system prompt. It treats it just the same as any other user input. <br>2. Mistral 24B is a mixed bag. I'm not sure if it's my settings or something else, but it fairly consistently ends up looping; it'll call the same tool over and over again with the exact same arguments. This happens with other models as well, but not nearly as frequently.<br>3. Qwen 2.5 14B: pretty dang good, I'd say. The Cogito fine-tune is also surprisingly usable.<br>4. Prompting: I have found that a good, detailed system prompt tends to /somewhat/ improve results, especially if it contains clear directions on where to look for things related to specific topics. I'm still in the middle of writing one that's accurate to my Emacs set-up, but when I do finish it, it'll be in the repository as an example.<br>5. One issue that I still struggle with is that the LLMs don't take any time to process the user request. Often they'll find some relevant information in one file, and then decide that's enough and just refuse to look any further. Often devolving into traversing directories /as if/ they're looking for something... and they get stuck doing that without end. <br><br>It all boils down to the fact that LLMs aren't intelligent, so while I have a reasonable foundation for the data collection, the major focus is on creating guardrails, processes and inescapable sequences. These will (ideally) railroad LLMs into doing actual research and processing before they deliver a summary/ report based on the org-mode notes I have.<br><br>Tags:<br></span><a href="https://fed.bajsicki.com/tags/Emacs" rel="nofollow noopener" target="_blank">#Emacs</a> <a href="https://fed.bajsicki.com/tags/gptel" rel="nofollow noopener" target="_blank">#gptel</a> <a href="https://fed.bajsicki.com/tags/codeberg" rel="nofollow noopener" target="_blank">#codeberg</a> <a href="https://fed.bajsicki.com/tags/forgejo" rel="nofollow noopener" target="_blank">#forgejo</a> <a href="https://fed.bajsicki.com/tags/orgmode" rel="nofollow noopener" target="_blank">#orgmode</a> <a href="https://fed.bajsicki.com/tags/orgql" rel="nofollow noopener" target="_blank">#orgql</a> <a href="https://fed.bajsicki.com/tags/llm" rel="nofollow noopener" target="_blank">#llm</a> <a href="https://fed.bajsicki.com/tags/ai" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://fed.bajsicki.com/tags/informationmanagement" rel="nofollow noopener" target="_blank">#informationmanagement</a> <a href="https://fed.bajsicki.com/tags/gptelorgtools" rel="nofollow noopener" target="_blank">#gptelorgtools</a></p>
Phil<p>So currently I'm hosting <code>gptel-org-tools</code><span> on my own forge... <br><br></span><a href="https://git.bajsicki.com/phil/gptel-org-tools" rel="nofollow noopener" target="_blank">https://git.bajsicki.com/phil/gptel-org-tools</a><span><br><br>I can't seem to find a good way for people to create issues.<br><br>I thought that creating issues via email was a thing with Forgejo, but it appears not. <br><br>So here's a poll. Despite my hatred of Microsoft, is it for the best to move the repo to GitHub? <br><br>Or is there some way to federate with GitHub users so I don't need to open public sign-ups on my git? <br><br>I'm not exactly clear on what the move is here.<br><br></span><a href="https://fed.bajsicki.com/tags/Emacs" rel="nofollow noopener" target="_blank">#Emacs</a> <a href="https://fed.bajsicki.com/tags/gptel" rel="nofollow noopener" target="_blank">#gptel</a> <a href="https://fed.bajsicki.com/tags/gitforge" rel="nofollow noopener" target="_blank">#gitforge</a> <a href="https://fed.bajsicki.com/tags/forgejo" rel="nofollow noopener" target="_blank">#forgejo</a> <a href="https://fed.bajsicki.com/tags/github" rel="nofollow noopener" target="_blank">#github</a> <a href="https://fed.bajsicki.com/tags/microsoft" rel="nofollow noopener" target="_blank">#microsoft</a> <a href="https://fed.bajsicki.com/tags/foss" rel="nofollow noopener" target="_blank">#foss</a></p>
oatmeal<p><span class="h-card" translate="no"><a href="https://front-end.social/@DodoTheDev" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>DodoTheDev</span></a></span> in respect to mobile, I guess it depends on what you’re doing with the mobile client? Mostly viewing or you need to edit too? </p><p>Syncthing should solve syncing any type of non virtual file, and now has an astounding iOS client. If you write in markdown any client should do on iOS for basic editing, and there are couple of org clients for basic editing or task management (orgro, scratch, plain org, journelly, beorg). I rarely edit on my phone. </p><p>Emacs learning curve can be mitigated by starting with a configuration framework like doom or other. It’s not different than learning any other new software you pick up. Hopefully not being to use Ctl-c Ctl-v in emacs is not a showstopper, though there’s a package for that too… </p><p>The return on the initial investment in learning <a href="https://kolektiva.social/tags/emacs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>emacs</span></a> is unmeasurable. Just have a look at the expanding ecosystem of <a href="https://kolektiva.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> packages to start with… from <a href="https://kolektiva.social/tags/gptel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>gptel</span></a> to ollama-buddy etc.</p>